1
0
mirror of https://github.com/Mbed-TLS/mbedtls.git synced 2025-07-30 22:43:08 +03:00

Switch to the new code style

Signed-off-by: Gilles Peskine <Gilles.Peskine@arm.com>
This commit is contained in:
Gilles Peskine
2023-01-11 14:52:35 +01:00
parent 480f683d15
commit 1b6c09a62e
391 changed files with 73134 additions and 75084 deletions

View File

@ -28,7 +28,8 @@
#if defined(__has_feature)
#if __has_feature(memory_sanitizer)
#warning "MBEDTLS_AESNI_C is known to cause spurious error reports with some memory sanitizers as they do not understand the assembly code."
#warning \
"MBEDTLS_AESNI_C is known to cause spurious error reports with some memory sanitizers as they do not understand the assembly code."
#endif
#endif
@ -47,22 +48,21 @@
/*
* AES-NI support detection routine
*/
int mbedtls_aesni_has_support( unsigned int what )
int mbedtls_aesni_has_support(unsigned int what)
{
static int done = 0;
static unsigned int c = 0;
if( ! done )
{
asm( "movl $1, %%eax \n\t"
if (!done) {
asm ("movl $1, %%eax \n\t"
"cpuid \n\t"
: "=c" (c)
:
: "eax", "ebx", "edx" );
: "eax", "ebx", "edx");
done = 1;
}
return( ( c & what ) != 0 );
return (c & what) != 0;
}
/*
@ -94,12 +94,12 @@ int mbedtls_aesni_has_support( unsigned int what )
/*
* AES-NI AES-ECB block en(de)cryption
*/
int mbedtls_aesni_crypt_ecb( mbedtls_aes_context *ctx,
int mode,
const unsigned char input[16],
unsigned char output[16] )
int mbedtls_aesni_crypt_ecb(mbedtls_aes_context *ctx,
int mode,
const unsigned char input[16],
unsigned char output[16])
{
asm( "movdqu (%3), %%xmm0 \n\t" // load input
asm ("movdqu (%3), %%xmm0 \n\t" // load input
"movdqu (%1), %%xmm1 \n\t" // load round key 0
"pxor %%xmm1, %%xmm0 \n\t" // round 0
"add $16, %1 \n\t" // point to next round key
@ -110,51 +110,50 @@ int mbedtls_aesni_crypt_ecb( mbedtls_aes_context *ctx,
"1: \n\t" // encryption loop
"movdqu (%1), %%xmm1 \n\t" // load round key
AESENC xmm1_xmm0 "\n\t" // do round
"add $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
"add $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"
"jmp 3f \n\t"
"2: \n\t" // decryption loop
"movdqu (%1), %%xmm1 \n\t"
"2: \n\t" // decryption loop
"movdqu (%1), %%xmm1 \n\t"
AESDEC xmm1_xmm0 "\n\t" // do round
"add $16, %1 \n\t"
"subl $1, %0 \n\t"
"jnz 2b \n\t"
"movdqu (%1), %%xmm1 \n\t" // load round key
"add $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
"3: \n\t"
"movdqu %%xmm0, (%4) \n\t" // export output
:
: "r" (ctx->nr), "r" (ctx->rk), "r" (mode), "r" (input), "r" (output)
: "memory", "cc", "xmm0", "xmm1" );
: "memory", "cc", "xmm0", "xmm1");
return( 0 );
return 0;
}
/*
* GCM multiplication: c = a times b in GF(2^128)
* Based on [CLMUL-WP] algorithms 1 (with equation 27) and 5.
