Get aesni.c compiling with Visual Studio
Clang is nice enough to support bitwise operators on __m128i, but MSVC
isn't.
Also, __cpuid() in MSVC comes from <intrin.h> (which is included via
<emmintrin.h>), not <cpuid.h>.
Signed-off-by: Tom Cosgrove <tom.cosgrove@arm.com>
diff --git a/library/aesni.c b/library/aesni.c
index 3acc329..30b4b17 100644
--- a/library/aesni.c
+++ b/library/aesni.c
@@ -33,7 +33,9 @@
#if defined(MBEDTLS_HAVE_AESNI_INTRINSICS) || defined(MBEDTLS_HAVE_X86_64)
#if defined(MBEDTLS_HAVE_AESNI_INTRINSICS)
+#if !defined(_WIN32)
#include <cpuid.h>
+#endif
#include <immintrin.h>
#endif
@@ -79,10 +81,11 @@
{
const __m128i *rk = (const __m128i *) (ctx->buf + ctx->rk_offset);
unsigned nr = ctx->nr; // Number of remaining rounds
+
// Load round key 0
__m128i xmm0;
memcpy(&xmm0, input, 16);
- xmm0 ^= *rk;
+ xmm0 = _mm_xor_si128(xmm0, rk[0]); // xmm0 ^= *rk;
++rk;
--nr;
@@ -122,12 +125,12 @@
*dd = _mm_clmulepi64_si128(aa, bb, 0x11); // a1*b1 = d1:d0
__m128i ee = _mm_clmulepi64_si128(aa, bb, 0x10); // a0*b1 = e1:e0
__m128i ff = _mm_clmulepi64_si128(aa, bb, 0x01); // a1*b0 = f1:f0
- ff ^= ee; // e1+f1:e0+f0
+ ff = _mm_xor_si128(ff, ee); // e1+f1:e0+f0
ee = ff; // e1+f1:e0+f0
ff = _mm_srli_si128(ff, 8); // 0:e1+f1
ee = _mm_slli_si128(ee, 8); // e0+f0:0
- *dd ^= ff; // d1:d0+e1+f1
- *cc ^= ee; // c1+e0+f1:c0
+ *dd = _mm_xor_si128(*dd, ff); // d1:d0+e1+f1
+ *cc = _mm_xor_si128(*cc, ee); // c1+e0+f1:c0
}
static void gcm_shift(__m128i *cc, __m128i *dd)
@@ -146,8 +149,8 @@
xmm3 = _mm_slli_si128(xmm3, 8); // r0>>63:0
xmm4 = _mm_slli_si128(xmm4, 8); // 0:r1>>63
- *cc = xmm1 | xmm3; // r1<<1|r0>>63:r0<<1
- *dd = xmm2 | xmm4 | xmm5; // r3<<1|r2>>62:r2<<1|r1>>63
+ *cc = _mm_or_si128(xmm1, xmm3); // r1<<1|r0>>63:r0<<1
+ *dd = _mm_or_si128(_mm_or_si128(xmm2, xmm4), xmm5); // r3<<1|r2>>62:r2<<1|r1>>63
}
static __m128i gcm_reduce1(__m128i xx)
@@ -157,8 +160,8 @@
__m128i aa = _mm_slli_epi64(xx, 63); // x1<<63:x0<<63 = stuff:a
__m128i bb = _mm_slli_epi64(xx, 62); // x1<<62:x0<<62 = stuff:b
__m128i cc = _mm_slli_epi64(xx, 57); // x1<<57:x0<<57 = stuff:c
- __m128i dd = _mm_slli_si128(aa ^ bb ^ cc, 8); // a+b+c:0
- return dd ^ xx; // x1+a+b+c:x0 = d:x0
+ __m128i dd = _mm_slli_si128(_mm_xor_si128(_mm_xor_si128(aa, bb), cc), 8); // a+b+c:0
+ return _mm_xor_si128(dd, xx); // x1+a+b+c:x0 = d:x0
}
static __m128i gcm_reduce2(__m128i dx)
@@ -173,9 +176,9 @@
__m128i eh = _mm_slli_epi64(dx, 63); // d<<63:stuff
__m128i fh = _mm_slli_epi64(dx, 62); // d<<62:stuff
__m128i gh = _mm_slli_epi64(dx, 57); // d<<57:stuff
- __m128i hh = _mm_srli_si128(eh ^ fh ^ gh, 8); // 0:missing bits of d
+ __m128i hh = _mm_srli_si128(_mm_xor_si128(_mm_xor_si128(eh, fh), gh), 8); // 0:missing bits of d
- return ee ^ ff ^ gg ^ hh ^ dx;
+ return _mm_xor_si128(_mm_xor_si128(_mm_xor_si128(_mm_xor_si128(ee, ff), gg), hh), dx);
}
void mbedtls_aesni_gcm_mult(unsigned char c[16],
@@ -199,7 +202,7 @@
*/
__m128i dx = gcm_reduce1(cc);
__m128i xh = gcm_reduce2(dx);
- cc = xh ^ dd; // x3+h1:x2+h0
+ cc = _mm_xor_si128(xh, dd); // x3+h1:x2+h0
/* Now byte-reverse the outputs */
for (size_t i = 0; i < 16; i++) {
@@ -241,13 +244,13 @@
* and this is returned, to be written to the round key buffer.
