linux/arch/arm64/crypto/crct10dif-ce-core.S

537 lines
16 KiB
ArmAsm

//
// Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
//
// Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
// Copyright (C) 2019 Google LLC <ebiggers@google.com>
//
// This program is free software; you can redistribute it and/or modify
// it under the terms of the GNU General Public License version 2 as
// published by the Free Software Foundation.
//
// Derived from the x86 version:
//
// Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
//
// Copyright (c) 2013, Intel Corporation
//
// Authors:
// Erdinc Ozturk <erdinc.ozturk@intel.com>
// Vinodh Gopal <vinodh.gopal@intel.com>
// James Guilford <james.guilford@intel.com>
// Tim Chen <tim.c.chen@linux.intel.com>
//
// This software is available to you under a choice of one of two
// licenses. You may choose to be licensed under the terms of the GNU
// General Public License (GPL) Version 2, available from the file
// COPYING in the main directory of this source tree, or the
// OpenIB.org BSD license below:
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the
// distribution.
//
// * Neither the name of the Intel Corporation nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
//
// THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
// LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
// SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Reference paper titled "Fast CRC Computation for Generic
// Polynomials Using PCLMULQDQ Instruction"
// URL: http://www.intel.com/content/dam/www/public/us/en/documents
// /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
//
#include <linux/linkage.h>
#include <asm/assembler.h>
.text
.arch armv8-a+crypto
init_crc .req w19
buf .req x20
len .req x21
fold_consts_ptr .req x22
fold_consts .req v10
ad .req v14
k00_16 .req v15
k32_48 .req v16
t3 .req v17
t4 .req v18
t5 .req v19
t6 .req v20
t7 .req v21
t8 .req v22
t9 .req v23
perm1 .req v24
perm2 .req v25
perm3 .req v26
perm4 .req v27
bd1 .req v28
bd2 .req v29
bd3 .req v30
bd4 .req v31
.macro __pmull_init_p64
.endm
.macro __pmull_pre_p64, bd
.endm
.macro __pmull_init_p8
// k00_16 := 0x0000000000000000_000000000000ffff
// k32_48 := 0x00000000ffffffff_0000ffffffffffff
movi k32_48.2d, #0xffffffff
mov k32_48.h[2], k32_48.h[0]
ushr k00_16.2d, k32_48.2d, #32
// prepare the permutation vectors
mov_q x5, 0x080f0e0d0c0b0a09
movi perm4.8b, #8
dup perm1.2d, x5
eor perm1.16b, perm1.16b, perm4.16b
ushr perm2.2d, perm1.2d, #8
ushr perm3.2d, perm1.2d, #16
ushr perm4.2d, perm1.2d, #24
sli perm2.2d, perm1.2d, #56
sli perm3.2d, perm1.2d, #48
sli perm4.2d, perm1.2d, #40
.endm
.macro __pmull_pre_p8, bd
tbl bd1.16b, {\bd\().16b}, perm1.16b
tbl bd2.16b, {\bd\().16b}, perm2.16b
tbl bd3.16b, {\bd\().16b}, perm3.16b
tbl bd4.16b, {\bd\().16b}, perm4.16b
.endm
SYM_FUNC_START_LOCAL(__pmull_p8_core)
.L__pmull_p8_core:
ext t4.8b, ad.8b, ad.8b, #1 // A1
ext t5.8b, ad.8b, ad.8b, #2 // A2
ext t6.8b, ad.8b, ad.8b, #3 // A3
pmull t4.8h, t4.8b, fold_consts.8b // F = A1*B
pmull t8.8h, ad.8b, bd1.8b // E = A*B1
pmull t5.8h, t5.8b, fold_consts.8b // H = A2*B
