diff options
Diffstat (limited to 'arch/arm64/crypto/crct10dif-ce-core.S')
-rw-r--r-- | arch/arm64/crypto/crct10dif-ce-core.S | 340 |
1 files changed, 264 insertions, 76 deletions
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S index f179c01bd55c..9e82e8e8ed05 100644 --- a/arch/arm64/crypto/crct10dif-ce-core.S +++ b/arch/arm64/crypto/crct10dif-ce-core.S @@ -74,15 +74,202 @@ .text .cpu generic+crypto - arg1_low32 .req w0 - arg2 .req x1 - arg3 .req x2 + arg1_low32 .req w19 + arg2 .req x20 + arg3 .req x21 vzr .req v13 -ENTRY(crc_t10dif_pmull) + ad .req v14 + bd .req v10 + + 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 + +__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, bd.8b // F = A1*B + pmull t8.8h, ad.8b, bd1.8b // E = A*B1 + pmull t5.8h, t5.8b, bd.8b // H = A2*B + pmull t7.8h, ad.8b, bd2.8b // G = A*B2 + pmull t6.8h, t6.8b, bd.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, bd.16b // F = A1*B + pmull2 t8.8h, ad.16b, bd1.16b // E = A*B1 + pmull2 t5.8h, t5.16b, bd.16b // H = A2*B + pmull2 t7.8h, ad.16b, bd2.16b // G = A*B2 + pmull2 t6.8h, t6.16b, bd.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 +ENDPROC(__pmull_p8_core) + + .macro __pmull_p8, rq, ad, bd, i + .ifnc \bd, v10 + .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 + + .macro fold64, p, reg1, reg2 + ldp q11, q12, [arg2], #0x20 + + __pmull_\p v8, \reg1, v10, 2 + __pmull_\p \reg1, \reg1, v10 + +CPU_LE( rev64 v11.16b, v11.16b ) +CPU_LE( rev64 v12.16b, v12.16b ) + + __pmull_\p v9, \reg2, v10, 2 + __pmull_\p \reg2, \reg2, v10 + +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 + + .macro fold16, p, reg, rk + __pmull_\p v8, \reg, v10 + __pmull_\p \reg, \reg, v10, 2 + .ifnb \rk + ldr_l q10, \rk, x8 + __pmull_pre_\p v10 + .endif + eor v7.16b, v7.16b, v8.16b + eor v7.16b, v7.16b, \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 3, 128 + + mov arg1_low32, w0 + mov arg2, x1 + mov arg3, x2 + movi vzr.16b, #0 // init zero register + __pmull_init_\p + // adjust the 16-bit initial_crc value, scale it to 32 bits lsl arg1_low32, arg1_low32, #16 @@ -90,7 +277,7 @@ ENTRY(crc_t10dif_pmull) cmp arg3, #256 // for sizes less than 128, we can't fold 64B at a time... - b.lt _less_than_128 + b.lt .L_less_than_128_\@ // load the initial crc value // crc value does not need to be byte-reflected, but it needs @@ -131,6 +318,7 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) ldr_l q10, rk3, x8 // xmm10 has rk3 and rk4 // type of pmull instruction // will determine which constant to use + __pmull_pre_\p v10 // // we subtract 256 instead of 128 to save one instruction from the loop @@ -141,42 +329,39 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) // buffer. The _fold_64_B_loop will fold 64B at a time // until we have 64+y Bytes of buffer - // fold 64B at a time. This section of the code folds 4 vector // registers in parallel -_fold_64_B_loop: - - .macro fold64, reg1, reg2 - ldp q11, q12, [arg2], #0x20 - - pmull2 v8.1q, \reg1\().2d, v10.2d - pmull \reg1\().1q, \reg1\().1d, v10.1d - -CPU_LE( rev64 v11.16b, v11.16b ) -CPU_LE( rev64 v12.16b, v12.16b ) - - pmull2 v9.1q, \reg2\().2d, v10.2d - pmull \reg2\().1q, \reg2\().1d, v10.1d +.L_fold_64_B_loop_\@: -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 - - fold64 v0, v1 - fold64 v2, v3 - fold64 v4, v5 - fold64 v6, v7 + fold64 \p, v0, v1 + fold64 \p, v2, v3 + fold64 \p, v4, v5 + fold64 \p, v6, v7 subs arg3, arg3, #128 // check if there is another 64B in the buffer to be able to fold - b.ge _fold_64_B_loop + b.lt .L_fold_64_B_end_\@ + + 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] + ldr_l q10, rk3, x8 + movi vzr.16b, #0 // init zero register + __pmull_init_\p + __pmull_pre_\p v10 + endif_yield_neon + b .L_fold_64_B_loop_\@ + +.L_fold_64_B_end_\@: // at this point, the buffer pointer is pointing at the last y Bytes // of the buffer the 64B of folded data is in 4 of the vector // registers: v0, v1, v2, v3 @@ -185,38 +370,29 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 ) // constants ldr_l q10, rk9, x8 + __pmull_pre_\p v10 - .macro fold16, reg, rk - pmull v8.1q, \reg\().1d, v10.1d - pmull2 \reg\().1q, \reg\().2d, v10.2d - .ifnb \rk - ldr_l q10, \rk, x8 - .endif - eor v7.16b, v7.16b, v8.16b - eor v7.16b, v7.16b, \reg\().16b - .endm - - fold16 v0, rk11 - fold16 v1, rk13 - fold16 v2, rk15 - fold16 v3, rk17 - fold16 v4, rk19 - fold16 v5, rk1 - fold16 v6 + fold16 \p, v0, rk11 + fold16 \p, v1, rk13 + fold16 \p, v2, rk15 + fold16 \p, v3, rk17 + fold16 \p, v4, rk19 + fold16 \p, v5, rk1 + fold16 \p, v6 // instead of 64, we add 48 to the loop counter to save 1 instruction // from the loop instead of a cmp instruction, we use the negative // flag with the jl instruction adds arg3, arg3, #(128-16) - b.lt _final_reduction_for_128 + b.lt .L_final_reduction_for_128_\@ // now we have 16+y bytes left to reduce. 