diff options
Diffstat (limited to 'arch/arm64/crypto/aes-modes.S')
-rw-r--r-- | arch/arm64/crypto/aes-modes.S | 1002 |
1 files changed, 662 insertions, 340 deletions
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index 2674d43d1384..5abc834271f4 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES * * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> - * - * 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. */ /* included by aes-ce.S and aes-neon.S */ @@ -13,127 +10,66 @@ .text .align 4 -/* - * There are several ways to instantiate this code: - * - no interleave, all inline - * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2) - * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE) - * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4) - * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE) - * - * Macros imported by this code: - * - enc_prepare - setup NEON registers for encryption - * - dec_prepare - setup NEON registers for decryption - * - enc_switch_key - change to new key after having prepared for encryption - * - encrypt_block - encrypt a single block - * - decrypt block - decrypt a single block - * - encrypt_block2x - encrypt 2 blocks in parallel (if INTERLEAVE == 2) - * - decrypt_block2x - decrypt 2 blocks in parallel (if INTERLEAVE == 2) - * - encrypt_block4x - encrypt 4 blocks in parallel (if INTERLEAVE == 4) - * - decrypt_block4x - decrypt 4 blocks in parallel (if INTERLEAVE == 4) - */ - -#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE) -#define FRAME_PUSH stp x29, x30, [sp,#-16]! ; mov x29, sp -#define FRAME_POP ldp x29, x30, [sp],#16 +#ifndef MAX_STRIDE +#define MAX_STRIDE 4 +#endif -#if INTERLEAVE == 2 +#if MAX_STRIDE == 4 +#define ST4(x...) x +#define ST5(x...) +#else +#define ST4(x...) +#define ST5(x...) x +#endif -aes_encrypt_block2x: - encrypt_block2x v0, v1, w3, x2, x6, w7 +SYM_FUNC_START_LOCAL(aes_encrypt_block4x) + encrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7 ret -ENDPROC(aes_encrypt_block2x) +SYM_FUNC_END(aes_encrypt_block4x) -aes_decrypt_block2x: - decrypt_block2x v0, v1, w3, x2, x6, w7 +SYM_FUNC_START_LOCAL(aes_decrypt_block4x) + decrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7 ret -ENDPROC(aes_decrypt_block2x) - -#elif INTERLEAVE == 4 +SYM_FUNC_END(aes_decrypt_block4x) -aes_encrypt_block4x: - encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7 +#if MAX_STRIDE == 5 +SYM_FUNC_START_LOCAL(aes_encrypt_block5x) + encrypt_block5x v0, v1, v2, v3, v4, w3, x2, x8, w7 ret -ENDPROC(aes_encrypt_block4x) +SYM_FUNC_END(aes_encrypt_block5x) -aes_decrypt_block4x: - decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7 +SYM_FUNC_START_LOCAL(aes_decrypt_block5x) + decrypt_block5x v0, v1, v2, v3, v4, w3, x2, x8, w7 ret -ENDPROC(aes_decrypt_block4x) - -#else -#error INTERLEAVE should equal 2 or 4 -#endif - - .macro do_encrypt_block2x - bl aes_encrypt_block2x - .endm - - .macro do_decrypt_block2x - bl aes_decrypt_block2x - .endm - - .macro do_encrypt_block4x - bl aes_encrypt_block4x - .endm - - .macro do_decrypt_block4x - bl aes_decrypt_block4x - .endm - -#else -#define FRAME_PUSH -#define FRAME_POP - - .macro do_encrypt_block2x - encrypt_block2x v0, v1, w3, x2, x6, w7 - .endm - - .macro do_decrypt_block2x - decrypt_block2x v0, v1, w3, x2, x6, w7 - .endm - - .macro do_encrypt_block4x - encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7 - .endm - - .macro do_decrypt_block4x - decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7 - .endm - +SYM_FUNC_END(aes_decrypt_block5x) #endif /* * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, - * int blocks, int first) + * int blocks) * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, - * int blocks, int first) + * int blocks) */ -AES_ENTRY(aes_ecb_encrypt) - FRAME_PUSH - cbz w5, .LecbencloopNx +AES_FUNC_START(aes_ecb_encrypt) + stp x29, x30, [sp, #-16]! + mov x29, sp enc_prepare w3, x2, x5 .LecbencloopNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #MAX_STRIDE bmi .Lecbenc1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */ - do_encrypt_block2x - st1 {v0.16b-v1.16b}, [x0], #32 -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */ - do_encrypt_block4x +ST4( bl aes_encrypt_block4x ) +ST5( ld1 {v4.16b}, [x1], #16 ) +ST5( bl aes_encrypt_block5x ) st1 {v0.16b-v3.16b}, [x0], #64 -#endif +ST5( st1 {v4.16b}, [x0], #16 ) b .LecbencloopNx .Lecbenc1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #MAX_STRIDE beq .Lecbencout -#endif .Lecbencloop: ld1 {v0.16b}, [x1], #16 /* get next pt block */ encrypt_block v0, w3, x2, x5, w6 @@ -141,35 +77,30 @@ AES_ENTRY(aes_ecb_encrypt) subs w4, w4, #1 bne .Lecbencloop .Lecbencout: - FRAME_POP + ldp x29, x30, [sp], #16 ret -AES_ENDPROC(aes_ecb_encrypt) +AES_FUNC_END(aes_ecb_encrypt) -AES_ENTRY(aes_ecb_decrypt) - FRAME_PUSH - cbz w5, .LecbdecloopNx +AES_FUNC_START(aes_ecb_decrypt) + stp x29, x30, [sp, #-16]! + mov x29, sp dec_prepare w3, x2, x5 .LecbdecloopNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #MAX_STRIDE bmi .Lecbdec1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ - do_decrypt_block2x - st1 {v0.16b-v1.16b}, [x0], #32 -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ - do_decrypt_block4x +ST4( bl aes_decrypt_block4x ) +ST5( ld1 {v4.16b}, [x1], #16 ) +ST5( bl aes_decrypt_block5x ) st1 {v0.16b-v3.16b}, [x0], #64 -#endif +ST5( st1 {v4.16b}, [x0], #16 ) b .LecbdecloopNx .Lecbdec1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #MAX_STRIDE beq .Lecbdecout -#endif .Lecbdecloop: ld1 {v0.16b}, [x1], #16 /* get next ct block */ decrypt_block v0, w3, x2, x5, w6 @@ -177,327 +108,665 @@ AES_ENTRY(aes_ecb_decrypt) subs w4, w4, #1 bne .Lecbdecloop .Lecbdecout: - FRAME_POP + ldp x29, x30, [sp], #16 ret -AES_ENDPROC(aes_ecb_decrypt) +AES_FUNC_END(aes_ecb_decrypt) /* * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, - * int blocks, u8 iv[], int first) + * int blocks, u8 iv[]) * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, - * int blocks, u8 iv[], int first) + * int blocks, u8 iv[]) + * aes_essiv_cbc_encrypt(u8 out[], u8 const in[], u32 const rk1[], + * int rounds, int blocks, u8 iv[], + * u32 const rk2[]); + * aes_essiv_cbc_decrypt(u8 out[], u8 const in[], u32 const rk1[], + * int rounds, int blocks, u8 iv[], + * u32 const rk2[]); */ -AES_ENTRY(aes_cbc_encrypt) - cbz w6, .Lcbcencloop +AES_FUNC_START(aes_essiv_cbc_encrypt) + ld1 {v4.16b}, [x5] /* get iv */ - ld1 {v0.16b}, [x5] /* get iv */ + mov w8, #14 /* AES-256: 14 rounds */ + enc_prepare w8, x6, x7 + encrypt_block v4, w8, x6, x7, w9 + enc_switch_key w3, x2, x6 + b .Lcbcencloop4x + +AES_FUNC_START(aes_cbc_encrypt) + ld1 {v4.16b}, [x5] /* get iv */ enc_prepare w3, x2, x6 -.Lcbcencloop: - ld1 {v1.16b}, [x1], #16 /* get next pt block */ - eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */ +.Lcbcencloop4x: + subs w4, w4, #4 + bmi .Lcbcenc1x + ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */ + eor v0.16b, v0.16b, v4.16b /* ..and xor with iv */ encrypt_block v0, w3, x2, x6, w7 - st1 {v0.16b}, [x0], #16 + eor v1.16b, v1.16b, v0.16b + encrypt_block v1, w3, x2, x6, w7 + eor v2.16b, v2.16b, v1.16b + encrypt_block v2, w3, x2, x6, w7 + eor v3.16b, v3.16b, v2.16b + encrypt_block v3, w3, x2, x6, w7 + st1 {v0.16b-v3.16b}, [x0], #64 + mov v4.16b, v3.16b + b .Lcbcencloop4x +.Lcbcenc1x: + adds w4, w4, #4 + beq .Lcbcencout +.Lcbcencloop: + ld1 {v0.16b}, [x1], #16 /* get next pt block */ + eor v4.16b, v4.16b, v0.16b /* ..and xor with iv */ + encrypt_block v4, w3, x2, x6, w7 + st1 {v4.16b}, [x0], #16 subs w4, w4, #1 bne .Lcbcencloop - st1 {v0.16b}, [x5] /* return iv */ +.Lcbcencout: + st1 {v4.16b}, [x5] /* return iv */ ret -AES_ENDPROC(aes_cbc_encrypt) +AES_FUNC_END(aes_cbc_encrypt) +AES_FUNC_END(aes_essiv_cbc_encrypt) + +AES_FUNC_START(aes_essiv_cbc_decrypt) + stp x29, x30, [sp, #-16]! + mov x29, sp + ld1 {cbciv.16b}, [x5] /* get iv */ -AES_ENTRY(aes_cbc_decrypt) - FRAME_PUSH - cbz w6, .LcbcdecloopNx + mov w8, #14 /* AES-256: 14 rounds */ + enc_prepare w8, x6, x7 + encrypt_block cbciv, w8, x6, x7, w9 + b .Lessivcbcdecstart - ld1 {v7.16b}, [x5] /* get iv */ +AES_FUNC_START(aes_cbc_decrypt) + stp x29, x30, [sp, #-16]! + mov x29, sp + + ld1 {cbciv.16b}, [x5] /* get iv */ +.Lessivcbcdecstart: dec_prepare w3, x2, x6 .LcbcdecloopNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #MAX_STRIDE bmi .Lcbcdec1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ - mov v2.16b, v0.16b - mov v3.16b, v1.16b - do_decrypt_block2x - eor v0.16b, v0.16b, v7.16b - eor v1.16b, v1.16b, v2.16b - mov v7.16b, v3.16b - st1 {v0.16b-v1.16b}, [x0], #32 -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ +#if MAX_STRIDE == 5 + ld1 {v4.16b}, [x1], #16 /* get 1 ct block */ + mov v5.16b, v0.16b + mov v6.16b, v1.16b + mov v7.16b, v2.16b + bl aes_decrypt_block5x + sub x1, x1, #32 + eor v0.16b, v0.16b, cbciv.16b + eor v1.16b, v1.16b, v5.16b + ld1 {v5.16b}, [x1], #16 /* reload 1 ct block */ + ld1 {cbciv.16b}, [x1], #16 /* reload 1 ct block */ + eor v2.16b, v2.16b, v6.16b + eor v3.16b, v3.16b, v7.16b + eor v4.16b, v4.16b, v5.16b +#else mov v4.16b, v0.16b mov v5.16b, v1.16b mov v6.16b, v2.16b - do_decrypt_block4x + bl aes_decrypt_block4x sub x1, x1, #16 - eor v0.16b, v0.16b, v7.16b + eor v0.16b, v0.16b, cbciv.16b eor v1.16b, v1.16b, v4.16b - ld1 {v7.16b}, [x1], #16 /* reload 1 ct block */ + ld1 {cbciv.16b}, [x1], #16 /* reload 1 ct block */ eor v2.16b, v2.16b, v5.16b eor v3.16b, v3.16b, v6.16b - st1 {v0.16b-v3.16b}, [x0], #64 #endif + st1 {v0.16b-v3.16b}, [x0], #64 +ST5( st1 {v4.16b}, [x0], #16 ) b .LcbcdecloopNx .Lcbcdec1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #MAX_STRIDE beq .Lcbcdecout -#endif .Lcbcdecloop: ld1 {v1.16b}, [x1], #16 /* get next ct block */ mov v0.16b, v1.16b /* ...and copy to v0 */ decrypt_block v0, w3, x2, x6, w7 - eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */ - mov v7.16b, v1.16b /* ct is next iv */ + eor v0.16b, v0.16b, cbciv.16b /* xor with iv => pt */ + mov cbciv.16b, v1.16b /* ct is next iv */ st1 {v0.16b}, [x0], #16 subs w4, w4, #1 bne .Lcbcdecloop .Lcbcdecout: - FRAME_POP - st1 {v7.16b}, [x5] /* return iv */ + st1 {cbciv.16b}, [x5] /* return iv */ + ldp x29, x30, [sp], #16 ret -AES_ENDPROC(aes_cbc_decrypt) +AES_FUNC_END(aes_cbc_decrypt) +AES_FUNC_END(aes_essiv_cbc_decrypt) /* - * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, - * int blocks, u8 ctr[], int first) + * aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[], + * int rounds, int bytes, u8 const iv[]) + * aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[], + * int rounds, int bytes, u8 const iv[]) */ -AES_ENTRY(aes_ctr_encrypt) - FRAME_PUSH - cbz w6, .Lctrnotfirst /* 1st time around? */ +AES_FUNC_START(aes_cbc_cts_encrypt) + adr_l x8, .Lcts_permute_table + sub x4, x4, #16 + add x9, x8, #32 + add x8, x8, x4 + sub x9, x9, x4 + ld1 {v3.16b}, [x8] + ld1 {v4.16b}, [x9] + + ld1 {v0.16b}, [x1], x4 /* overlapping loads */ + ld1 {v1.16b}, [x1] + + ld1 {v5.16b}, [x5] /* get iv */ enc_prepare w3, x2, x6 - ld1 {v4.16b}, [x5] - -.Lctrnotfirst: - umov x8, v4.d[1] /* keep swabbed ctr in reg */ - rev x8, x8 -#if INTERLEAVE >= 2 - cmn w8, w4 /* 32 bit overflow? */ - bcs .Lctrloop -.LctrloopNx: - subs w4, w4, #INTERLEAVE - bmi .Lctr1x -#if INTERLEAVE == 2 - mov v0.8b, v4.8b - mov v1.8b, v4.8b - rev x7, x8 - add x8, x8, #1 - ins v0.d[1], x7 - rev x7, x8 - add x8, x8, #1 - ins v1.d[1], x7 - ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */ - do_encrypt_block2x - eor v0.16b, v0.16b, v2.16b - eor v1.16b, v1.16b, v3.16b - st1 {v0.16b-v1.16b}, [x0], #32 -#else - ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */ - dup v7.4s, w8 - mov v0.16b, v4.16b - add v7.4s, v7.4s, v8.4s - mov v1.16b, v4.16b - rev32 v8.16b, v7.16b - mov v2.16b, v4.16b - mov v3.16b, v4.16b - mov v1.s[3], v8.s[0] - mov v2.s[3], v8.s[1] - mov v3.s[3], v8.s[2] - ld1 {v5.16b-v7.16b}, [x1], #48 /* get 3 input blocks */ - do_encrypt_block4x - eor v0.16b, v5.16b, v0.16b - ld1 {v5.16b}, [x1], #16 /* get 1 input block */ - eor v1.16b, v6.16b, v1.16b - eor v2.16b, v7.16b, v2.16b - eor v3.16b, v5.16b, v3.16b - st1 {v0.16b-v3.16b}, [x0], #64 - add x8, x8, #INTERLEAVE -#endif - rev x7, x8 - ins v4.d[1], x7 - cbz w4, .Lctrout - b .LctrloopNx -.Lctr1x: - adds w4, w4, #INTERLEAVE - beq .Lctrout -#endif -.Lctrloop: - mov v0.16b, v4.16b + + eor v0.16b, v0.16b, v5.16b /* xor with iv */ + tbl v1.16b, {v1.16b}, v4.16b encrypt_block v0, w3, x2, x6, w7 - adds x8, x8, #1 /* increment BE ctr */ - rev x7, x8 - ins v4.d[1], x7 - bcs .Lctrcarry /* overflow? */ + eor v1.16b, v1.16b, v0.16b + tbl v0.16b, {v0.16b}, v3.16b + encrypt_block v1, w3, x2, x6, w7 -.Lctrcarrydone: - subs w4, w4, #1 - bmi .Lctrtailblock /* blocks <0 means tail block */ - ld1 {v3.16b}, [x1], #16 - eor v3.16b, v0.16b, v3.16b - st1 {v3.16b}, [x0], #16 - bne .Lctrloop - -.Lctrout: - st1 {v4.16b}, [x5] /* return next CTR value */ - FRAME_POP + add x4, x0, x4 + st1 {v0.16b}, [x4] /* overlapping stores */ + st1 {v1.16b}, [x0] ret +AES_FUNC_END(aes_cbc_cts_encrypt) + +AES_FUNC_START(aes_cbc_cts_decrypt) + adr_l x8, .Lcts_permute_table + sub x4, x4, #16 + add x9, x8, #32 + add x8, x8, x4 + sub x9, x9, x4 + ld1 {v3.16b}, [x8] + ld1 {v4.16b}, [x9] -.Lctrtailblock: + ld1 {v0.16b}, [x1], x4 /* overlapping loads */ + ld1 {v1.16b}, [x1] + + ld1 {v5.16b}, [x5] /* get iv */ + dec_prepare w3, x2, x6 + + decrypt_block v0, w3, x2, x6, w7 + tbl v2.16b, {v0.16b}, v3.16b + eor v2.16b, v2.16b, v1.16b + + tbx v0.16b, {v1.16b}, v4.16b + decrypt_block v0, w3, x2, x6, w7 + eor v0.16b, v0.16b, v5.16b /* xor with iv */ + + add x4, x0, x4 + st1 {v2.16b}, [x4] /* overlapping stores */ st1 {v0.16b}, [x0] - FRAME_POP ret +AES_FUNC_END(aes_cbc_cts_decrypt) + + .section ".rodata", "a" + .align 6 +.Lcts_permute_table: + .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + .byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 + .byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf + .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff + .previous -.Lctrcarry: - umov x7, v4.d[0] /* load upper word of ctr */ - rev x7, x7 /* ... to handle the carry */ - add x7, x7, #1 - rev x7, x7 - ins v4.d[0], x7 - b .Lctrcarrydone -AES_ENDPROC(aes_ctr_encrypt) - .ltorg + /* + * This macro generates the code for CTR and XCTR mode. + */ +.macro ctr_encrypt xctr + // Arguments + OUT .req x0 + IN .req x1 + KEY .req x2 + ROUNDS_W .req w3 + BYTES_W .req w4 + IV .req x5 + BYTE_CTR_W .req w6 // XCTR only + // Intermediate values + CTR_W .req w11 // XCTR only + CTR .req x11 // XCTR only + IV_PART .req x12 + BLOCKS .req x13 + BLOCKS_W .req w13 + + stp x29, x30, [sp, #-16]! + mov x29, sp + + enc_prepare ROUNDS_W, KEY, IV_PART + ld1 {vctr.16b}, [IV] + /* + * Keep 64 bits of the IV in a register. For CTR mode this lets us + * easily increment the IV. For XCTR mode this lets us efficiently XOR + * the 64-bit counter with the IV. + */ + .if \xctr + umov IV_PART, vctr.d[0] + lsr CTR_W, BYTE_CTR_W, #4 + .else + umov IV_PART, vctr.d[1] + rev IV_PART, IV_PART + .endif + +.LctrloopNx\xctr: + add BLOCKS_W, BYTES_W, #15 + sub BYTES_W, BYTES_W, #MAX_STRIDE << 4 + lsr BLOCKS_W, BLOCKS_W, #4 + mov w8, #MAX_STRIDE + cmp BLOCKS_W, w8 + csel BLOCKS_W, BLOCKS_W, w8, lt /* + * Set up the counter values in v0-v{MAX_STRIDE-1}. + * + * If we are encrypting less than MAX_STRIDE blocks, the tail block + * handling code expects the last keystream block to be in + * v{MAX_STRIDE-1}. For example: if encrypting two blocks with + * MAX_STRIDE=5, then v3 and v4 should have the next two counter blocks. + */ + .if \xctr + add CTR, CTR, BLOCKS + .else + adds IV_PART, IV_PART, BLOCKS + .endif + mov v0.16b, vctr.16b + mov v1.16b, vctr.16b + mov v2.16b, vctr.16b + mov v3.16b, vctr.16b +ST5( mov v4.16b, vctr.16b ) + .if \xctr + sub x6, CTR, #MAX_STRIDE - 1 + sub x7, CTR, #MAX_STRIDE - 2 + sub x8, CTR, #MAX_STRIDE - 3 + sub x9, CTR, #MAX_STRIDE - 4 +ST5( sub x10, CTR, #MAX_STRIDE - 5 ) + eor x6, x6, IV_PART + eor x7, x7, IV_PART + eor x8, x8, IV_PART + eor x9, x9, IV_PART +ST5( eor x10, x10, IV_PART ) + mov v0.d[0], x6 + mov v1.d[0], x7 + mov v2.d[0], x8 + mov v3.d[0], x9 +ST5( mov v4.d[0], x10 ) + .else + bcs 0f + .subsection 1 + /* + * This subsection handles carries. + * + * Conditional branching here is allowed with respect to time + * invariance since the branches are dependent on the IV instead + * of the plaintext or key. This code is rarely executed in + * practice anyway. + */ + + /* Apply carry to outgoing counter. */ +0: umov x8, vctr.d[0] + rev x8, x8 + add x8, x8, #1 + rev x8, x8 + ins vctr.d[0], x8 + + /* + * Apply carry to counter blocks if needed. + * + * Since the carry flag was set, we know 0 <= IV_PART < + * MAX_STRIDE. Using the value of IV_PART we can determine how + * many counter blocks need to be updated. + */ + cbz IV_PART, 2f + adr x16, 1f + sub x16, x16, IV_PART, lsl #3 + br x16 + bti c + mov v0.d[0], vctr.d[0] + bti c + mov v1.d[0], vctr.d[0] + bti c + mov v2.d[0], vctr.d[0] + bti c + mov v3.d[0], vctr.d[0] +ST5( bti c ) +ST5( mov v4.d[0], vctr.d[0] ) +1: b 2f + .previous + +2: rev x7, IV_PART + ins vctr.d[1], x7 + sub x7, IV_PART, #MAX_STRIDE - 1 + sub x8, IV_PART, #MAX_STRIDE - 2 + sub x9, IV_PART, #MAX_STRIDE - 3 + rev x7, x7 + rev x8, x8 + mov v1.d[1], x7 + rev x9, x9 +ST5( sub x10, IV_PART, #MAX_STRIDE - 4 ) + mov v2.d[1], x8 +ST5( rev x10, x10 ) + mov v3.d[1], x9 +ST5( mov v4.d[1], x10 ) + .endif + + /* + * If there are at least MAX_STRIDE blocks left, XOR the data with + * keystream and store. Otherwise jump to tail handling. + */ + tbnz BYTES_W, #31, .Lctrtail\xctr + ld1 {v5.16b-v7.16b}, [IN], #48 +ST4( bl aes_encrypt_block4x ) +ST5( bl aes_encrypt_block5x ) + eor v0.16b, v5.16b, v0.16b +ST4( ld1 {v5.16b}, [IN], #16 ) + eor v1.16b, v6.16b, v1.16b +ST5( ld1 {v5.16b-v6.16b}, [IN], #32 ) + eor v2.16b, v7.16b, v2.16b + eor v3.16b, v5.16b, v3.16b +ST5( eor v4.16b, v6.16b, v4.16b ) + st1 {v0.16b-v3.16b}, [OUT], #64 +ST5( st1 {v4.16b}, [OUT], #16 ) + cbz BYTES_W, .Lctrout\xctr + b .LctrloopNx\xctr + +.Lctrout\xctr: + .if !\xctr + st1 {vctr.16b}, [IV] /* return next CTR value */ + .endif + ldp x29, x30, [sp], #16 + ret + +.Lctrtail\xctr: + /* + * Handle up to MAX_STRIDE * 16 - 1 bytes of plaintext + * + * This code expects the last keystream block to be in v{MAX_STRIDE-1}. + * For example: if encrypting two blocks with MAX_STRIDE=5, then v3 and + * v4 should have the next two counter blocks. + * + * This allows us to store the ciphertext by writing to overlapping + * regions of memory. Any invalid ciphertext blocks get overwritten by + * correctly computed blocks. This approach greatly simplifies the + * logic for storing the ciphertext. + */ + mov x16, #16 + ands w7, BYTES_W, #0xf + csel x13, x7, x16, ne + +ST5( cmp BYTES_W, #64 - (MAX_STRIDE << 4)) +ST5( csel x14, x16, xzr, gt ) + cmp BYTES_W, #48 - (MAX_STRIDE << 4) + csel x15, x16, xzr, gt + cmp BYTES_W, #32 - (MAX_STRIDE << 4) + csel x16, x16, xzr, gt + cmp BYTES_W, #16 - (MAX_STRIDE << 4) + + adr_l x9, .Lcts_permute_table + add x9, x9, x13 + ble .Lctrtail1x\xctr + +ST5( ld1 {v5.16b}, [IN], x14 ) + ld1 {v6.16b}, [IN], x15 + ld1 {v7.16b}, [IN], x16 + +ST4( bl aes_encrypt_block4x ) +ST5( bl aes_encrypt_block5x ) + + ld1 {v8.16b}, [IN], x13 + ld1 {v9.16b}, [IN] + ld1 {v10.16b}, [x9] + +ST4( eor v6.16b, v6.16b, v0.16b ) +ST4( eor v7.16b, v7.16b, v1.16b ) +ST4( tbl v3.16b, {v3.16b}, v10.16b ) +ST4( eor v8.16b, v8.16b, v2.16b ) +ST4( eor v9.16b, v9.16b, v3.16b ) + +ST5( eor v5.16b, v5.16b, v0.16b ) +ST5( eor v6.16b, v6.16b, v1.16b ) +ST5( tbl v4.16b, {v4.16b}, v10.16b ) +ST5( eor v7.16b, v7.16b, v2.16b ) +ST5( eor v8.16b, v8.16b, v3.16b ) +ST5( eor v9.16b, v9.16b, v4.16b ) + +ST5( st1 {v5.16b}, [OUT], x14 ) + st1 {v6.16b}, [OUT], x15 + st1 {v7.16b}, [OUT], x16 + add x13, x13, OUT + st1 {v9.16b}, [x13] // overlapping stores + st1 {v8.16b}, [OUT] + b .Lctrout\xctr + +.Lctrtail1x\xctr: + /* + * Handle <= 16 bytes of plaintext + * + * This code always reads and writes 16 bytes. To avoid out of bounds + * accesses, XCTR and CTR modes must use a temporary buffer when + * encrypting/decrypting less than 16 bytes. + * + * This code is unusual in that it loads the input and stores the output + * relative to the end of the buffers rather than relative to the start. + * This causes unusual behaviour when encrypting/decrypting less than 16 + * bytes; the end of the data is expected to be at the end of the + * temporary buffer rather than the start of the data being at the start + * of the temporary buffer. + */ + sub x8, x7, #16 + csel x7, x7, x8, eq + add IN, IN, x7 + add OUT, OUT, x7 + ld1 {v5.16b}, [IN] + ld1 {v6.16b}, [OUT] +ST5( mov v3.16b, v4.16b ) + encrypt_block v3, ROUNDS_W, KEY, x8, w7 + ld1 {v10.16b-v11.16b}, [x9] + tbl v3.16b, {v3.16b}, v10.16b + sshr v11.16b, v11.16b, #7 + eor v5.16b, v5.16b, v3.16b + bif v5.16b, v6.16b, v11.16b + st1 {v5.16b}, [OUT] + b .Lctrout\xctr + + // Arguments + .unreq OUT + .unreq IN + .unreq KEY + .unreq ROUNDS_W + .unreq BYTES_W + .unreq IV + .unreq BYTE_CTR_W // XCTR only + // Intermediate values + .unreq CTR_W // XCTR only + .unreq CTR // XCTR only + .unreq IV_PART + .unreq BLOCKS + .unreq BLOCKS_W +.endm + + /* + * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, + * int bytes, u8 ctr[]) + * + * The input and output buffers must always be at least 16 bytes even if + * encrypting/decrypting less than 16 bytes. Otherwise out of bounds + * accesses will occur. The data to be encrypted/decrypted is expected + * to be at the end of this 16-byte temporary buffer rather than the + * start. + */ + +AES_FUNC_START(aes_ctr_encrypt) + ctr_encrypt 0 +AES_FUNC_END(aes_ctr_encrypt) + + /* + * aes_xctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds, + * int bytes, u8 const iv[], int byte_ctr) + * + * The input and output buffers must always be at least 16 bytes even if + * encrypting/decrypting less than 16 bytes. Otherwise out of bounds + * accesses will occur. The data to be encrypted/decrypted is expected + * to be at the end of this 16-byte temporary buffer rather than the + * start. + */ + +AES_FUNC_START(aes_xctr_encrypt) + ctr_encrypt 1 +AES_FUNC_END(aes_xctr_encrypt) + + + /* + * aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds, + * int bytes, u8 const rk2[], u8 iv[], int first) * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds, - * int blocks, u8 const rk2[], u8 iv[], int first) - * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds, - * int blocks, u8 const rk2[], u8 iv[], int first) + * int bytes, u8 const rk2[], u8 iv[], int first) */ - .macro next_tweak, out, in, const, tmp + .macro next_tweak, out, in, tmp sshr \tmp\().2d, \in\().2d, #63 - and \tmp\().16b, \tmp\().16b, \const\().16b + and \tmp\().16b, \tmp\().16b, xtsmask.16b add \out\().2d, \in\().2d, \in\().2d ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8 eor \out\().16b, \out\().16b, \tmp\().16b .endm -.Lxts_mul_x: -CPU_LE( .quad 1, 0x87 ) -CPU_BE( .quad 0x87, 1 ) + .macro xts_load_mask, tmp + movi xtsmask.2s, #0x1 + movi \tmp\().2s, #0x87 + uzp1 xtsmask.4s, xtsmask.4s, \tmp\().4s + .endm -AES_ENTRY(aes_xts_encrypt) - FRAME_PUSH - cbz w7, .LxtsencloopNx +AES_FUNC_START(aes_xts_encrypt) + stp x29, x30, [sp, #-16]! + mov x29, sp ld1 {v4.16b}, [x6] - enc_prepare w3, x5, x6 - encrypt_block v4, w3, x5, x6, w7 /* first tweak */ - enc_switch_key w3, x2, x6 - ldr q7, .Lxts_mul_x + xts_load_mask v8 + cbz w7, .Lxtsencnotfirst + + enc_prepare w3, x5, x8 + xts_cts_skip_tw w7, .LxtsencNx + encrypt_block v4, w3, x5, x8, w7 /* first tweak */ + enc_switch_key w3, x2, x8 b .LxtsencNx +.Lxtsencnotfirst: + enc_prepare w3, x2, x8 .LxtsencloopNx: - ldr q7, .Lxts_mul_x - next_tweak v4, v4, v7, v8 + next_tweak v4, v4, v8 .LxtsencNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #64 bmi .Lxtsenc1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */ - next_tweak v5, v4, v7, v8 - eor v0.16b, v0.16b, v4.16b - eor v1.16b, v1.16b, v5.16b - do_encrypt_block2x - eor v0.16b, v0.16b, v4.16b - eor v1.16b, v1.16b, v5.16b - st1 {v0.16b-v1.16b}, [x0], #32 - cbz w4, .LxtsencoutNx - next_tweak v4, v5, v7, v8 - b .LxtsencNx -.LxtsencoutNx: - mov v4.16b, v5.16b - b .Lxtsencout -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */ - next_tweak v5, v4, v7, v8 + next_tweak v5, v4, v8 eor v0.16b, v0.16b, v4.16b - next_tweak v6, v5, v7, v8 + next_tweak v6, v5, v8 eor v1.16b, v1.16b, v5.16b eor v2.16b, v2.16b, v6.16b - next_tweak v7, v6, v7, v8 + next_tweak v7, v6, v8 eor v3.16b, v3.16b, v7.16b - do_encrypt_block4x + bl aes_encrypt_block4x eor v3.16b, v3.16b, v7.16b eor v0.16b, v0.16b, v4.16b eor v1.16b, v1.16b, v5.16b eor v2.16b, v2.16b, v6.16b st1 {v0.16b-v3.16b}, [x0], #64 mov v4.16b, v7.16b - cbz w4, .Lxtsencout + cbz w4, .Lxtsencret + xts_reload_mask v8 b .LxtsencloopNx -#endif .Lxtsenc1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #64 beq .Lxtsencout -#endif + subs w4, w4, #16 + bmi .LxtsencctsNx .Lxtsencloop: - ld1 {v1.16b}, [x1], #16 - eor v0.16b, v1.16b, v4.16b - encrypt_block v0, w3, x2, x6, w7 + ld1 {v0.16b}, [x1], #16 +.Lxtsencctsout: + eor v0.16b, v0.16b, v4.16b + encrypt_block v0, w3, x2, x8, w7 eor v0.16b, v0.16b, v4.16b + cbz w4, .Lxtsencout + subs w4, w4, #16 + next_tweak v4, v4, v8 + bmi .Lxtsenccts st1 {v0.16b}, [x0], #16 - subs w4, w4, #1 - beq .Lxtsencout - next_tweak v4, v4, v7, v8 b .Lxtsencloop .Lxtsencout: - FRAME_POP + st1 {v0.16b}, [x0] +.Lxtsencret: + st1 {v4.16b}, [x6] + ldp x29, x30, [sp], #16 ret -AES_ENDPROC(aes_xts_encrypt) - -AES_ENTRY(aes_xts_decrypt) - FRAME_PUSH - cbz w7, .LxtsdecloopNx +.LxtsencctsNx: + mov v0.16b, v3.16b + sub x0, x0, #16 +.Lxtsenccts: + adr_l x8, .Lcts_permute_table + + add x1, x1, w4, sxtw /* rewind input pointer */ + add w4, w4, #16 /* # bytes in final block */ + add x9, x8, #32 + add x8, x8, x4 + sub x9, x9, x4 + add x4, x0, x4 /* output address of final block */ + + ld1 {v1.16b}, [x1] /* load final block */ + ld1 {v2.16b}, [x8] + ld1 {v3.16b}, [x9] + + tbl v2.16b, {v0.16b}, v2.16b + tbx v0.16b, {v1.16b}, v3.16b + st1 {v2.16b}, [x4] /* overlapping stores */ + mov w4, wzr + b .Lxtsencctsout +AES_FUNC_END(aes_xts_encrypt) + +AES_FUNC_START(aes_xts_decrypt) + stp x29, x30, [sp, #-16]! + mov x29, sp + + /* subtract 16 bytes if we are doing CTS */ + sub w8, w4, #0x10 + tst w4, #0xf + csel w4, w4, w8, eq ld1 {v4.16b}, [x6] - enc_prepare w3, x5, x6 - encrypt_block v4, w3, x5, x6, w7 /* first tweak */ - dec_prepare w3, x2, x6 - ldr q7, .Lxts_mul_x + xts_load_mask v8 + xts_cts_skip_tw w7, .Lxtsdecskiptw + cbz