summaryrefslogtreecommitdiffstatshomepage
diff options
context:
space:
mode:
authorJason A. Donenfeld <Jason@zx2c4.com>2018-09-08 22:25:32 -0600
committerJason A. Donenfeld <Jason@zx2c4.com>2018-09-10 18:03:52 -0600
commit7789701ee2ca6afabe044632d030bfcf883eaa12 (patch)
tree25d4a782cc82e8357ef3aef5d396c0e25516424a
parentpoly1305: rewrite self tests from scratch (diff)
downloadwireguard-monolithic-historical-7789701ee2ca6afabe044632d030bfcf883eaa12.tar.xz
wireguard-monolithic-historical-7789701ee2ca6afabe044632d030bfcf883eaa12.zip
poly1305: switch to donna
-rw-r--r--src/crypto/zinc/poly1305/poly1305-donna32.h198
-rw-r--r--src/crypto/zinc/poly1305/poly1305-donna64.h177
-rw-r--r--src/crypto/zinc/poly1305/poly1305.c206
3 files changed, 398 insertions, 183 deletions
diff --git a/src/crypto/zinc/poly1305/poly1305-donna32.h b/src/crypto/zinc/poly1305/poly1305-donna32.h
new file mode 100644
index 0000000..1decb33
--- /dev/null
+++ b/src/crypto/zinc/poly1305/poly1305-donna32.h
@@ -0,0 +1,198 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is based in part on Andrew Moon's poly1305-donna, which is in the
+ * public domain.
+ */
+
+struct poly1305_internal {
+ u32 h[5];
+ u32 r[5];
+};
+
+static void poly1305_init_generic(void *ctx, const u8 key[16])
+{
+ struct poly1305_internal *st = (struct poly1305_internal *)ctx;
+
+ /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+ st->r[0] = (get_unaligned_le32(&key[0])) & 0x3ffffff;
+ st->r[1] = (get_unaligned_le32(&key[3]) >> 2) & 0x3ffff03;
+ st->r[2] = (get_unaligned_le32(&key[6]) >> 4) & 0x3ffc0ff;
+ st->r[3] = (get_unaligned_le32(&key[9]) >> 6) & 0x3f03fff;
+ st->r[4] = (get_unaligned_le32(&key[12]) >> 8) & 0x00fffff;
+
+ /* h = 0 */
+ st->h[0] = 0;
+ st->h[1] = 0;
+ st->h[2] = 0;
+ st->h[3] = 0;
+ st->h[4] = 0;
+}
+
+static void poly1305_blocks_generic(void *ctx, const u8 *input, size_t len,
+ const u32 padbit)
+{
+ struct poly1305_internal *st = (struct poly1305_internal *)ctx;
+ const u32 hibit = padbit << 24;
+ u32 r0, r1, r2, r3, r4;
+ u32 s1, s2, s3, s4;
+ u32 h0, h1, h2, h3, h4;
+ u64 d0, d1, d2, d3, d4;
+ u32 c;
+
+ r0 = st->r[0];
+ r1 = st->r[1];
+ r2 = st->r[2];
+ r3 = st->r[3];
+ r4 = st->r[4];
+
+ s1 = r1 * 5;
+ s2 = r2 * 5;
+ s3 = r3 * 5;
+ s4 = r4 * 5;
+
+ h0 = st->h[0];
+ h1 = st->h[1];
+ h2 = st->h[2];
+ h3 = st->h[3];
+ h4 = st->h[4];
+
+ while (len >= POLY1305_BLOCK_SIZE) {
+ /* h += m[i] */
