1 /* SPDX-License-Identifier: GPL-2.0-only */ 2 /* 3 * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions 4 * 5 * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org> 6 */ 7 8 #include <linux/linkage.h> 9 #include <asm/assembler.h> 10 11 .text 12 .arch armv8-a+crypto 13 14 /* 15 * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes, 16 * u32 *macp, u8 const rk[], u32 rounds); 17 */ 18 SYM_FUNC_START(ce_aes_ccm_auth_data) 19 ldr w8, [x3] /* leftover from prev round? */ 20 ld1 {v0.16b}, [x0] /* load mac */ 21 cbz w8, 1f 22 sub w8, w8, #16 23 eor v1.16b, v1.16b, v1.16b 24 0: ldrb w7, [x1], #1 /* get 1 byte of input */ 25 subs w2, w2, #1 26 add w8, w8, #1 27 ins v1.b[0], w7 28 ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */ 29 beq 8f /* out of input? */ 30 cbnz w8, 0b 31 eor v0.16b, v0.16b, v1.16b 32 1: ld1 {v3.4s}, [x4] /* load first round key */ 33 prfm pldl1strm, [x1] 34 cmp w5, #12 /* which key size? */ 35 add x6, x4, #16 36 sub w7, w5, #2 /* modified # of rounds */ 37 bmi 2f 38 bne 5f 39 mov v5.16b, v3.16b 40 b 4f 41 2: mov v4.16b, v3.16b 42 ld1 {v5.4s}, [x6], #16 /* load 2nd round key */ 43 3: aese v0.16b, v4.16b 44 aesmc v0.16b, v0.16b 45 4: ld1 {v3.4s}, [x6], #16 /* load next round key */ 46 aese v0.16b, v5.16b 47 aesmc v0.16b, v0.16b 48 5: ld1 {v4.4s}, [x6], #16 /* load next round key */ 49 subs w7, w7, #3 50 aese v0.16b, v3.16b 51 aesmc v0.16b, v0.16b 52 ld1 {v5.4s}, [x6], #16 /* load next round key */ 53 bpl 3b 54 aese v0.16b, v4.16b 55 subs w2, w2, #16 /* last data? */ 56 eor v0.16b, v0.16b, v5.16b /* final round */ 57 bmi 6f 58 ld1 {v1.16b}, [x1], #16 /* load next input block */ 59 eor v0.16b, v0.16b, v1.16b /* xor with mac */ 60 bne 1b 61 6: st1 {v0.16b}, [x0] /* store mac */ 62 beq 10f 63 adds w2, w2, #16 64 beq 10f 65 mov w8, w2 66 7: ldrb w7, [x1], #1 67 umov w6, v0.b[0] 68 eor w6, w6, w7 69 strb w6, [x0], #1 70 subs w2, w2, #1 71 beq 10f 72 ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */ 73 b 7b 74 8: cbz w8, 91f 75 mov w7, w8 76 add w8, w8, #16 77 9: ext v1.16b, v1.16b, v1.16b, #1 78 adds w7, w7, #1 79 bne 9b 80 91: eor v0.16b, v0.16b, v1.16b 81 st1 {v0.16b}, [x0] 82 10: str w8, [x3] 83 ret 84 SYM_FUNC_END(ce_aes_ccm_auth_data) 85 86 /* 87 * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[], 88 * u32 rounds); 89 */ 90 SYM_FUNC_START(ce_aes_ccm_final) 91 ld1 {v3.4s}, [x2], #16 /* load first round key */ 92 ld1 {v0.16b}, [x0] /* load mac */ 93 cmp w3, #12 /* which key size? */ 94 sub w3, w3, #2 /* modified # of rounds */ 95 ld1 {v1.16b}, [x1] /* load 1st ctriv */ 96 bmi 0f 97 bne 3f 98 mov v5.16b, v3.16b 99 b 2f 100 0: mov v4.16b, v3.16b 101 1: ld1 {v5.4s}, [x2], #16 /* load next round key */ 102 aese v0.16b, v4.16b 103 aesmc v0.16b, v0.16b 104 aese v1.16b, v4.16b 105 aesmc v1.16b, v1.16b 106 2: ld1 {v3.4s}, [x2], #16 /* load next round key */ 107 aese v0.16b, v5.16b 108 aesmc v0.16b, v0.16b 109 aese v1.16b, v5.16b 110 aesmc v1.16b, v1.16b 111 3: ld1 {v4.4s}, [x2], #16 /* load next round key */ 112 subs w3, w3, #3 113 aese v0.16b, v3.16b 114 aesmc v0.16b, v0.16b 115 aese v1.16b, v3.16b 116 aesmc v1.16b, v1.16b 117 bpl 1b 118 aese v0.16b, v4.16b 119 aese v1.16b, v4.16b 120 /* final round key cancels