diff --git a/library/aesni.c b/library/aesni.c
index 9ade1bf..2756194 100644
--- a/library/aesni.c
+++ b/library/aesni.c
@@ -75,13 +75,13 @@
  * 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 AESDEC(regs)      ".byte 0x66,0x0F,0x38,0xDE," regs "\n\t"
+#define AESDECLAST(regs)  ".byte 0x66,0x0F,0x38,0xDF," regs "\n\t"
+#define AESENC(regs)      ".byte 0x66,0x0F,0x38,0xDC," regs "\n\t"
+#define AESENCLAST(regs)  ".byte 0x66,0x0F,0x38,0xDD," regs "\n\t"
+#define AESIMC(regs)      ".byte 0x66,0x0F,0x38,0xDB," regs "\n\t"
+#define AESKEYGENA(regs, imm)  ".byte 0x66,0x0F,0x3A,0xDF," regs "," imm "\n\t"
+#define PCLMULQDQ(regs, imm)   ".byte 0x66,0x0F,0x3A,0x44," regs "," imm "\n\t"
 
 #define xmm0_xmm0   "0xC0"
 #define xmm0_xmm1   "0xC8"
@@ -109,25 +109,25 @@
 
          "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
-         AESENCLAST xmm1_xmm0      "\n\t" // last round
-                                   "jmp       3f              \n\t"
+         AESENC(xmm1_xmm0)                // 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
+         AESENCLAST(xmm1_xmm0)            // last round
+         "jmp       3f              \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
-         AESDECLAST xmm1_xmm0      "\n\t" // last round
+         "2:                        \n\t" // decryption loop
+         "movdqu    (%1), %%xmm1    \n\t"
+         AESDEC(xmm1_xmm0)                // do round
+         "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)            // 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");
@@ -163,34 +163,34 @@
          "movdqa %%xmm1, %%xmm2             \n\t" // copy of b1:b0
          "movdqa %%xmm1, %%xmm3             \n\t" // same
          "movdqa %%xmm1, %%xmm4             \n\t" // same
-         PCLMULQDQ xmm0_xmm1 ",0x00         \n\t" // a0*b0 = c1:c0
-         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
+         PCLMULQDQ(xmm0_xmm1, "0x00")             // a0*b0 = c1:c0
+         PCLMULQDQ(xmm0_xmm2, "0x11")             // a1*b1 = d1:d0
+         PCLMULQDQ(xmm0_xmm3, "0x10")             // a0*b1 = e1:e0
+         PCLMULQDQ(xmm0_xmm4, "0x01")             // 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
 
          /*
           * Now shift the result one bit to the left,
           * taking advantage of [CLMUL-WP] eq 27 (p. 18)
           */
-                             "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
@@ -198,44 +198,44 @@
           * 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");
@@ -261,8 +261,8 @@
 
     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"
+             AESIMC(xmm0_xmm0)
+             "movdqu %%xmm0, (%1)       \n\t"
              :
              : "r" (fk), "r" (ik)
              : "memory", "xmm0");
@@ -306,16 +306,16 @@
 
          /* 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"
+         AESKEYGENA(xmm0_xmm1, "0x01")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x02")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x04")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x08")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x10")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x20")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x40")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x80")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x1B")      "call 1b \n\t"
+         AESKEYGENA(xmm0_xmm1, "0x36")      "call 1b \n\t"
          :
          : "r" (rk), "r" (key)
          : "memory", "cc", "0");
@@ -364,14 +364,14 @@
          "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"
+         AESKEYGENA(xmm1_xmm2, "0x01")  "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x02")  "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x04")  "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x08")  "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x10")  "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x20")  "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x40")  "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x80")  "call 1b \n\t"
 
          :
          : "r" (rk), "r" (key)
@@ -414,31 +414,31 @@
 
          /* 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"
+         AESKEYGENA(xmm0_xmm2, "0x00")
+         "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"
-         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"
+         "2:                                \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x01")      "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x02")      "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x04")      "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x08")      "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x10")      "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x20")      "call 1b \n\t"
+         AESKEYGENA(xmm1_xmm2, "0x40")      "call 1b \n\t"
          :
          : "r" (rk), "r" (key)
          : "memory", "cc", "0");