+ h0 += (get_unaligned_le32(&input[0])) & 0x3ffffff;
+ h1 += (get_unaligned_le32(&input[3]) >> 2) & 0x3ffffff;
+ h2 += (get_unaligned_le32(&input[6]) >> 4) & 0x3ffffff;
+ h3 += (get_unaligned_le32(&input[9]) >> 6) & 0x3ffffff;
+ h4 += (get_unaligned_le32(&input[12]) >> 8) | hibit;
+
+ /* h *= r */
+ d0 = ((u64)h0 * r0) + ((u64)h1 * s4) +
+ ((u64)h2 * s3) + ((u64)h3 * s2) +
+ ((u64)h4 * s1);
+ d1 = ((u64)h0 * r1) + ((u64)h1 * r0) +
+ ((u64)h2 * s4) + ((u64)h3 * s3) +
+ ((u64)h4 * s2);
+ d2 = ((u64)h0 * r2) + ((u64)h1 * r1) +
+ ((u64)h2 * r0) + ((u64)h3 * s4) +
+ ((u64)h4 * s3);
+ d3 = ((u64)h0 * r3) + ((u64)h1 * r2) +
+ ((u64)h2 * r1) + ((u64)h3 * r0) +
+ ((u64)h4 * s4);
+ d4 = ((u64)h0 * r4) + ((u64)h1 * r3) +
+ ((u64)h2 * r2) + ((u64)h3 * r1) +
+ ((u64)h4 * r0);
+
+ /* (partial) h %= p */
+ c = (u32)(d0 >> 26);
+ h0 = (u32)d0 & 0x3ffffff;
+ d1 += c;
+ c = (u32)(d1 >> 26);
+ h1 = (u32)d1 & 0x3ffffff;
+ d2 += c;
+ c = (u32)(d2 >> 26);
+ h2 = (u32)d2 & 0x3ffffff;
+ d3 += c;
+ c = (u32)(d3 >> 26);
+ h3 = (u32)d3 & 0x3ffffff;
+ d4 += c;
+ c = (u32)(d4 >> 26);
+ h4 = (u32)d4 & 0x3ffffff;
+ h0 += c * 5;
+ c = (h0 >> 26);
+ h0 = h0 & 0x3ffffff;
+ h1 += c;
+
+ input += POLY1305_BLOCK_SIZE;
+ len -= POLY1305_BLOCK_SIZE;
+ }
+
+ st->h[0] = h0;
+ st->h[1] = h1;
+ st->h[2] = h2;
+ st->h[3] = h3;
+ st->h[4] = h4;
+}
+
+static void poly1305_emit_generic(void *ctx, u8 mac[16], const u32 nonce[4])
+{
+ struct poly1305_internal *st = (struct poly1305_internal *)ctx;
+ u32 h0, h1, h2, h3, h4, c;
+ u32 g0, g1, g2, g3, g4;
+ u64 f;
+ u32 mask;
+
+ /* fully carry h */
+ h0 = st->h[0];
+ h1 = st->h[1];
+ h2 = st->h[2];
+ h3 = st->h[3];
+ h4 = st->h[4];
+
+ c = h1 >> 26;
+ h1 = h1 & 0x3ffffff;
+ h2 += c;
+ c = h2 >> 26;
+ h2 = h2 & 0x3ffffff;
+ h3 += c;
+ c = h3 >> 26;
+ h3 = h3 & 0x3ffffff;
+ h4 += c;
+ c = h4 >> 26;
+ h4 = h4 & 0x3ffffff;
+ h0 += c * 5;
+ c = h0 >> 26;
+ h0 = h0 & 0x3ffffff;
+ h1 += c;
+
+ /* compute h + -p */
+ g0 = h0 + 5;
+ c = g0 >> 26;
+ g0 &= 0x3ffffff;
+ g1 = h1 + c;
+ c = g1 >> 26;
+ g1 &= 0x3ffffff;
+ g2 = h2 + c;
+ c = g2 >> 26;
+ g2 &= 0x3ffffff;
+ g3 = h3 + c;
+ c = g3 >> 26;
+ g3 &= 0x3ffffff;
+ g4 = h4 + c - (1UL << 26);
+
+ /* select h if h < p, or h + -p if h >= p */
+ mask = (g4 >> ((sizeof(u32) * 8) - 1)) - 1;
+ g0 &= mask;
+ g1 &= mask;
+ g2 &= mask;
+ g3 &= mask;
+ g4 &= mask;
+ mask = ~mask;
+
+ h0 = (h0 & mask) | g0;
+ h1 = (h1 & mask) | g1;
+ h2 = (h2 & mask) | g2;