*/
xmm1 = _mm_shuffle_epi32(xmm1, 0xff); // X:X:X:X
- xmm1 ^= xmm0; // X+r3:X+r2:X+r1:r4
+ xmm1 = _mm_xor_si128(xmm1, xmm0); // X+r3:X+r2:X+r1:r4
xmm0 = _mm_slli_si128(xmm0, 4); // r2:r1:r0:0
- xmm1 ^= xmm0; // X+r3+r2:X+r2+r1:r5:r4
+ xmm1 = _mm_xor_si128(xmm1, xmm0); // X+r3+r2:X+r2+r1:r5:r4
xmm0 = _mm_slli_si128(xmm0, 4); // r1:r0:0:0
- xmm1 ^= xmm0; // X+r3+r2+r1:r6:r5:r4
+ xmm1 = _mm_xor_si128(xmm1, xmm0); // X+r3+r2+r1:r6:r5:r4
xmm0 = _mm_slli_si128(xmm0, 4); // r0:0:0:0
- xmm1 ^= xmm0; // r7:r6:r5:r4
+ xmm1 = _mm_xor_si128(xmm1, xmm0); // r7:r6:r5:r4
return xmm1;
}
@@ -341,26 +344,26 @@
* On exit, *rk0 is r11:r10:r9:r8 and *rk1 is r15:r14:r13:r12
*/
xmm2 = _mm_shuffle_epi32(xmm2, 0xff);
- xmm2 ^= xmm0;
+ xmm2 = _mm_xor_si128(xmm2, xmm0);
xmm0 = _mm_slli_si128(xmm0, 4);
- xmm2 ^= xmm0;
+ xmm2 = _mm_xor_si128(xmm2, xmm0);
xmm0 = _mm_slli_si128(xmm0, 4);
- xmm2 ^= xmm0;
+ xmm2 = _mm_xor_si128(xmm2, xmm0);
xmm0 = _mm_slli_si128(xmm0, 4);
- xmm0 ^= xmm2;
+ xmm0 = _mm_xor_si128(xmm0, xmm2);
*rk0 = xmm0;
/* Set xmm2 to stuff:Y:stuff:stuff with Y = subword( r11 )
* and proceed to generate next round key from there */
xmm2 = _mm_aeskeygenassist_si128(xmm0, 0x00);
xmm2 = _mm_shuffle_epi32(xmm2, 0xaa);
- xmm2 ^= xmm1;
+ xmm2 = _mm_xor_si128(xmm2, xmm1);
xmm1 = _mm_slli_si128(xmm1, 4);
- xmm2 ^= xmm1;
+ xmm2 = _mm_xor_si128(xmm2, xmm1);
xmm1 = _mm_slli_si128(xmm1, 4);
- xmm2 ^= xmm1;
+ xmm2 = _mm_xor_si128(xmm2, xmm1);
xmm1 = _mm_slli_si128(xmm1, 4);
- xmm1 ^= xmm2;
+ xmm1 = _mm_xor_si128(xmm1, xmm2);
*rk1 = xmm1;
}