16 Bytes is in register v7 // and the rest is in memory. We can fold 16 bytes at a time if y>=16 // continue folding 16B at a time -_16B_reduction_loop: - pmull v8.1q, v7.1d, v10.1d - pmull2 v7.1q, v7.2d, v10.2d +.L_16B_reduction_loop_\@: + __pmull_\p v8, v7, v10 + __pmull_\p v7, v7, v10, 2 eor v7.16b, v7.16b, v8.16b ldr q0, [arg2], #16 @@ -228,22 +404,22 @@ CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 ) // instead of a cmp instruction, we utilize the flags with the // jge instruction equivalent of: cmp arg3, 16-16 // check if there is any more 16B in the buffer to be able to fold - b.ge _16B_reduction_loop + b.ge .L_16B_reduction_loop_\@ // now we have 16+z bytes left to reduce, where 0<= z < 16. // first, we reduce the data in the xmm7 register -_final_reduction_for_128: +.L_final_reduction_for_128_\@: // check if any more data to fold. If not, compute the CRC of // the final 128 bits adds arg3, arg3, #16 - b.eq _128_done + b.eq .L_128_done_\@ // here we are getting data that is less than 16 bytes. // since we know that there was data before the pointer, we can // offset the input pointer before the actual point, to receive // exactly 16 bytes. after that the registers need to be adjusted. -_get_last_two_regs: +.L_get_last_two_regs_\@: add arg2, arg2, arg3 ldr q1, [arg2, #-16] CPU_LE( rev64 v1.16b, v1.16b ) @@ -268,46 +444,48 @@ CPU_LE( ext v1.16b, v1.16b, v1.16b, #8 ) bsl v0.16b, v2.16b, v1.16b // fold 16 Bytes - pmull v8.1q, v7.1d, v10.1d - pmull2 v7.1q, v7.2d, v10.2d + __pmull_\p v8, v7, v10 + __pmull_\p v7, v7, v10, 2 eor v7.16b, v7.16b, v8.16b eor v7.16b, v7.16b, v0.16b -_128_done: +.L_128_done_\@: // compute crc of a 128-bit value ldr_l q10, rk5, x8 // rk5 and rk6 in xmm10 + __pmull_pre_\p v10 // 64b fold ext v0.16b, vzr.16b, v7.16b, #8 mov v7.d[0], v7.d[1] - pmull v7.1q, v7.1d, v10.1d + __pmull_\p v7, v7, v10 eor v7.16b, v7.16b, v0.16b // 32b fold ext v0.16b, v7.16b, vzr.16b, #4 mov v7.s[3], vzr.s[0] - pmull2 v0.1q, v0.2d, v10.2d + __pmull_\p v0, v0, v10, 2 eor v7.16b, v7.16b, v0.16b // barrett reduction -_barrett: ldr_l q10, rk7, x8 + __pmull_pre_\p v10 mov v0.d[0], v7.d[1] - pmull v0.1q, v0.1d, v10.1d + __pmull_\p v0, v0, v10 ext v0.16b, vzr.16b, v0.16b, #12 - pmull2 v0.1q, v0.2d, v10.2d + __pmull_\p v0, v0, v10, 2 ext v0.16b, vzr.16b, v0.16b, #12 eor v7.16b, v7.16b, v0.16b mov w0, v7.s[1] -_cleanup: +.L_cleanup_\@: // scale the result back to 16 bits lsr x0, x0, #16 + frame_pop ret -_less_than_128: - cbz arg3, _cleanup +.L_less_than_128_\@: + cbz arg3, .L_cleanup_\@ movi v0.16b, #0 mov v0.s[3], arg1_low32 // get the initial crc value @@ -318,20 +496,21 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) eor v7.16b, v7.16b, v0.16b // xor the initial crc value cmp arg3, #16 - b.eq _128_done // exactly 16 left - b.lt _less_than_16_left + b.eq .L_128_done_\@ // exactly 16 left + b.lt .L_less_than_16_left_\@ ldr_l q10, rk1, x8 // rk1 and rk2 in xmm10 + __pmull_pre_\p v10 // update the counter. subtract 32 instead of 16 to save one // instruction from the loop subs arg3, arg3, #32 - b.ge _16B_reduction_loop + b.ge .L_16B_reduction_loop_\@ add arg3, arg3, #16 - b _get_last_two_regs + b .L_get_last_two_regs_\@ -_less_than_16_left: +.L_less_than_16_left_\@: // shl r9, 4 adr_l x0, tbl_shf_table + 16 sub x0, x0, arg3 @@ -339,8 +518,17 @@ _less_than_16_left: movi v9.16b, #0x80 eor v0.16b, v0.16b, v9.16b tbl v7.16b, {v7.16b}, v0.16b - b _128_done -ENDPROC(crc_t10dif_pmull) + b .L_128_done_\@ + .endm + +ENTRY(crc_t10dif_pmull_p8) + crc_t10dif_pmull p8 +ENDPROC(crc_t10dif_pmull_p8) + + .align 5 +ENTRY(crc_t10dif_pmull_p64) + crc_t10dif_pmull p64 +ENDPROC(crc_t10dif_pmull_p64) // precomputed constants // these constants are precomputed from the poly: |