+ h3 = (h3 & mask) | g3;
+ h4 = (h4 & mask) | g4;
+
+ /* h = h % (2^128) */
+ h0 = ((h0) | (h1 << 26)) & 0xffffffff;
+ h1 = ((h1 >> 6) | (h2 << 20)) & 0xffffffff;
+ h2 = ((h2 >> 12) | (h3 << 14)) & 0xffffffff;
+ h3 = ((h3 >> 18) | (h4 << 8)) & 0xffffffff;
+
+ /* mac = (h + nonce) % (2^128) */
+ f = (u64)h0 + nonce[0];
+ h0 = (u32)f;
+ f = (u64)h1 + nonce[1] + (f >> 32);
+ h1 = (u32)f;
+ f = (u64)h2 + nonce[2] + (f >> 32);
+ h2 = (u32)f;
+ f = (u64)h3 + nonce[3] + (f >> 32);
+ h3 = (u32)f;
+
+ put_unaligned_le32(h0, &mac[0]);
+ put_unaligned_le32(h1, &mac[4]);
+ put_unaligned_le32(h2, &mac[8]);
+ put_unaligned_le32(h3, &mac[12]);
+}
diff --git a/src/crypto/zinc/poly1305/poly1305-donna64.h b/src/crypto/zinc/poly1305/poly1305-donna64.h
new file mode 100644
index 0000000..2aa2570
--- /dev/null
+++ b/src/crypto/zinc/poly1305/poly1305-donna64.h
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * This is based in part on Andrew Moon's poly1305-donna, which is in the
+ * public domain.
+ */
+
+typedef __uint128_t u128;
+
+struct poly1305_internal {
+ u64 r[3];
+ u64 h[3];
+};
+
+static void poly1305_init_generic(void *ctx, const u8 key[16])
+{
+ struct poly1305_internal *st = (struct poly1305_internal *)ctx;
+ u64 t0, t1;
+
+ /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
+ t0 = get_unaligned_le64(&key[0]);
+ t1 = get_unaligned_le64(&key[8]);
+
+ st->r[0] = t0 & 0xffc0fffffff;
+ st->r[1] = ((t0 >> 44) | (t1 << 20)) & 0xfffffc0ffff;
+ st->r[2] = ((t1 >> 24)) & 0x00ffffffc0f;
+
+ /* h = 0 */
+ st->h[0] = 0;
+ st->h[1] = 0;
+ st->h[2] = 0;
+}
+
+static void poly1305_blocks_generic(void *ctx, const u8 *input, size_t len,
+ const u32 padbit)
+{
+ struct poly1305_internal *st = (struct poly1305_internal *)ctx;
+ const u64 hibit = ((u64)padbit) << 40;
+ u64 r0, r1, r2;
+ u64 s1, s2;
+ u64 h0, h1, h2;
+ u64 c;
+ u128 d0, d1, d2, d;
+
+ r0 = st->r[0];
+ r1 = st->r[1];
+ r2 = st->r[2];
+
+ h0 = st->h[0];
+ h1 = st->h[1];
+ h2 = st->h[2];
+
+ s1 = r1 * (5 << 2);
+ s2 = r2 * (5 << 2);
+
+ while (len >= POLY1305_BLOCK_SIZE) {
+ u64 t0, t1;
+
+ /* h += m[i] */
+ t0 = get_unaligned_le64(&input[0]);
+ t1 = get_unaligned_le64(&input[8]);
+
+ h0 += t0 & 0xfffffffffff;
+ h1 += ((t0 >> 44) | (t1 << 20)) & 0xfffffffffff;
+ h2 += (((t1 >> 24)) & 0x3ffffffffff) | hibit;
+
+ /* h *= r */
+ d0 = (u128)h0 * r0;
+ d = (u128)h1 * s2;
+ d0 += d;
+ d = (u128)h2 * s1;
+ d0 += d;
+ d1 = (u128)h0 * r1;