*/
void mbedtls_aesni_gcm_mult( unsigned char c[16],
const unsigned char a[16],
const unsigned char b[16] )
void mbedtls_aesni_gcm_mult(unsigned char c[16],
const unsigned char a[16],
const unsigned char b[16])
{
unsigned char aa[16], bb[16], cc[16];
size_t i;
/* The inputs are in big-endian order, so byte-reverse them */
for( i = 0; i < 16; i++ )
{
for (i = 0; i < 16; i++) {
aa[i] = a[15 - i];
bb[i] = b[15 - i];
}
asm( "movdqu (%0), %%xmm0 \n\t" // a1:a0
asm ("movdqu (%0), %%xmm0 \n\t" // a1:a0
"movdqu (%1), %%xmm1 \n\t" // b1:b0
/*
@ -168,30 +167,30 @@ void mbedtls_aesni_gcm_mult( unsigned char c[16],
PCLMULQDQ xmm0_xmm2 ",0x11 \n\t" // a1*b1 = d1:d0
PCLMULQDQ xmm0_xmm3 ",0x10 \n\t" // a0*b1 = e1:e0
PCLMULQDQ xmm0_xmm4 ",0x01 \n\t" // a1*b0 = f1:f0
"pxor %%xmm3, %%xmm4 \n\t" // e1+f1:e0+f0
"movdqa %%xmm4, %%xmm3 \n\t" // same
"psrldq $8, %%xmm4 \n\t" // 0:e1+f1
"pslldq $8, %%xmm3 \n\t" // e0+f0:0
"pxor %%xmm4, %%xmm2 \n\t" // d1:d0+e1+f1
"pxor %%xmm3, %%xmm1 \n\t" // c1+e0+f1:c0
"pxor %%xmm3, %%xmm4 \n\t" // e1+f1:e0+f0
"movdqa %%xmm4, %%xmm3 \n\t" // same
"psrldq $8, %%xmm4 \n\t" // 0:e1+f1
"pslldq $8, %%xmm3 \n\t" // e0+f0:0
"pxor %%xmm4, %%xmm2 \n\t" // d1:d0+e1+f1
"pxor %%xmm3, %%xmm1 \n\t" // c1+e0+f1:c0
/*
* Now shift the result one bit to the left,
* taking advantage of [CLMUL-WP] eq 27 (p. 20)
*/
"movdqa %%xmm1, %%xmm3 \n\t" // r1:r0
"movdqa %%xmm2, %%xmm4 \n\t" // r3:r2
"psllq $1, %%xmm1 \n\t" // r1<<1:r0<<1
"psllq $1, %%xmm2 \n\t" // r3<<1:r2<<1
"psrlq $63, %%xmm3 \n\t" // r1>>63:r0>>63
"psrlq $63, %%xmm4 \n\t" // r3>>63:r2>>63
"movdqa %%xmm3, %%xmm5 \n\t" // r1>>63:r0>>63
"pslldq $8, %%xmm3 \n\t" // r0>>63:0
"pslldq $8, %%xmm4 \n\t" // r2>>63:0
"psrldq $8, %%xmm5 \n\t" // 0:r1>>63
"por %%xmm3, %%xmm1 \n\t" // r1<<1|r0>>63:r0<<1
"por %%xmm4, %%xmm2 \n\t" // r3<<1|r2>>62:r2<<1
"por %%xmm5, %%xmm2 \n\t" // r3<<1|r2>>62:r2<<1|r1>>63
"movdqa %%xmm1, %%xmm3 \n\t" // r1:r0
"movdqa %%xmm2, %%xmm4 \n\t" // r3:r2
"psllq $1, %%xmm1 \n\t" // r1<<1:r0<<1
"psllq $1, %%xmm2 \n\t" // r3<<1:r2<<1
"psrlq $63, %%xmm3 \n\t" // r1>>63:r0>>63
"psrlq $63, %%xmm4 \n\t" // r3>>63:r2>>63
"movdqa %%xmm3, %%xmm5 \n\t" // r1>>63:r0>>63
"pslldq $8, %%xmm3 \n\t" // r0>>63:0
"pslldq $8, %%xmm4 \n\t" // r2>>63:0
"psrldq $8, %%xmm5 \n\t" // 0:r1>>63
"por %%xmm3, %%xmm1 \n\t" // r1<<1|r0>>63:r0<<1
"por %%xmm4, %%xmm2 \n\t" // r3<<1|r2>>62:r2<<1
"por %%xmm5, %%xmm2 \n\t" // r3<<1|r2>>62:r2<<1|r1>>63
/*
* Now reduce modulo the GCM polynomial x^128 + x^7 + x^2 + x + 1
@ -199,51 +198,52 @@ void mbedtls_aesni_gcm_mult( unsigned char c[16],
* Currently xmm2:xmm1 holds x3:x2:x1:x0 (already shifted).