w7, .Lxtsdecnotfirst + + enc_prepare w3, x5, x8 + encrypt_block v4, w3, x5, x8, w7 /* first tweak */ +.Lxtsdecskiptw: + dec_prepare w3, x2, x8 b .LxtsdecNx +.Lxtsdecnotfirst: + dec_prepare w3, x2, x8 .LxtsdecloopNx: - ldr q7, .Lxts_mul_x - next_tweak v4, v4, v7, v8 + next_tweak v4, v4, v8 .LxtsdecNx: -#if INTERLEAVE >= 2 - subs w4, w4, #INTERLEAVE + subs w4, w4, #64 bmi .Lxtsdec1x -#if INTERLEAVE == 2 - ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */ - next_tweak v5, v4, v7, v8 - eor v0.16b, v0.16b, v4.16b - eor v1.16b, v1.16b, v5.16b - do_decrypt_block2x - eor v0.16b, v0.16b, v4.16b - eor v1.16b, v1.16b, v5.16b - st1 {v0.16b-v1.16b}, [x0], #32 - cbz w4, .LxtsdecoutNx - next_tweak v4, v5, v7, v8 - b .LxtsdecNx -.LxtsdecoutNx: - mov v4.16b, v5.16b - b .Lxtsdecout -#else ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */ - next_tweak v5, v4, v7, v8 + next_tweak v5, v4, v8 eor v0.16b, v0.16b, v4.16b - next_tweak v6, v5, v7, v8 + next_tweak v6, v5, v8 eor v1.16b, v1.16b, v5.16b eor v2.16b, v2.16b, v6.16b - next_tweak v7, v6, v7, v8 + next_tweak v7, v6, v8 eor v3.16b, v3.16b, v7.16b - do_decrypt_block4x + bl aes_decrypt_block4x eor v3.16b, v3.16b, v7.16b eor v0.16b, v0.16b, v4.16b eor v1.16b, v1.16b, v5.16b @@ -505,36 +774,88 @@ AES_ENTRY(aes_xts_decrypt) st1 {v0.16b-v3.16b}, [x0], #64 mov v4.16b, v7.16b cbz w4, .Lxtsdecout + xts_reload_mask v8 b .LxtsdecloopNx -#endif .Lxtsdec1x: - adds w4, w4, #INTERLEAVE + adds w4, w4, #64 beq .Lxtsdecout -#endif + subs w4, w4, #16 .Lxtsdecloop: - ld1 {v1.16b}, [x1], #16 - eor v0.16b, v1.16b, v4.16b - decrypt_block v0, w3, x2, x6, w7 + ld1 {v0.16b}, [x1], #16 + bmi .Lxtsdeccts +.Lxtsdecctsout: + eor v0.16b, v0.16b, v4.16b + decrypt_block v0, w3, x2, x8, w7 eor v0.16b, v0.16b, v4.16b st1 {v0.16b}, [x0], #16 - subs w4, w4, #1 - beq .Lxtsdecout - next_tweak v4, v4, v7, v8 + cbz w4, .Lxtsdecout + subs w4, w4, #16 + next_tweak v4, v4, v8 b .Lxtsdecloop .Lxtsdecout: - FRAME_POP + st1 {v4.16b}, [x6] + ldp x29, x30, [sp], #16 ret -AES_ENDPROC(aes_xts_decrypt) + +.Lxtsdeccts: + adr_l x8, .Lcts_permute_table + + add x1, x1, w4, sxtw /* rewind input pointer */ + add w4, w4, #16 /* # bytes in final block */ + add x9, x8, #32 + add x8, x8, x4 + sub x9, x9, x4 + add x4, x0, x4 /* output address of final block */ + + next_tweak v5, v4, v8 + + ld1 {v1.16b}, [x1] /* load final block */ + ld1 {v2.16b}, [x8] + ld1 {v3.16b}, [x9] + + eor v0.16b, v0.16b, v5.16b + decrypt_block v0, w3, x2, x8, w7 + eor v0.16b, v0.16b, v5.16b + + tbl v2.16b, {v0.16b}, v2.16b + tbx v0.16b, {v1.16b}, v3.16b + + st1 {v2.16b}, [x4] /* overlapping stores */ + mov w4, wzr + b .Lxtsdecctsout +AES_FUNC_END(aes_xts_decrypt) /* * aes_mac_update(u8 const in[], u32 const rk[], int rounds, * int blocks, u8 dg[], int enc_before, int enc_after) */ -AES_ENTRY(aes_mac_update) +AES_FUNC_START(aes_mac_update) ld1 {v0.16b}, [x4] /* get dg */ enc_prepare w2, x1, x7 - cbnz w5, .Lmacenc + cbz w5, .Lmacloop4x + + encrypt_block v0, w2, x1, x7, w8 +.Lmacloop4x: + subs w3, w3, #4 + bmi .Lmac1x + ld1 {v1.16b-v4.16b}, [x0], #64 /* get next pt block */ + eor v0.16b, v0.16b, v1.16b /* ..and xor with dg */ + encrypt_block v0, w2, x1, x7, w8 + eor v0.16b, v0.16b, v2.16b + encrypt_block v0, w2, x1, x7, w8 + eor v0.16b, v0.16b, v3.16b + encrypt_block v0, w2, x1, x7, w8 + eor v0.16b, v0.16b, v4.16b + cmp w3, wzr + csinv x5, x6, xzr, eq + cbz w5, .Lmacout + encrypt_block v0, w2, x1, x7, w8 + st1 {v0.16b}, [x4] /* return dg */ + cond_yield .Lmacout, x7, x8 + b .Lmacloop4x +.Lmac1x: + add w3, w3, #4 .Lmacloop: cbz w3, .Lmacout ld1 {v1.16b}, [x0], #16 /* get next pt block */ @@ -550,5 +871,6 @@ AES_ENTRY(aes_mac_update) .Lmacout: st1 {v0.16b}, [x4] /* return dg */ + mov w0, w3 ret -AES_ENDPROC(aes_mac_update) +AES_FUNC_END(aes_mac_update) |