+ d = (u128)h1 * r0;
+ d1 += d;
+ d = (u128)h2 * s2;
+ d1 += d;
+ d2 = (u128)h0 * r2;
+ d = (u128)h1 * r1;
+ d2 += d;
+ d = (u128)h2 * r0;
+ d2 += d;
+
+ /* (partial) h %= p */
+ c = (u64)(d0 >> 44);
+ h0 = (u64)d0 & 0xfffffffffff;
+ d1 += c;
+ c = (u64)(d1 >> 44);
+ h1 = (u64)d1 & 0xfffffffffff;
+ d2 += c;
+ c = (u64)(d2 >> 42);
+ h2 = (u64)d2 & 0x3ffffffffff;
+ h0 += c * 5;
+ c = h0 >> 44;
+ h0 = h0 & 0xfffffffffff;
+ h1 += c;
+
+ input += POLY1305_BLOCK_SIZE;
+ len -= POLY1305_BLOCK_SIZE;
+ }
+
+ st->h[0] = h0;
+ st->h[1] = h1;
+ st->h[2] = h2;
+}
+
+static void poly1305_emit_generic(void *ctx, u8 mac[16], const u32 nonce[4])
+{
+ struct poly1305_internal *st = (struct poly1305_internal *)ctx;
+ u64 h0, h1, h2, c;
+ u64 g0, g1, g2;
+ u64 t0, t1;
+
+ /* fully carry h */
+ h0 = st->h[0];
+ h1 = st->h[1];
+ h2 = st->h[2];
+
+ c = h1 >> 44;
+ h1 &= 0xfffffffffff;
+ h2 += c;
+ c = h2 >> 42;
+ h2 &= 0x3ffffffffff;
+ h0 += c * 5;
+ c = h0 >> 44;
+ h0 &= 0xfffffffffff;
+ h1 += c;
+ c = h1 >> 44;
+ h1 &= 0xfffffffffff;
+ h2 += c;
+ c = h2 >> 42;
+ h2 &= 0x3ffffffffff;
+ h0 += c * 5;
+ c = h0 >> 44;
+ h0 &= 0xfffffffffff;
+ h1 += c;
+
+ /* compute h + -p */
+ g0 = h0 + 5;
+ c = g0 >> 44;
+ g0 &= 0xfffffffffff;
+ g1 = h1 + c;
+ c = g1 >> 44;
+ g1 &= 0xfffffffffff;
+ g2 = h2 + c - (1ULL << 42);
+
+ /* select h if h < p, or h + -p if h >= p */
+ c = (g2 >> ((sizeof(u64) * 8) - 1)) - 1;
+ g0 &= c;
+ g1 &= c;
+ g2 &= c;
+ c = ~c;
+ h0 = (h0 & c) | g0;
+ h1 = (h1 & c) | g1;
+ h2 = (h2 & c) | g2;
+
+ /* h = (h + nonce) */
+ t0 = ((u64)nonce[1] << 32) | nonce[0];
+ t1 = ((u64)nonce[3] << 32) | nonce[2];
+
+ h0 += t0 & 0xfffffffffff;
+ c = h0 >> 44;
+ h0 &= 0xfffffffffff;
+ h1 += (((t0 >> 44) | (t1 << 20)) & 0xfffffffffff) + c;
+ c = h1 >> 44;
+ h1 &= 0xfffffffffff;
+ h2 += (((t1 >> 24)) & 0x3ffffffffff) + c;
+ h2 &= 0x3ffffffffff;
+
+ /* mac = h % (2^128) */
+ h0 = h0 | (h1 << 44);
+ h1 = (h1 >> 20) | (h2 << 24);
+
+ put_unaligned_le64(h0, &mac[0]);
+ put_unaligned_le64(h1, &mac[8]);
+}
diff --git a/src/crypto/zinc/poly1305/poly1305.c b/src/crypto/zinc/poly1305/poly1305.c
index fd662de..c09b092 100644
--- a/src/crypto/zinc/poly1305/poly1305.c
+++ b/src/crypto/zinc/poly1305/poly1305.c
@@ -1,9 +1,6 @@
-/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0
*
* Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
- *
- * This is based in part on Andy Polyakov's implementation from CRYPTOGAMS.
