ceph/src/crypto/isa-l/isa-l_crypto/aes/cbc_enc_128_x4_sb.asm

   1 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
   2 ;  Copyright(c) 2011-2016 Intel Corporation All rights reserved.
   3 ;
   4 ;  Redistribution and use in source and binary forms, with or without
   5 ;  modification, are permitted provided that the following conditions
   6 ;  are met:
   7 ;    * Redistributions of source code must retain the above copyright
   8 ;      notice, this list of conditions and the following disclaimer.
   9 ;    * Redistributions in binary form must reproduce the above copyright
  10 ;      notice, this list of conditions and the following disclaimer in
  11 ;      the documentation and/or other materials provided with the
  12 ;      distribution.
  13 ;    * Neither the name of Intel Corporation nor the names of its
  14 ;      contributors may be used to endorse or promote products derived
  15 ;      from this software without specific prior written permission.
  16 ;
  17 ;  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  18 ;  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  19 ;  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  20 ;  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  21 ;  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  22 ;  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  23 ;  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  24 ;  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  25 ;  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  26 ;  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  27 ;  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  28 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  29
  30 ;;; routine to do a 128 bit CBC AES encrypt
  31 ;;; Updates In and Out pointers at end
  32 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  33 ;;void aes_cbc_enc_128_x4(void      *in,
  34 ;;                        uint8_t   *IV,
  35 ;;                        uint8_t   *keys,
  36 ;;                        void      *out,
  37 ;;                        uint64_t   len_bytes);
  38 ; arg 1: IN:   pointer to input (cipher text)
  39 ; arg 2: IV:   pointer to IV
  40 ; arg 3: KEYS: pointer to keys
  41 ; arg 4: OUT:  pointer to output (plain text)
  42 ; arg 5: LEN:  length in bytes (multiple of 16)
  43
  44 %include "reg_sizes.asm"
  45
  46 %ifidn __OUTPUT_FORMAT__, elf64
  47 %define IN0             rdi
  48 %define IN              rdi
  49 %define IV              rsi
  50 %define KEYS    rdx
  51 %define OUT     rcx
  52 %define LEN             r8
  53 %define KEYS0   rdx
  54 %define OUT0    rcx
  55 %define func(x) x:
  56 %define FUNC_SAVE
  57 %define FUNC_RESTORE
  58 %endif
  59
  60 %ifidn __OUTPUT_FORMAT__, win64
  61 %define IN0             rcx
  62 %define IN              rcx
  63 %define IV              rdx
  64 %define KEYS0   r8
  65 %define OUT0    r9
  66 %define KEYS    r8
  67 %define OUT             r9
  68 %define LEN             r10
  69 %define PS              8
  70 %define stack_size      10*16 + 1*8     ; must be an odd multiple of 8
  71 %define arg(x)          [rsp + stack_size + PS + PS*x]
  72
  73 %define func(x) proc_frame x
  74 %macro FUNC_SAVE 0
  75         alloc_stack     stack_size
  76         save_xmm128     xmm6, 0*16
  77         save_xmm128     xmm7, 1*16
  78         save_xmm128     xmm8, 2*16
  79         save_xmm128     xmm9, 3*16
  80         save_xmm128     xmm10, 4*16
  81         save_xmm128     xmm11, 5*16
  82         save_xmm128     xmm12, 6*16
  83         save_xmm128     xmm13, 7*16
  84         save_xmm128     xmm14, 8*16
  85         save_xmm128     xmm15, 9*16
  86         end_prolog
  87         mov     LEN, arg(4)
  88 %endmacro
  89
  90 %macro FUNC_RESTORE 0
  91         movdqa  xmm6, [rsp + 0*16]
  92         movdqa  xmm7, [rsp + 1*16]
  93         movdqa  xmm8, [rsp + 2*16]
  94         movdqa  xmm9, [rsp + 3*16]
  95         movdqa  xmm10, [rsp + 4*16]
  96         movdqa  xmm11, [rsp + 5*16]
  97         movdqa  xmm12, [rsp + 6*16]
  98         movdqa  xmm13, [rsp + 7*16]
  99         movdqa  xmm14, [rsp + 8*16]
 100         movdqa  xmm15, [rsp + 9*16]
 101         add     rsp, stack_size
 102 %endmacro
 103 %endif
 104
 105 %define KEY_ROUNDS 11
 106 %define XMM_USAGE    (16)
 107 %define UNROLLED_LOOPS (3)
 108 %define PARALLEL_BLOCKS (UNROLLED_LOOPS)
 109 %define EARLY_BLOCKS (2)
 110
 111 ; instruction set specific operation definitions
 112 %define MOVDQ         movdqu
 113 %define PXOR          pxor
 114 %define AES_ENC       aesenc
 115 %define AES_ENC_LAST  aesenclast
 116
 117 %include "cbc_common.asm"
 118
 119
 120 global aes_cbc_enc_128_x4:function
 121 func(aes_cbc_enc_128_x4)
 122         FUNC_SAVE
 123
 124         mov     IDX, 0
 125         FILL_KEY_CACHE   CKEY_CNT, FIRST_CKEY, KEYS, MOVDQ
 126         CBC_ENC_INIT     FIRST_XDATA, TMP, MOVDQ, PXOR, IV, IN, IDX
 127
 128 main_loop:
 129         CBC_ENC_SUBLOOP  KEY_ROUNDS, UNROLLED_LOOPS, FIRST_XDATA, MOVDQ, PXOR, AES_ENC, AES_ENC_LAST, TMP, TMP_CNT, FIRST_CKEY, CKEY_CNT, KEYS, CACHED_KEYS, IN, OUT, IDX, LEN
 130         jne     main_loop
 131
 132 done:
 133         FUNC_RESTORE
 134         ret
 135
 136 endproc_frame