pmull t7.8h, ad.8b, bd2.8b // G = A*B2
pmull t6.8h, t6.8b, fold_consts.8b // J = A3*B
pmull t9.8h, ad.8b, bd3.8b // I = A*B3
pmull t3.8h, ad.8b, bd4.8b // K = A*B4
b 0f
.L__pmull_p8_core2:
tbl t4.16b, {ad.16b}, perm1.16b // A1
tbl t5.16b, {ad.16b}, perm2.16b // A2
tbl t6.16b, {ad.16b}, perm3.16b // A3
pmull2 t4.8h, t4.16b, fold_consts.16b // F = A1*B
pmull2 t8.8h, ad.16b, bd1.16b // E = A*B1
pmull2 t5.8h, t5.16b, fold_consts.16b // H = A2*B
pmull2 t7.8h, ad.16b, bd2.16b // G = A*B2
pmull2 t6.8h, t6.16b, fold_consts.16b // J = A3*B
pmull2 t9.8h, ad.16b, bd3.16b // I = A*B3
pmull2 t3.8h, ad.16b, bd4.16b // K = A*B4
0: eor t4.16b, t4.16b, t8.16b // L = E + F
eor t5.16b, t5.16b, t7.16b // M = G + H
eor t6.16b, t6.16b, t9.16b // N = I + J
uzp1 t8.2d, t4.2d, t5.2d
uzp2 t4.2d, t4.2d, t5.2d
uzp1 t7.2d, t6.2d, t3.2d
uzp2 t6.2d, t6.2d, t3.2d
// t4 = (L) (P0 + P1) << 8
// t5 = (M) (P2 + P3) << 16
eor t8.16b, t8.16b, t4.16b
and t4.16b, t4.16b, k32_48.16b
// t6 = (N) (P4 + P5) << 24
// t7 = (K) (P6 + P7) << 32
eor t7.16b, t7.16b, t6.16b
and t6.16b, t6.16b, k00_16.16b
eor t8.16b, t8.16b, t4.16b
eor t7.16b, t7.16b, t6.16b
zip2 t5.2d, t8.2d, t4.2d
zip1 t4.2d, t8.2d, t4.2d
zip2 t3.2d, t7.2d, t6.2d
zip1 t6.2d, t7.2d, t6.2d
ext t4.16b, t4.16b, t4.16b, #15
ext t5.16b, t5.16b, t5.16b, #14
ext t6.16b, t6.16b, t6.16b, #13
ext t3.16b, t3.16b, t3.16b, #12
eor t4.16b, t4.16b, t5.16b
eor t6.16b, t6.16b, t3.16b
ret
SYM_FUNC_END(__pmull_p8_core)
.macro __pmull_p8, rq, ad, bd, i
.ifnc \bd, fold_consts
.err
.endif
mov ad.16b, \ad\().16b
.ifb \i
pmull \rq\().8h, \ad\().8b, \bd\().8b // D = A*B
.else
pmull2 \rq\().8h, \ad\().16b, \bd\().16b // D = A*B
.endif
bl .L__pmull_p8_core\i
eor \rq\().16b, \rq\().16b, t4.16b
eor \rq\().16b, \rq\().16b, t6.16b
.endm
// Fold reg1, reg2 into the next 32 data bytes, storing the result back
// into reg1, reg2.
.macro fold_32_bytes, p, reg1, reg2
ldp q11, q12, [buf], #0x20
__pmull_\p v8, \reg1, fold_consts, 2
__pmull_\p \reg1, \reg1, fold_consts
CPU_LE( rev64 v11.16b, v11.16b )
CPU_LE( rev64 v12.16b, v12.16b )
__pmull_\p v9, \reg2, fold_consts, 2
__pmull_\p \reg2, \reg2, fold_consts
CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 )
CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
eor \reg1\().16b, \reg1\().16b, v8.16b
eor \reg2\().16b, \reg2\().16b, v9.16b
eor \reg1\().16b, \reg1\().16b, v11.16b
eor \reg2\().16b, \reg2\().16b, v12.16b
.endm
// Fold src_reg into dst_reg, optionally loading the next fold constants
.macro fold_16_bytes, p, src_reg, dst_reg, load_next_consts
__pmull_\p v8, \src_reg, fold_consts
__pmull_\p \src_reg, \src_reg, fold_consts, 2
.ifnb \load_next_consts
ld1 {fold_consts.2d}, [fold_consts_ptr], #16
__pmull_pre_\p fold_consts
.endif
eor \dst_reg\().16b, \dst_reg\().16b, v8.16b
eor \dst_reg\().16b, \dst_reg\().16b, \src_reg\().16b
.endm
.macro __pmull_p64, rd, rn, rm, n
.ifb \n
pmull \rd\().1q, \rn\().1d, \rm\().1d
.else
pmull2 \rd\().1q, \rn\().2d, \rm\().2d
.endif
.endm
.macro crc_t10dif_pmull, p
frame_push 4, 128
mov init_crc, w0
mov buf, x1
mov len, x2
__pmull_init_\p
// For sizes less than 256 bytes, we can't fold 128 bytes at a time.