*
* Implementation of the Poly1305 message authenticator.
*
@@ -23,7 +20,7 @@ static inline bool poly1305_init_arch(void *ctx,
{
return false;
}
-static inline bool poly1305_blocks_arch(void *ctx, const u8 *inp,
+static inline bool poly1305_blocks_arch(void *ctx, const u8 *input,
const size_t len, const u32 padbit,
simd_context_t simd_context)
{
@@ -40,166 +37,11 @@ void __init poly1305_fpu_init(void)
}
#endif
-struct poly1305_internal {
- u32 h[5];
- u32 r[4];
-};
-
-static void poly1305_init_generic(void *ctx, const u8 key[16])
-{
- struct poly1305_internal *st = (struct poly1305_internal *)ctx;
-
- /* h = 0 */
- st->h[0] = 0;
- st->h[1] = 0;
- st->h[2] = 0;
- st->h[3] = 0;
- st->h[4] = 0;
-
- /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
- st->r[0] = get_unaligned_le32(&key[ 0]) & 0x0fffffff;
- st->r[1] = get_unaligned_le32(&key[ 4]) & 0x0ffffffc;
- st->r[2] = get_unaligned_le32(&key[ 8]) & 0x0ffffffc;
- st->r[3] = get_unaligned_le32(&key[12]) & 0x0ffffffc;
-}
-
-static void poly1305_blocks_generic(void *ctx, const u8 *inp, size_t len,
- const u32 padbit)
-{
-#define CONSTANT_TIME_CARRY(a, b) \
- ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1))
- struct poly1305_internal *st = (struct poly1305_internal *)ctx;
- u32 r0, r1, r2, r3;
- u32 s1, s2, s3;
- u32 h0, h1, h2, h3, h4, c;
- u64 d0, d1, d2, d3;
-
- r0 = st->r[0];
- r1 = st->r[1];
- r2 = st->r[2];
- r3 = st->r[3];
-
- s1 = r1 + (r1 >> 2);
- s2 = r2 + (r2 >> 2);
- s3 = r3 + (r3 >> 2);
-
- h0 = st->h[0];
- h1 = st->h[1];
- h2 = st->h[2];
- h3 = st->h[3];
- h4 = st->h[4];
-
- while (len >= POLY1305_BLOCK_SIZE) {
- /* h += m[i] */
- h0 = (u32)(d0 = (u64)h0 + (0 ) + get_unaligned_le32(&inp[ 0]));
- h1 = (u32)(d1 = (u64)h1 + (d0 >> 32) + get_unaligned_le32(&inp[ 4]));
- h2 = (u32)(d2 = (u64)h2 + (d1 >> 32) + get_unaligned_le32(&inp[ 8]));
- h3 = (u32)(d3 = (u64)h3 + (d2 >> 32) + get_unaligned_le32(&inp[12]));
- h4 += (u32)(d3 >> 32) + padbit;
-
- /* h *= r "%" p, where "%" stands for "partial remainder" */
- d0 = ((u64)h0 * r0) +
- ((u64)h1 * s3) +
- ((u64)h2 * s2) +
- ((u64)h3 * s1);
- d1 = ((u64)h0 * r1) +
- ((u64)h1 * r0) +
- ((u64)h2 * s3) +
- ((u64)h3 * s2) +
- (h4 * s1);
- d2 = ((u64)h0 * r2) +
- ((u64)h1 * r1) +
- ((u64)h2 * r0) +
- ((u64)h3 * s3) +
- (h4 * s2);
- d3 = ((u64)h0 * r3) +
- ((u64)h1 * r2) +
- ((u64)h2 * r1) +
- ((u64)h3 * r0) +
- (h4 * s3);
- h4 = (h4 * r0);
-
- /* last reduction step: */
- /* a) h4:h0 = h4<<128 + d3<<96 + d2<<64 + d1<<32 + d0 */
- h0 = (u32)d0;
- h1 = (u32)(d1 += d0 >> 32);