*/
/* Step 2 (1) */
"movdqa %%xmm1, %%xmm3 \n\t" // x1:x0
"movdqa %%xmm1, %%xmm4 \n\t" // same
"movdqa %%xmm1, %%xmm5 \n\t" // same
"psllq $63, %%xmm3 \n\t" // x1<<63:x0<<63 = stuff:a
"psllq $62, %%xmm4 \n\t" // x1<<62:x0<<62 = stuff:b
"psllq $57, %%xmm5 \n\t" // x1<<57:x0<<57 = stuff:c
"movdqa %%xmm1, %%xmm3 \n\t" // x1:x0
"movdqa %%xmm1, %%xmm4 \n\t" // same
"movdqa %%xmm1, %%xmm5 \n\t" // same
"psllq $63, %%xmm3 \n\t" // x1<<63:x0<<63 = stuff:a
"psllq $62, %%xmm4 \n\t" // x1<<62:x0<<62 = stuff:b
"psllq $57, %%xmm5 \n\t" // x1<<57:x0<<57 = stuff:c
/* Step 2 (2) */
"pxor %%xmm4, %%xmm3 \n\t" // stuff:a+b
"pxor %%xmm5, %%xmm3 \n\t" // stuff:a+b+c
"pslldq $8, %%xmm3 \n\t" // a+b+c:0
"pxor %%xmm3, %%xmm1 \n\t" // x1+a+b+c:x0 = d:x0
"pxor %%xmm4, %%xmm3 \n\t" // stuff:a+b
"pxor %%xmm5, %%xmm3 \n\t" // stuff:a+b+c
"pslldq $8, %%xmm3 \n\t" // a+b+c:0
"pxor %%xmm3, %%xmm1 \n\t" // x1+a+b+c:x0 = d:x0
/* Steps 3 and 4 */
"movdqa %%xmm1,%%xmm0 \n\t" // d:x0
"movdqa %%xmm1,%%xmm4 \n\t" // same
"movdqa %%xmm1,%%xmm5 \n\t" // same
"psrlq $1, %%xmm0 \n\t" // e1:x0>>1 = e1:e0'
"psrlq $2, %%xmm4 \n\t" // f1:x0>>2 = f1:f0'
"psrlq $7, %%xmm5 \n\t" // g1:x0>>7 = g1:g0'
"pxor %%xmm4, %%xmm0 \n\t" // e1+f1:e0'+f0'
"pxor %%xmm5, %%xmm0 \n\t" // e1+f1+g1:e0'+f0'+g0'
"movdqa %%xmm1,%%xmm0 \n\t" // d:x0
"movdqa %%xmm1,%%xmm4 \n\t" // same
"movdqa %%xmm1,%%xmm5 \n\t" // same
"psrlq $1, %%xmm0 \n\t" // e1:x0>>1 = e1:e0'
"psrlq $2, %%xmm4 \n\t" // f1:x0>>2 = f1:f0'
"psrlq $7, %%xmm5 \n\t" // g1:x0>>7 = g1:g0'
"pxor %%xmm4, %%xmm0 \n\t" // e1+f1:e0'+f0'
"pxor %%xmm5, %%xmm0 \n\t" // e1+f1+g1:e0'+f0'+g0'
// e0'+f0'+g0' is almost e0+f0+g0, ex\tcept for some missing
// bits carried from d. Now get those\t bits back in.
"movdqa %%xmm1,%%xmm3 \n\t" // d:x0
"movdqa %%xmm1,%%xmm4 \n\t" // same
"movdqa %%xmm1,%%xmm5 \n\t" // same
"psllq $63, %%xmm3 \n\t" // d<<63:stuff
"psllq $62, %%xmm4 \n\t" // d<<62:stuff
"psllq $57, %%xmm5 \n\t" // d<<57:stuff
"pxor %%xmm4, %%xmm3 \n\t" // d<<63+d<<62:stuff
"pxor %%xmm5, %%xmm3 \n\t" // missing bits of d:stuff
"psrldq $8, %%xmm3 \n\t" // 0:missing bits of d
"pxor %%xmm3, %%xmm0 \n\t" // e1+f1+g1:e0+f0+g0
"pxor %%xmm1, %%xmm0 \n\t" // h1:h0
"pxor %%xmm2, %%xmm0 \n\t" // x3+h1:x2+h0
"movdqa %%xmm1,%%xmm3 \n\t" // d:x0
"movdqa %%xmm1,%%xmm4 \n\t" // same
"movdqa %%xmm1,%%xmm5 \n\t" // same
"psllq $63, %%xmm3 \n\t" // d<<63:stuff
"psllq $62, %%xmm4 \n\t" // d<<62:stuff
"psllq $57, %%xmm5 \n\t" // d<<57:stuff
"pxor %%xmm4, %%xmm3 \n\t" // d<<63+d<<62:stuff
"pxor %%xmm5, %%xmm3 \n\t" // missing bits of d:stuff
"psrldq $8, %%xmm3 \n\t" // 0:missing bits of d
"pxor %%xmm3, %%xmm0 \n\t" // e1+f1+g1:e0+f0+g0
"pxor %%xmm1, %%xmm0 \n\t" // h1:h0
"pxor %%xmm2, %%xmm0 \n\t" // x3+h1:x2+h0
"movdqu %%xmm0, (%2) \n\t" // done
"movdqu %%xmm0, (%2) \n\t" // done
:
: "r" (aa), "r" (bb), "r" (cc)
: "memory", "cc", "xmm0", "xmm1", "xmm2", "xmm3", "xmm4", "xmm5" );
: "memory", "cc", "xmm0", "xmm1", "xmm2", "xmm3", "xmm4", "xmm5");
/* Now byte-reverse the outputs */
for( i = 0; i < 16; i++ )
for (i = 0; i < 16; i++) {
c[i] = cc[15 - i];
}