cmp len, #256
b.lt .Lless_than_256_bytes_\@
adr_l fold_consts_ptr, .Lfold_across_128_bytes_consts
// Load the first 128 data bytes. Byte swapping is necessary to make
// the bit order match the polynomial coefficient order.
ldp q0, q1, [buf]
ldp q2, q3, [buf, #0x20]
ldp q4, q5, [buf, #0x40]
ldp q6, q7, [buf, #0x60]
add buf, buf, #0x80
CPU_LE( rev64 v0.16b, v0.16b )
CPU_LE( rev64 v1.16b, v1.16b )
CPU_LE( rev64 v2.16b, v2.16b )
CPU_LE( rev64 v3.16b, v3.16b )
CPU_LE( rev64 v4.16b, v4.16b )
CPU_LE( rev64 v5.16b, v5.16b )
CPU_LE( rev64 v6.16b, v6.16b )
CPU_LE( rev64 v7.16b, v7.16b )
CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
CPU_LE( ext v1.16b, v1.16b, v1.16b, #8 )
CPU_LE( ext v2.16b, v2.16b, v2.16b, #8 )
CPU_LE( ext v3.16b, v3.16b, v3.16b, #8 )
CPU_LE( ext v4.16b, v4.16b, v4.16b, #8 )
CPU_LE( ext v5.16b, v5.16b, v5.16b, #8 )
CPU_LE( ext v6.16b, v6.16b, v6.16b, #8 )
CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
// XOR the first 16 data *bits* with the initial CRC value.
movi v8.16b, #0
mov v8.h[7], init_crc
eor v0.16b, v0.16b, v8.16b
// Load the constants for folding across 128 bytes.
ld1 {fold_consts.2d}, [fold_consts_ptr]
__pmull_pre_\p fold_consts
// Subtract 128 for the 128 data bytes just consumed. Subtract another
// 128 to simplify the termination condition of the following loop.
sub len, len, #256
// While >= 128 data bytes remain (not counting v0-v7), fold the 128
// bytes v0-v7 into them, storing the result back into v0-v7.
.Lfold_128_bytes_loop_\@:
fold_32_bytes \p, v0, v1
fold_32_bytes \p, v2, v3
fold_32_bytes \p, v4, v5
fold_32_bytes \p, v6, v7
subs len, len, #128
b.lt .Lfold_128_bytes_loop_done_\@
if_will_cond_yield_neon
stp q0, q1, [sp, #.Lframe_local_offset]
stp q2, q3, [sp, #.Lframe_local_offset + 32]
stp q4, q5, [sp, #.Lframe_local_offset + 64]
stp q6, q7, [sp, #.Lframe_local_offset + 96]
do_cond_yield_neon
ldp q0, q1, [sp, #.Lframe_local_offset]
ldp q2, q3, [sp, #.Lframe_local_offset + 32]
ldp q4, q5, [sp, #.Lframe_local_offset + 64]
ldp q6, q7, [sp, #.Lframe_local_offset + 96]
ld1 {fold_consts.2d}, [fold_consts_ptr]
__pmull_init_\p
__pmull_pre_\p fold_consts
endif_yield_neon
b .Lfold_128_bytes_loop_\@
.Lfold_128_bytes_loop_done_\@:
// Now fold the 112 bytes in v0-v6 into the 16 bytes in v7.
