diff options
Diffstat (limited to 'arch/arm64/crypto/aes-neonbs-core.S')
| -rw-r--r-- | arch/arm64/crypto/aes-neonbs-core.S | 264 |
1 files changed, 65 insertions, 199 deletions
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S index a3405b8c344b..d427f4556b6e 100644 --- a/arch/arm64/crypto/aes-neonbs-core.S +++ b/arch/arm64/crypto/aes-neonbs-core.S @@ -735,119 +735,67 @@ SYM_FUNC_END(aesbs_cbc_decrypt) * int blocks, u8 iv[]) */ SYM_FUNC_START_LOCAL(__xts_crypt8) - mov x6, #1 - lsl x6, x6, x23 - subs w23, w23, #8 - csel x23, x23, xzr, pl - csel x6, x6, xzr, mi + movi v18.2s, #0x1 + movi v19.2s, #0x87 + uzp1 v18.4s, v18.4s, v19.4s + + ld1 {v0.16b-v3.16b}, [x1], #64 + ld1 {v4.16b-v7.16b}, [x1], #64 + + next_tweak v26, v25, v18, v19 + next_tweak v27, v26, v18, v19 + next_tweak v28, v27, v18, v19 + next_tweak v29, v28, v18, v19 + next_tweak v30, v29, v18, v19 + next_tweak v31, v30, v18, v19 + next_tweak v16, v31, v18, v19 + next_tweak v17, v16, v18, v19 - ld1 {v0.16b}, [x20], #16 - next_tweak v26, v25, v30, v31 eor v0.16b, v0.16b, v25.16b - tbnz x6, #1, 0f - - ld1 {v1.16b}, [x20], #16 - next_tweak v27, v26, v30, v31 eor v1.16b, v1.16b, v26.16b - tbnz x6, #2, 0f - - ld1 {v2.16b}, [x20], #16 - next_tweak v28, v27, v30, v31 eor v2.16b, v2.16b, v27.16b - tbnz x6, #3, 0f - - ld1 {v3.16b}, [x20], #16 - next_tweak v29, v28, v30, v31 eor v3.16b, v3.16b, v28.16b - tbnz x6, #4, 0f - - ld1 {v4.16b}, [x20], #16 - str q29, [sp, #.Lframe_local_offset] eor v4.16b, v4.16b, v29.16b - next_tweak v29, v29, v30, v31 - tbnz x6, #5, 0f - - ld1 {v5.16b}, [x20], #16 - str q29, [sp, #.Lframe_local_offset + 16] - eor v5.16b, v5.16b, v29.16b - next_tweak v29, v29, v30, v31 - tbnz x6, #6, 0f - - ld1 {v6.16b}, [x20], #16 - str q29, [sp, #.Lframe_local_offset + 32] - eor v6.16b, v6.16b, v29.16b - next_tweak v29, v29, v30, v31 - tbnz x6, #7, 0f + eor v5.16b, v5.16b, v30.16b + eor v6.16b, v6.16b, v31.16b + eor v7.16b, v7.16b, v16.16b - ld1 {v7.16b}, [x20], #16 - str q29, [sp, #.Lframe_local_offset + 48] - eor v7.16b, v7.16b, v29.16b - next_tweak v29, v29, v30, v31 + stp q16, q17, [sp, #16] -0: mov bskey, x21 - mov rounds, x22 + mov bskey, x2 + mov rounds, x3 br x16 SYM_FUNC_END(__xts_crypt8) .macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7 - frame_push 6, 64 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 + stp x29, x30, [sp, #-48]! + mov x29, sp - movi v30.2s, #0x1 - movi v25.2s, #0x87 - uzp1 v30.4s, v30.4s, v25.4s - ld1 {v25.16b}, [x24] + ld1 {v25.16b}, [x5] -99: adr x16, \do8 +0: adr x16, \do8 bl __xts_crypt8 - ldp q16, q17, [sp, #.Lframe_local_offset] - ldp q18, q19, [sp, #.Lframe_local_offset + 32] + eor v16.16b, \o0\().16b, v25.16b + eor v17.16b, \o1\().16b, v26.16b + eor v18.16b, \o2\().16b, v27.16b + eor v19.16b, \o3\().16b, v28.16b - eor \o0\().16b, \o0\().16b, v25.16b - eor \o1\().16b, \o1\().16b, v26.16b - eor \o2\().16b, \o2\().16b, v27.16b - eor \o3\().16b, \o3\().16b, v28.16b + ldp q24, q25, [sp, #16] - st1 {\o0\().16b}, [x19], #16 - mov v25.16b, v26.16b - tbnz x6, #1, 1f - st1 {\o1\().16b}, [x19], #16 - mov v25.16b, v27.16b - tbnz x6, #2, 1f - st1 {\o2\().16b}, [x19], #16 - mov v25.16b, v28.16b - tbnz x6, #3, 1f - st1 {\o3\().16b}, [x19], #16 - mov v25.16b, v29.16b - tbnz x6, #4, 1f + eor v20.16b, \o4\().16b, v29.16b + eor v21.16b, \o5\().16b, v30.16b + eor v22.16b, \o6\().16b, v31.16b + eor v23.16b, \o7\().16b, v24.16b - eor \o4\().16b, \o4\().16b, v16.16b - eor \o5\().16b, \o5\().16b, v17.16b - eor \o6\().16b, \o6\().16b, v18.16b - eor \o7\().16b, \o7\().16b, v19.16b + st1 {v16.16b-v19.16b}, [x0], #64 + st1 {v20.16b-v23.16b}, [x0], #64 - st1 {\o4\().16b}, [x19], #16 - tbnz x6, #5, 1f - st1 {\o5\().16b}, [x19], #16 - tbnz x6, #6, 1f - st1 {\o6\().16b}, [x19], #16 - tbnz x6, #7, 1f - st1 {\o7\().16b}, [x19], #16 + subs x4, x4, #8 + b.gt 0b - cbz x23, 1f - st1 {v25.16b}, [x24] - - b 99b - -1: st1 {v25.16b}, [x24] - frame_pop + st1 {v25.16b}, [x5] + ldp x29, x30, [sp], #48 ret .endm @@ -869,133 +817,51 @@ SYM_FUNC_END(aesbs_xts_decrypt) /* * aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], - * int rounds, int blocks, u8 iv[], u8 final[]) + * int rounds, int blocks, u8 iv[]) */ SYM_FUNC_START(aesbs_ctr_encrypt) - frame_push 8 - - mov x19, x0 - mov x20, x1 - mov x21, x2 - mov x22, x3 - mov x23, x4 - mov x24, x5 - mov x25, x6 + stp x29, x30, [sp, #-16]! + mov x29, sp - cmp x25, #0 - cset x26, ne - add x23, x23, x26 // do one extra block if final - - ldp x7, x8, [x24] - ld1 {v0.16b}, [x24] + ldp x7, x8, [x5] + ld1 {v0.16b}, [x5] CPU_LE( rev x7, x7 ) CPU_LE( rev x8, x8 ) adds x8, x8, #1 adc x7, x7, xzr -99: mov x9, #1 - lsl x9, x9, x23 - subs w23, w23, #8 - csel x23, x23, xzr, pl - csel x9, x9, xzr, le - - tbnz x9, #1, 0f - next_ctr v1 - tbnz x9, #2, 0f +0: next_ctr v1 next_ctr v2 - tbnz x9, #3, 0f next_ctr v3 - tbnz x9, #4, 0f next_ctr v4 - tbnz x9, #5, 0f next_ctr v5 - tbnz x9, #6, 0f next_ctr v6 - tbnz x9, #7, 0f next_ctr v7 -0: mov bskey, x21 - mov rounds, x22 + mov bskey, x2 + mov rounds, x3 bl aesbs_encrypt8 - lsr x9, x9, x26 // disregard the extra block - tbnz x9, #0, 0f - - ld1 {v8.16b}, [x20], #16 - eor v0.16b, v0.16b, v8.16b - st1 {v0.16b}, [x19], #16 - tbnz x9, #1, 1f + ld1 { v8.16b-v11.16b}, [x1], #64 + ld1 {v12.16b-v15.16b}, [x1], #64 - ld1 {v9.16b}, [x20], #16 - eor v1.16b, v1.16b, v9.16b - st1 {v1.16b}, [x19], #16 - tbnz x9, #2, 2f + eor v8.16b, v0.16b, v8.16b + eor v9.16b, v1.16b, v9.16b + eor v10.16b, v4.16b, v10.16b + eor v11.16b, v6.16b, v11.16b + eor v12.16b, v3.16b, v12.16b + eor v13.16b, v7.16b, v13.16b + eor v14.16b, v2.16b, v14.16b + eor v15.16b, v5.16b, v15.16b - ld1 {v10.16b}, [x20], #16 - eor v4.16b, v4.16b, v10.16b - st1 {v4.16b}, [x19], #16 - tbnz x9, #3, 3f + st1 { v8.16b-v11.16b}, [x0], #64 + st1 {v12.16b-v15.16b}, [x0], #64 - ld1 {v11.16b}, [x20], #16 - eor v6.16b, v6.16b, v11.16b - st1 {v6.16b}, [x19], #16 - tbnz x9, #4, 4f - - ld1 {v12.16b}, [x20], #16 - eor v3.16b, v3.16b, v12.16b - st1 {v3.16b}, [x19], #16 - tbnz x9, #5, 5f - - ld1 {v13.16b}, [x20], #16 - eor v7.16b, v7.16b, v13.16b - st1 {v7.16b}, [x19], #16 - tbnz x9, #6, 6f + next_ctr v0 + subs x4, x4, #8 + b.gt 0b - ld1 {v14.16b}, [x20], #16 - eor v2.16b, v2.16b, v14.16b - st1 {v2.16b}, [x19], #16 - tbnz x9, #7, 7f - - ld1 {v15.16b}, [x20], #16 - eor v5.16b, v5.16b, v15.16b - st1 {v5.16b}, [x19], #16 - -8: next_ctr v0 - st1 {v0.16b}, [x24] - cbz x23, .Lctr_done - - b 99b - -.Lctr_done: - frame_pop + st1 {v0.16b}, [x5] + ldp x29, x30, [sp], #16 ret - - /* - * If we are handling the tail of the input (x6 != NULL), return the - * final keystream block back to the caller. - */ -0: cbz x25, 8b - st1 {v0.16b}, [x25] - b 8b -1: cbz x25, 8b - st1 {v1.16b}, [x25] - b 8b -2: cbz x25, 8b - st1 {v4.16b}, [x25] - b 8b -3: cbz x25, 8b - st1 {v6.16b}, [x25] - b 8b -4: cbz x25, 8b - st1 {v3.16b}, [x25] - b 8b -5: cbz x25, 8b - st1 {v7.16b}, [x25] - b 8b -6: cbz x25, 8b - st1 {v2.16b}, [x25] - b 8b -7: cbz x25, 8b - st1 {v5.16b}, [x25] - b 8b SYM_FUNC_END(aesbs_ctr_encrypt) |