return;
}
@ -251,32 +251,33 @@ void mbedtls_aesni_gcm_mult( unsigned char c[16],
/*
* Compute decryption round keys from encryption round keys
*/
void mbedtls_aesni_inverse_key( unsigned char *invkey,
const unsigned char *fwdkey, int nr )
void mbedtls_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 );
memcpy(ik, fk, 16);
for( fk -= 16, ik += 16; fk > fwdkey; fk -= 16, ik += 16 )
asm( "movdqu (%0), %%xmm0 \n\t"
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"
"movdqu %%xmm0, (%1) \n\t"
:
: "r" (fk), "r" (ik)
: "memory", "xmm0" );
: "memory", "xmm0");
}
memcpy( ik, fk, 16 );
memcpy(ik, fk, 16);
}
/*
* Key expansion, 128-bit case
*/
static void aesni_setkey_enc_128( unsigned char *rk,
const unsigned char *key )
static void aesni_setkey_enc_128(unsigned char *rk,
const unsigned char *key)
{
asm( "movdqu (%1), %%xmm0 \n\t" // copy the original 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
@ -317,16 +318,16 @@ static void aesni_setkey_enc_128( unsigned char *rk,
AESKEYGENA xmm0_xmm1 ",0x36 \n\tcall 1b \n\t"
:
: "r" (rk), "r" (key)
: "memory", "cc", "0" );
: "memory", "cc", "0");
}
/*
* Key expansion, 192-bit case
*/
static void aesni_setkey_enc_192( unsigned char *rk,
const unsigned char *key )
static void aesni_setkey_enc_192(unsigned char *rk,
const unsigned char *key)
{
asm( "movdqu (%1), %%xmm0 \n\t" // copy original round 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"
@ -374,16 +375,16 @@ static void aesni_setkey_enc_192( unsigned char *rk,
:
: "r" (rk), "r" (key)
: "memory", "cc", "0" );
: "memory", "cc", "0");
}
/*
* Key expansion, 256-bit case
*/
static void aesni_setkey_enc_256( unsigned char *rk,
const unsigned char *key )
static void aesni_setkey_enc_256(unsigned char *rk,
const unsigned char *key)
{
asm( "movdqu (%1), %%xmm0 \n\t"
asm ("movdqu (%1), %%xmm0 \n\t"
"movdqu %%xmm0, (%0) \n\t"
"add $16, %0 \n\t"
"movdqu 16(%1), %%xmm1 \n\t"
@ -414,23 +415,23 @@ static void aesni_setkey_enc_256( unsigned char *rk,
/* 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"
"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 mbedtls_aes_context.buf
*/
"2: \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"
@ -440,25 +441,24 @@ static void aesni_setkey_enc_256( unsigned char *rk,
AESKEYGENA xmm1_xmm2 ",0x40 \n\tcall 1b \n\t"
:
: "r" (rk), "r" (key)
: "memory", "cc", "0" );
: "memory", "cc", "0");
}
/*
* Key expansion, wrapper
*/
int mbedtls_aesni_setkey_enc( unsigned char *rk,
const unsigned char *key,
size_t bits )
int mbedtls_aesni_setkey_enc(unsigned char *rk,
const unsigned char *key,
size_t bits)
{
switch( bits )
{
case 128: aesni_setkey_enc_128( rk, key ); break;
case 192: aesni_setkey_enc_192( rk, key ); break;
case 256: aesni_setkey_enc_256( rk, key ); break;
default : return( MBEDTLS_ERR_AES_INVALID_KEY_LENGTH );
switch (bits) {
case 128: aesni_setkey_enc_128(rk, key); break;
case 192: aesni_setkey_enc_192(rk, key); break;
case 256: aesni_setkey_enc_256(rk, key); break;
default: return MBEDTLS_ERR_AES_INVALID_KEY_LENGTH;
}
return( 0 );
return 0;
}
#endif /* MBEDTLS_HAVE_X86_64 */