- h2 = (u32)(d2 += d1 >> 32);
- h3 = (u32)(d3 += d2 >> 32);
- h4 += (u32)(d3 >> 32);
- /* b) (h4:h0 += (h4:h0>>130) * 5) %= 2^130 */
- c = (h4 >> 2) + (h4 & ~3U);
- h4 &= 3;
- h0 += c;
- h1 += (c = CONSTANT_TIME_CARRY(h0, c));
- h2 += (c = CONSTANT_TIME_CARRY(h1, c));
- h3 += (c = CONSTANT_TIME_CARRY(h2, c));
- h4 += CONSTANT_TIME_CARRY(h3, c);
- /*
- * Occasional overflows to 3rd bit of h4 are taken care of
- * "naturally". If after this point we end up at the top of
- * this loop, then the overflow bit will be accounted for
- * in next iteration. If we end up in poly1305_emit, then
- * comparison to modulus below will still count as "carry
- * into 131st bit", so that properly reduced value will be
- * picked in conditional move.
- */
-
- inp += POLY1305_BLOCK_SIZE;
- len -= POLY1305_BLOCK_SIZE;
- }
-
- st->h[0] = h0;
- st->h[1] = h1;
- st->h[2] = h2;
- st->h[3] = h3;
- st->h[4] = h4;
-#undef CONSTANT_TIME_CARRY
-}
-
-static void poly1305_emit_generic(void *ctx, u8 mac[16], const u32 nonce[4])
-{
- struct poly1305_internal *st = (struct poly1305_internal *)ctx;
- u32 h0, h1, h2, h3, h4;
- u32 g0, g1, g2, g3, g4;
- u64 t;
- u32 mask;
-
- h0 = st->h[0];
- h1 = st->h[1];
- h2 = st->h[2];
- h3 = st->h[3];
- h4 = st->h[4];
-
- /* compare to modulus by computing h + -p */
- g0 = (u32)(t = (u64)h0 + 5);
- g1 = (u32)(t = (u64)h1 + (t >> 32));
- g2 = (u32)(t = (u64)h2 + (t >> 32));
- g3 = (u32)(t = (u64)h3 + (t >> 32));
- g4 = h4 + (u32)(t >> 32);
-
- /* if there was carry into 131st bit, h3:h0 = g3:g0 */
- mask = 0 - (g4 >> 2);
- g0 &= mask;
- g1 &= mask;
- g2 &= mask;
- g3 &= mask;
- mask = ~mask;
- h0 = (h0 & mask) | g0;
- h1 = (h1 & mask) | g1;
- h2 = (h2 & mask) | g2;
- h3 = (h3 & mask) | g3;
-
- /* mac = (h + nonce) % (2^128) */
- h0 = (u32)(t = (u64)h0 + nonce[0]);
- h1 = (u32)(t = (u64)h1 + (t >> 32) + nonce[1]);
- h2 = (u32)(t = (u64)h2 + (t >> 32) + nonce[2]);
- h3 = (u32)(t = (u64)h3 + (t >> 32) + nonce[3]);
-
- put_unaligned_le32(h0, &mac[ 0]);
- put_unaligned_le32(h1, &mac[ 4]);
- put_unaligned_le32(h2, &mac[ 8]);
- put_unaligned_le32(h3, &mac[12]);
-}
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+#include "poly1305-donna64.h"
+#else
+#include "poly1305-donna32.h"
+#endif
void poly1305_init(struct poly1305_ctx *ctx, const u8 key[POLY1305_KEY_SIZE],
simd_context_t simd_context)
@@ -211,16 +53,17 @@ void poly1305_init(struct poly1305_ctx *ctx, const u8 key[POLY1305_KEY_SIZE],
if (!poly1305_init_arch(ctx->opaque, key, simd_context))
