udp2raw/lib/aes_acc/aesni.c

/*
 * This file is adapted from PolarSSL 1.3.19 (GPL)
 */

/*
 *  AES-NI support functions
 *
 *  Copyright (C) 2006-2014, ARM Limited, All Rights Reserved
 *
 *  This file is part of mbed TLS (https://tls.mbed.org)
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License along
 *  with this program; if not, write to the Free Software Foundation, Inc.,
 *  51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
 */

/*
 * [AES-WP] http://software.intel.com/en-us/articles/intel-advanced-encryption-standard-aes-instructions-set
 * [CLMUL-WP] http://software.intel.com/en-us/articles/intel-carry-less-multiplication-instruction-and-its-usage-for-computing-the-gcm-mode/
 */

#include <string.h>
#include "aesni.h"

#if defined(HAVE_AMD64)

/*
 * AES-NI support detection routine
 */
#define AESNI_AES 0x02000000u

int aesni_supported( void )
{
    static int done = 0;
    static unsigned int c = 0;

    if( ! done )
    {
        asm( "movl  $1, %%eax   \n\t"
             "cpuid             \n\t"
             : "=c" (c)
             :
             : "eax", "ebx", "edx" );
        done = 1;
    }

    return( ( c & AESNI_AES ) != 0 );
}

/*
 * Binutils needs to be at least 2.19 to support AES-NI instructions.
 * Unfortunately, a lot of users have a lower version now (2014-04).
 * Emit bytecode directly in order to support "old" version of gas.
 *
 * Opcodes from the Intel architecture reference manual, vol. 3.
 * We always use registers, so we don't need prefixes for memory operands.
 * Operand macros are in gas order (src, dst) as opposed to Intel order
 * (dst, src) in order to blend better into the surrounding assembly code.
 */
#define AESDEC      ".byte 0x66,0x0F,0x38,0xDE,"
#define AESDECLAST  ".byte 0x66,0x0F,0x38,0xDF,"
#define AESENC      ".byte 0x66,0x0F,0x38,0xDC,"
#define AESENCLAST  ".byte 0x66,0x0F,0x38,0xDD,"
#define AESIMC      ".byte 0x66,0x0F,0x38,0xDB,"
#define AESKEYGENA  ".byte 0x66,0x0F,0x3A,0xDF,"
#define PCLMULQDQ   ".byte 0x66,0x0F,0x3A,0x44,"

#define xmm0_xmm0   "0xC0"
#define xmm0_xmm1   "0xC8"
#define xmm0_xmm2   "0xD0"
#define xmm0_xmm3   "0xD8"
#define xmm0_xmm4   "0xE0"
#define xmm1_xmm0   "0xC1"
#define xmm1_xmm2   "0xD1"

/*
 * AES-NI AES-ECB block en(de)cryption
 */
void aesni_crypt_ecb( int nr,
                      unsigned char *rk,
                      int mode,
                      const unsigned char input[16],
                      unsigned char output[16] )
{
    asm( "movdqu    (%3), %%xmm0    \n\t" // load input
         "movdqu    (%1), %%xmm1    \n\t" // load round key 0
         "pxor      %%xmm1, %%xmm0  \n\t" // round 0
         "addq      $16, %1         \n\t" // point to next round key
         "subl      $1, %0          \n\t" // normal rounds = nr - 1
         "test      %2, %2          \n\t" // mode?
         "jz        2f              \n\t" // 0 = decrypt

         "1:                        \n\t" // encryption loop
         "movdqu    (%1), %%xmm1    \n\t" // load round key
         AESENC     xmm1_xmm0      "\n\t" // do round
         "addq      $16, %1         \n\t" // point to next round key
         "subl      $1, %0          \n\t" // loop
         "jnz       1b              \n\t"
         "movdqu    (%1), %%xmm1    \n\t" // load round key
         AESENCLAST xmm1_xmm0      "\n\t" // last round
         "jmp       3f              \n\t"

         "2:                        \n\t" // decryption loop
         "movdqu    (%1), %%xmm1    \n\t"
         AESDEC     xmm1_xmm0      "\n\t" // do round
         "addq      $16, %1         \n\t"
         "subl      $1, %0          \n\t"
         "jnz       2b              \n\t"
         "movdqu    (%1), %%xmm1    \n\t" // load round key
         AESDECLAST xmm1_xmm0      "\n\t" // last round