// Fold across 64 bytes.
add fold_consts_ptr, fold_consts_ptr, #16
ld1 {fold_consts.2d}, [fold_consts_ptr], #16
__pmull_pre_\p fold_consts
fold_16_bytes \p, v0, v4
fold_16_bytes \p, v1, v5
fold_16_bytes \p, v2, v6
fold_16_bytes \p, v3, v7, 1
// Fold across 32 bytes.
fold_16_bytes \p, v4, v6
fold_16_bytes \p, v5, v7, 1
// Fold across 16 bytes.
fold_16_bytes \p, v6, v7
// Add 128 to get the correct number of data bytes remaining in 0...127
// (not counting v7), following the previous extra subtraction by 128.
// Then subtract 16 to simplify the termination condition of the
// following loop.
adds len, len, #(128-16)
// While >= 16 data bytes remain (not counting v7), fold the 16 bytes v7
// into them, storing the result back into v7.
b.lt .Lfold_16_bytes_loop_done_\@
.Lfold_16_bytes_loop_\@:
__pmull_\p v8, v7, fold_consts
__pmull_\p v7, v7, fold_consts, 2
eor v7.16b, v7.16b, v8.16b
ldr q0, [buf], #16
CPU_LE( rev64 v0.16b, v0.16b )
CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
eor v7.16b, v7.16b, v0.16b
subs len, len, #16
b.ge .Lfold_16_bytes_loop_\@
.Lfold_16_bytes_loop_done_\@:
// Add 16 to get the correct number of data bytes remaining in 0...15
// (not counting v7), following the previous extra subtraction by 16.
adds len, len, #16
b.eq .Lreduce_final_16_bytes_\@
.Lhandle_partial_segment_\@:
// Reduce the last '16 + len' bytes where 1 <= len <= 15 and the first
// 16 bytes are in v7 and the rest are the remaining data in 'buf'. To
// do this without needing a fold constant for each possible 'len',
// redivide the bytes into a first chunk of 'len' bytes and a second
// chunk of 16 bytes, then fold the first chunk into the second.
// v0 = last 16 original data bytes
add buf, buf, len
ldr q0, [buf, #-16]
CPU_LE( rev64 v0.16b, v0.16b )
CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
// v1 = high order part of second chunk: v7 left-shifted by 'len' bytes.
adr_l x4, .Lbyteshift_table + 16
sub x4, x4, len
ld1 {v2.16b}, [x4]
tbl v1.16b, {v7.16b}, v2.16b
// v3 = first chunk: v7 right-shifted by '16-len' bytes.
movi v3.16b, #0x80
eor v2.16b, v2.16b, v3.16b
tbl v3.16b, {v7.16b}, v2.16b
// Convert to 8-bit masks: 'len' 0x00 bytes, then '16-len' 0xff bytes.
sshr v2.16b, v2.16b, #7
// v2 = second chunk: 'len' bytes from v0 (low-order bytes),
// then '16-len' bytes from v1 (high-order bytes).
bsl v2.16b, v1.16b, v0.16b
// Fold the first chunk into the second chunk, storing the result in v7.
__pmull_\p v0, v3, fold_consts
__pmull_\p v7, v3, fold_consts, 2
eor v7.16b, v7.16b, v0.16b
eor v7.16b, v7.16b, v2.16b
.Lreduce_final_16_bytes_\@:
// Reduce the 128-bit value M(x), stored in v7, to the final 16-bit CRC.
movi v2.16b, #0 // init zero register
// Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
ld1 {fold_consts.2d}, [fold_consts_ptr], #16
__pmull_pre_\p fold_consts
// Fold the high 64 bits into the low 64 bits, while also multiplying by
// x^64. This produces a 128-bit value congruent to x^64 * M(x) and
// whose low 48 bits are 0.
ext v0.16b, v2.16b, v7.16b, #8
__pmull_\p v7, v7, fold_consts, 2 // high bits * x^48 * (x^80 mod G(x))
eor v0.16b, v0.16b, v7.16b // + low bits * x^64
// Fold the high 32 bits into the low 96 bits. This produces a 96-bit
// value congruent to x^64 * M(x) and whose low 48 bits are 0.
ext v1.16b, v0.16b, v2.16b, #12 // extract high 32 bits
mov v0.s[3], v2.s[0] // zero high 32 bits
__pmull_\p v1, v1, fold_consts // high 32 bits * x^48 * (x^48 mod G(x))
eor v0.16b, v0.16b, v1.16b // + low bits
// Load G(x) and floor(x^48 / G(x)).
ld1 {fold_consts.2d}, [fold_consts_ptr]
__pmull_pre_\p fold_consts
// Use Barrett reduction to compute the final CRC value.