out */ 121 eor v0.16b, v0.16b, v1.16b /* en-/decrypt the mac */ 122 st1 {v0.16b}, [x0] /* store result */ 123 ret 124 SYM_FUNC_END(ce_aes_ccm_final) 125 126 .macro aes_ccm_do_crypt,enc 127 ldr x8, [x6, #8] /* load lower ctr */ 128 ld1 {v0.16b}, [x5] /* load mac */ 129 CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */ 130 0: /* outer loop */ 131 ld1 {v1.8b}, [x6] /* load upper ctr */ 132 prfm pldl1strm, [x1] 133 add x8, x8, #1 134 rev x9, x8 135 cmp w4, #12 /* which key size? */ 136 sub w7, w4, #2 /* get modified # of rounds */ 137 ins v1.d[1], x9 /* no carry in lower ctr */ 138 ld1 {v3.4s}, [x3] /* load first round key */ 139 add x10, x3, #16 140 bmi 1f 141 bne 4f 142 mov v5.16b, v3.16b 143 b 3f 144 1: mov v4.16b, v3.16b 145 ld1 {v5.4s}, [x10], #16 /* load 2nd round key */ 146 2: /* inner loop: 3 rounds, 2x interleaved */ 147 aese v0.16b, v4.16b 148 aesmc v0.16b, v0.16b 149 aese v1.16b, v4.16b 150 aesmc v1.16b, v1.16b 151 3: ld1 {v3.4s}, [x10], #16 /* load next round key */ 152 aese v0.16b, v5.16b 153 aesmc v0.16b, v0.16b 154 aese v1.16b, v5.16b 155 aesmc v1.16b, v1.16b 156 4: ld1 {v4.4s}, [x10], #16 /* load next round key */ 157 subs w7, w7, #3 158 aese v0.16b, v3.16b 159 aesmc v0.16b, v0.16b 160 aese v1.16b, v3.16b 161 aesmc v1.16b, v1.16b 162 ld1 {v5.4s}, [x10], #16 /* load next round key */ 163 bpl 2b 164 aese v0.16b, v4.16b 165 aese v1.16b, v4.16b 166 subs w2, w2, #16 167 bmi 6f /* partial block? */ 168 ld1 {v2.16b}, [x1], #16 /* load next input block */ 169 .if \enc == 1 170 eor v2.16b, v2.16b, v5.16b /* final round enc+mac */ 171 eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */ 172 .else 173 eor v2.16b, v2.16b, v1.16b /* xor with crypted ctr */ 174 eor v1.16b, v2.16b, v5.16b /* final round enc */ 175 .endif 176 eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */ 177 st1 {v1.16b}, [x0], #16 /* write output block */ 178 bne 0b 179 CPU_LE( rev x8, x8 ) 180 st1 {v0.16b}, [x5] /* store mac */ 181 str x8, [x6, #8] /* store lsb end of ctr (BE) */ 182 5: ret 183 184 6: eor v0.16b, v0.16b, v5.16b /* final round mac */ 185 eor v1.16b, v1.16b, v5.16b /* final round enc */ 186 st1 {v0.16b}, [x5] /* store mac */ 187 add w2, w2, #16 /* process partial tail block */ 188 7: ldrb w9, [x1], #1 /* get 1 byte of input */ 189 umov w6, v1.b[0] /* get top crypted ctr byte */ 190 umov w7, v0.b[0] /* get top mac byte */ 191 .if \enc == 1 192 eor w7, w7, w9 193 eor w9, w9, w6 194 .else 195 eor w9, w9, w6 196 eor w7, w7, w9 197 .endif 198 strb w9, [x0], #1 /* store out byte */ 199 strb w7, [x5], #1 /* store mac byte */ 200 subs w2, w2, #1 201 beq 5b 202 ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */ 203 ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */ 204 b 7b 205 .endm 206 207 /* 208 * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes, 209 * u8 const rk[], u32 rounds, u8 mac[], 210 * u8 ctr[]); 211 * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes, 212 * u8 const rk[], u32 rounds, u8 mac[], 213 * u8 ctr[]); 214 */ 215 SYM_FUNC_START(ce_aes_ccm_encrypt) 216 aes_ccm_do_crypt 1 217 SYM_FUNC_END(ce_aes_ccm_encrypt) 218 219 SYM_FUNC_START(ce_aes_ccm_decrypt) 220 aes_ccm_do_crypt 0 221 SYM_FUNC_END(ce_aes_ccm_decrypt) 222