         "3:                        \n\t"
         "movdqu    %%xmm0, (%4)    \n\t" // export output
         :
         : "r" (nr), "r" (rk), "r" (mode), "r" (input), "r" (output)
         : "memory", "cc", "xmm0", "xmm1" );
}

/*
 * Compute decryption round keys from encryption round keys
 */
void aesni_inverse_key( unsigned char *invkey,
                        const unsigned char *fwdkey, int nr )
{
    unsigned char *ik = invkey;
    const unsigned char *fk = fwdkey + 16 * nr;

    memcpy( ik, fk, 16 );

    for( fk -= 16, ik += 16; fk > fwdkey; fk -= 16, ik += 16 )
        asm( "movdqu (%0), %%xmm0       \n\t"
             AESIMC  xmm0_xmm0         "\n\t"
             "movdqu %%xmm0, (%1)       \n\t"
             :
             : "r" (fk), "r" (ik)
             : "memory", "xmm0" );

    memcpy( ik, fk, 16 );
}

/*
 * Key expansion, 128-bit case
 */
void aesni_setkey_enc_128( unsigned char *rk,
                           const unsigned char *key )
{
    asm( "movdqu (%1), %%xmm0               \n\t" // copy the original key
         "movdqu %%xmm0, (%0)               \n\t" // as round key 0
         "jmp 2f                            \n\t" // skip auxiliary routine

         /*
          * Finish generating the next round key.
          *
          * On entry xmm0 is r3:r2:r1:r0 and xmm1 is X:stuff:stuff:stuff
          * with X = rot( sub( r3 ) ) ^ RCON.
          *
          * On exit, xmm0 is r7:r6:r5:r4
          * with r4 = X + r0, r5 = r4 + r1, r6 = r5 + r2, r7 = r6 + r3
          * and those are written to the round key buffer.
          */
         "1:                                \n\t"
         "pshufd $0xff, %%xmm1, %%xmm1      \n\t" // X:X:X:X
         "pxor %%xmm0, %%xmm1               \n\t" // X+r3:X+r2:X+r1:r4
         "pslldq $4, %%xmm0                 \n\t" // r2:r1:r0:0
         "pxor %%xmm0, %%xmm1               \n\t" // X+r3+r2:X+r2+r1:r5:r4
         "pslldq $4, %%xmm0                 \n\t" // etc
         "pxor %%xmm0, %%xmm1               \n\t"
         "pslldq $4, %%xmm0                 \n\t"
         "pxor %%xmm1, %%xmm0               \n\t" // update xmm0 for next time!
         "add $16, %0                       \n\t" // point to next round key
         "movdqu %%xmm0, (%0)               \n\t" // write it
         "ret                               \n\t"

         /* Main "loop" */
         "2:                                \n\t"
         AESKEYGENA xmm0_xmm1 ",0x01        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x02        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x04        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x08        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x10        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x20        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x40        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x80        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x1B        \n\tcall 1b \n\t"
         AESKEYGENA xmm0_xmm1 ",0x36        \n\tcall 1b \n\t"
         :
         : "r" (rk), "r" (key)
         : "memory", "cc", "0" );
}

/*
 * Key expansion, 192-bit case
 */
void aesni_setkey_enc_192( unsigned char *rk,
                           const unsigned char *key )
{
    asm( "movdqu (%1), %%xmm0   \n\t" // copy original round key
         "movdqu %%xmm0, (%0)   \n\t"
         "add $16, %0           \n\t"
         "movq 16(%1), %%xmm1   \n\t"
         "movq %%xmm1, (%0)     \n\t"
         "add $8, %0            \n\t"
         "jmp 2f                \n\t" // skip auxiliary routine