poly1305_init_generic(ctx->opaque, key);
+
ctx->num = 0;
}
EXPORT_SYMBOL(poly1305_init);
-static inline void poly1305_blocks(void *ctx, const u8 *inp, const size_t len,
+static inline void poly1305_blocks(void *ctx, const u8 *input, const size_t len,
const u32 padbit,
simd_context_t simd_context)
{
- if (!poly1305_blocks_arch(ctx, inp, len, padbit, simd_context))
- poly1305_blocks_generic(ctx, inp, len, padbit);
+ if (!poly1305_blocks_arch(ctx, input, len, padbit, simd_context))
+ poly1305_blocks_generic(ctx, input, len, padbit);
}
static inline void poly1305_emit(void *ctx, u8 mac[POLY1305_KEY_SIZE],
@@ -231,7 +74,7 @@ static inline void poly1305_emit(void *ctx, u8 mac[POLY1305_KEY_SIZE],
poly1305_emit_generic(ctx, mac, nonce);
}
-void poly1305_update(struct poly1305_ctx *ctx, const u8 *inp, size_t len,
+void poly1305_update(struct poly1305_ctx *ctx, const u8 *input, size_t len,
simd_context_t simd_context)
{
const size_t num = ctx->num % POLY1305_BLOCK_SIZE;
@@ -239,30 +82,28 @@ void poly1305_update(struct poly1305_ctx *ctx, const u8 *inp, size_t len,
if (num) {
rem = POLY1305_BLOCK_SIZE - num;
- if (len >= rem) {
- memcpy(ctx->data + num, inp, rem);
- poly1305_blocks(ctx->opaque, ctx->data,
- POLY1305_BLOCK_SIZE, 1, simd_context);
- inp += rem;
- len -= rem;
- } else {
- /* Still not enough data to process a block. */
- memcpy(ctx->data + num, inp, len);
+ if (len < rem) {
+ memcpy(ctx->data + num, input, len);
ctx->num = num + len;
return;
}
+ memcpy(ctx->data + num, input, rem);
+ poly1305_blocks(ctx->opaque, ctx->data, POLY1305_BLOCK_SIZE, 1,
+ simd_context);
+ input += rem;
+ len -= rem;
}
rem = len % POLY1305_BLOCK_SIZE;
len -= rem;
if (len >= POLY1305_BLOCK_SIZE) {
- poly1305_blocks(ctx->opaque, inp, len, 1, simd_context);
- inp += len;
+ poly1305_blocks(ctx->opaque, input, len, 1, simd_context);
+ input += len;
}
if (rem)
- memcpy(ctx->data, inp, rem);
+ memcpy(ctx->data, input, rem);
ctx->num = rem;
}
@@ -274,7 +115,7 @@ void poly1305_finish(struct poly1305_ctx *ctx, u8 mac[POLY1305_MAC_SIZE],
size_t num = ctx->num % POLY1305_BLOCK_SIZE;
if (num) {
- ctx->data[num++] = 1; /* pad bit */
+ ctx->data[num++] = 1;
while (num < POLY1305_BLOCK_SIZE)
ctx->data[num++] = 0;
poly1305_blocks(ctx->opaque, ctx->data, POLY1305_BLOCK_SIZE, 0,
@@ -283,7 +124,6 @@ void poly1305_finish(struct poly1305_ctx *ctx, u8 mac[POLY1305_MAC_SIZE],
poly1305_emit(ctx->opaque, mac, ctx->nonce, simd_context);
- /* zero out the state */
memzero_explicit(ctx, sizeof(*ctx));
}
EXPORT_SYMBOL(poly1305_finish);