init_crc .req w0
buf .req x1
len .req x2
- fold_consts_ptr .req x3
+ fold_consts_ptr .req x5
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
-
- // Compose { 0,0,0,0, 8,8,8,8, 1,1,1,1, 9,9,9,9 }
- movi bd1.4h, #8, lsl #8
- orr bd1.2s, #1, lsl #16
- orr bd1.2s, #1, lsl #24
- zip1 bd1.16b, bd1.16b, bd1.16b
- zip1 bd1.16b, bd1.16b, bd1.16b
- .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)
+ perm .req v27
.macro pmull16x64_p64, a16, b64, c64
pmull2 \c64\().1q, \a16\().2d, \b64\().2d
*/
.macro pmull16x64_p8, a16, b64, c64
ext t7.16b, \b64\().16b, \b64\().16b, #1
- tbl t5.16b, {\a16\().16b}, bd1.16b
+ tbl t5.16b, {\a16\().16b}, perm.16b
uzp1 t7.16b, \b64\().16b, t7.16b
bl __pmull_p8_16x64
ext \b64\().16b, t4.16b, t4.16b, #15
ret
SYM_FUNC_END(__pmull_p8_16x64)
- .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.
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
- __pmull_init_\p
// For sizes less than 256 bytes, we can't fold 128 bytes at a time.
cmp len, #256
pmull16x64_\p fold_consts, v3, v0
eor v7.16b, v3.16b, 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]
- .ifc \p, p8
- frame_pop
- .endif
- ret
+ b .Lreduce_final_16_bytes_\@
.Lless_than_256_bytes_\@:
// Checksumming a buffer of length 16...255 bytes
b.ge .Lfold_16_bytes_loop_\@ // 32 <= len <= 255
add len, len, #16
b .Lhandle_partial_segment_\@ // 17 <= len <= 31
+
+.Lreduce_final_16_bytes_\@:
.endm
//
//
SYM_FUNC_START(crc_t10dif_pmull_p8)
frame_push 1
+
+ // Compose { 0,0,0,0, 8,8,8,8, 1,1,1,1, 9,9,9,9 }
+ movi perm.4h, #8, lsl #8
+ orr perm.2s, #1, lsl #16
+ orr perm.2s, #1, lsl #24
+ zip1 perm.16b, perm.16b, perm.16b
+ zip1 perm.16b, perm.16b, perm.16b
+
crc_t10dif_pmull p8
+
+CPU_LE( rev64 v7.16b, v7.16b )
+CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
+ str q7, [x3]
+
+ frame_pop
+ ret
SYM_FUNC_END(crc_t10dif_pmull_p8)
.align 5
//
SYM_FUNC_START(crc_t10dif_pmull_p64)
crc_t10dif_pmull p64
+
+ // 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
+
+ // 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
+ pmull2 v7.1q, v7.2d, fold_consts.2d // 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 v1.1q, v1.1d, fold_consts.1d // 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]
+
+ // Use Barrett reduction to compute the final CRC value.
+ pmull2 v1.1q, v0.2d, fold_consts.2d // high 32 bits * floor(x^48 / G(x))
+ ushr v1.2d, v1.2d, #32 // /= x^32
+ pmull v1.1q, v1.1d, fold_consts.1d // *= 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]
+ ret
SYM_FUNC_END(crc_t10dif_pmull_p64)
.section ".rodata", "a"
projects / users / dwmw2 / linux.git / commitdiff