         /*
          * Finish generating the next 6 quarter-keys.
          *
          * On entry xmm0 is r3:r2:r1:r0, xmm1 is stuff:stuff:r5:r4
          * and xmm2 is stuff:stuff:X:stuff with X = rot( sub( r3 ) ) ^ RCON.
          *
          * On exit, xmm0 is r9:r8:r7:r6 and xmm1 is stuff:stuff:r11:r10
          * and those are written to the round key buffer.
          */
         "1:                            \n\t"
         "pshufd $0x55, %%xmm2, %%xmm2  \n\t" // X:X:X:X
         "pxor %%xmm0, %%xmm2           \n\t" // X+r3:X+r2:X+r1:r4
         "pslldq $4, %%xmm0             \n\t" // etc
         "pxor %%xmm0, %%xmm2           \n\t"
         "pslldq $4, %%xmm0             \n\t"
         "pxor %%xmm0, %%xmm2           \n\t"
         "pslldq $4, %%xmm0             \n\t"
         "pxor %%xmm2, %%xmm0           \n\t" // update xmm0 = r9:r8:r7:r6
         "movdqu %%xmm0, (%0)           \n\t"
         "add $16, %0                   \n\t"
         "pshufd $0xff, %%xmm0, %%xmm2  \n\t" // r9:r9:r9:r9
         "pxor %%xmm1, %%xmm2           \n\t" // stuff:stuff:r9+r5:r10
         "pslldq $4, %%xmm1             \n\t" // r2:r1:r0:0
         "pxor %%xmm2, %%xmm1           \n\t" // xmm1 = stuff:stuff:r11:r10
         "movq %%xmm1, (%0)             \n\t"
         "add $8, %0                    \n\t"
         "ret                           \n\t"

         "2:                            \n\t"
         AESKEYGENA xmm1_xmm2 ",0x01    \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x02    \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x04    \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x08    \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x10    \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x20    \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x40    \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x80    \n\tcall 1b \n\t"

         :
         : "r" (rk), "r" (key)
         : "memory", "cc", "0" );
}

/*
 * Key expansion, 256-bit case
 */
void aesni_setkey_enc_256( unsigned char *rk,
                           const unsigned char *key )
{
    asm( "movdqu (%1), %%xmm0           \n\t"
         "movdqu %%xmm0, (%0)           \n\t"
         "add $16, %0                   \n\t"
         "movdqu 16(%1), %%xmm1         \n\t"
         "movdqu %%xmm1, (%0)           \n\t"
         "jmp 2f                        \n\t" // skip auxiliary routine

         /*
          * Finish generating the next two round keys.
          *
          * On entry xmm0 is r3:r2:r1:r0, xmm1 is r7:r6:r5:r4 and
          * xmm2 is X:stuff:stuff:stuff with X = rot( sub( r7 )) ^ RCON
          *
          * On exit, xmm0 is r11:r10:r9:r8 and xmm1 is r15:r14:r13:r12
          * and those have been written to the output buffer.
          */
         "1:                                \n\t"
         "pshufd $0xff, %%xmm2, %%xmm2      \n\t"
         "pxor %%xmm0, %%xmm2               \n\t"
         "pslldq $4, %%xmm0                 \n\t"
         "pxor %%xmm0, %%xmm2               \n\t"
         "pslldq $4, %%xmm0                 \n\t"
         "pxor %%xmm0, %%xmm2               \n\t"
         "pslldq $4, %%xmm0                 \n\t"
         "pxor %%xmm2, %%xmm0               \n\t"
         "add $16, %0                       \n\t"
         "movdqu %%xmm0, (%0)               \n\t"

         /* Set xmm2 to stuff:Y:stuff:stuff with Y = subword( r11 )
          * and proceed to generate next round key from there */
         AESKEYGENA xmm0_xmm2 ",0x00        \n\t"
         "pshufd $0xaa, %%xmm2, %%xmm2      \n\t"
         "pxor %%xmm1, %%xmm2               \n\t"
         "pslldq $4, %%xmm1                 \n\t"
         "pxor %%xmm1, %%xmm2               \n\t"
         "pslldq $4, %%xmm1                 \n\t"
         "pxor %%xmm1, %%xmm2               \n\t"
         "pslldq $4, %%xmm1                 \n\t"
         "pxor %%xmm2, %%xmm1               \n\t"
         "add $16, %0                       \n\t"
         "movdqu %%xmm1, (%0)               \n\t"
         "ret                               \n\t"

         /*
          * Main "loop" - Generating one more key than necessary,
          * see definition of aes_context.buf
          */
         "2:                                \n\t"
         AESKEYGENA xmm1_xmm2 ",0x01        \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x02        \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x04        \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x08        \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x10        \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x20        \n\tcall 1b \n\t"
         AESKEYGENA xmm1_xmm2 ",0x40        \n\tcall 1b \n\t"
         :
         : "r" (rk), "r" (key)
         : "memory", "cc", "0" );
}

#endif /* HAVE_AMD64 */