__pmull_\p v1, v0, fold_consts, 2 // high 32 bits * floor(x^48 / G(x))
ushr v1.2d, v1.2d, #32 // /= x^32
__pmull_\p v1, v1, fold_consts // *= G(x)
ushr v0.2d, v0.2d, #48
eor v0.16b, v0.16b, v1.16b // + low 16 nonzero bits
// Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0.
umov w0, v0.h[0]
frame_pop
ret
.Lless_than_256_bytes_\@:
// Checksumming a buffer of length 16...255 bytes
adr_l fold_consts_ptr, .Lfold_across_16_bytes_consts
// Load the first 16 data bytes.
ldr q7, [buf], #0x10
CPU_LE( rev64 v7.16b, v7.16b )
CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
// XOR the first 16 data *bits* with the initial CRC value.
movi v0.16b, #0
mov v0.h[7], init_crc
eor v7.16b, v7.16b, v0.16b
// Load the fold-across-16-bytes constants.
ld1 {fold_consts.2d}, [fold_consts_ptr], #16
__pmull_pre_\p fold_consts
cmp len, #16
b.eq .Lreduce_final_16_bytes_\@ // len == 16
subs len, len, #32
b.ge .Lfold_16_bytes_loop_\@ // 32 <= len <= 255
add len, len, #16
b .Lhandle_partial_segment_\@ // 17 <= len <= 31
.endm
//
// u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len);
//
// Assumes len >= 16.
//
SYM_FUNC_START(crc_t10dif_pmull_p8)
crc_t10dif_pmull p8
SYM_FUNC_END(crc_t10dif_pmull_p8)
.align 5
//
// u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
//
// Assumes len >= 16.
//
SYM_FUNC_START(crc_t10dif_pmull_p64)
crc_t10dif_pmull p64
SYM_FUNC_END(crc_t10dif_pmull_p64)
.section ".rodata", "a"
.align 4
// Fold constants precomputed from the polynomial 0x18bb7
// G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
.Lfold_across_128_bytes_consts:
.quad 0x0000000000006123 // x^(8*128) mod G(x)
.quad 0x0000000000002295 // x^(8*128+64) mod G(x)
// .Lfold_across_64_bytes_consts:
.quad 0x0000000000001069 // x^(4*128) mod G(x)
.quad 0x000000000000dd31 // x^(4*128+64) mod G(x)
// .Lfold_across_32_bytes_consts:
.quad 0x000000000000857d // x^(2*128) mod G(x)
.quad 0x0000000000007acc // x^(2*128+64) mod G(x)
.Lfold_across_16_bytes_consts:
.quad 0x000000000000a010 // x^(1*128) mod G(x)
.quad 0x0000000000001faa // x^(1*128+64) mod G(x)
// .Lfinal_fold_consts:
.quad 0x1368000000000000 // x^48 * (x^48 mod G(x))
.quad 0x2d56000000000000 // x^48 * (x^80 mod G(x))
// .Lbarrett_reduction_consts:
.quad 0x0000000000018bb7 // G(x)
.quad 0x00000001f65a57f8 // floor(x^48 / G(x))
// For 1 <= len <= 15, the 16-byte vector beginning at &byteshift_table[16 -
// len] is the index vector to shift left by 'len' bytes, and is also {0x80,
// ..., 0x80} XOR the index vector to shift right by '16 - len' bytes.
.Lbyteshift_table:
.byte 0x0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87
.byte 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f
.byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7
.byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe , 0x0