scalar-crypto: Initial spike support for v0.8.1 (#635)

Brief:

- This commit adds spike support for the scalar cryptography extension.
  See the riscv-crypto repository (https://github.com/riscv/riscv-crypto)
  for more information on this extension.

- It is based on the experimental patch which has so far been kept in the
  riscv-crypto repository. Now that scalar crypto is nearly at the "freeze"
  stage and entering opcode consistency review, it makes sense to start
  upstreaming our experimental version.

- In terms of compiler support - we are using an experimental patch in
  the riscv-crypto repository at the moment, others are working on an
  upstream appropriate version.

Details:

- Add support for dedicated scalar crypto instructions.

- Add very basic support for the entropy source (entropy_source.h).
  Much of the behaviour of this is implementation specific. This model
  aims to provide the bare minimum of functionality which can be used to
  quickly develop software. It uses /dev/urandom as its entropy source for
  now.

- Scalar crypto is unique in that it _borrows_ instructions from the
  Bitmanipulation extension. This is currently _not_ encoded in the patch,
  as I didn't want to damage anything in Bitmanip which is currently under
  review. However, I've added a macro in riscv/decode.h called
  "require_either_extension(A,B)", which allows instructions to be valid
  opcodes iff they are in one or both extensions.

 On branch scalar-crypto
 Changes to be committed:
	modified:   README.md
	modified:   riscv/decode.h
	modified:   riscv/encoding.h
	new file:   riscv/entropy_source.h
	new file:   riscv/insns/aes64im.h
	new file:   riscv/insns/aes64ks1i.h
	new file:   riscv/insns/aes64ks2.h
	new file:   riscv/insns/aes_common.h
	new file:   riscv/insns/aesds.h
	new file:   riscv/insns/aesdsm.h
	new file:   riscv/insns/aeses.h
	new file:   riscv/insns/aesesm.h
	new file:   riscv/insns/sha256sig0.h
	new file:   riscv/insns/sha256sig1.h
	new file:   riscv/insns/sha256sum0.h
	new file:   riscv/insns/sha256sum1.h
	new file:   riscv/insns/sha512sig0.h
	new file:   riscv/insns/sha512sig0h.h
	new file:   riscv/insns/sha512sig0l.h
	new file:   riscv/insns/sha512sig1.h
	new file:   riscv/insns/sha512sig1h.h
	new file:   riscv/insns/sha512sig1l.h
	new file:   riscv/insns/sha512sum0.h
	new file:   riscv/insns/sha512sum0r.h
	new file:   riscv/insns/sha512sum1.h
	new file:   riscv/insns/sha512sum1r.h
	new file:   riscv/insns/sm3p0.h
	new file:   riscv/insns/sm3p1.h
	new file:   riscv/insns/sm4_common.h
	new file:   riscv/insns/sm4ed.h
	new file:   riscv/insns/sm4ks.h
	modified:   riscv/processor.cc
	modified:   riscv/processor.h
	modified:   riscv/riscv.mk.in

1 files changed, 156 insertions, 0 deletions

diff --git a/riscv/insns/aes_common.h b/riscv/insns/aes_common.h
new file mode 100644
index 0000000..9cc353c
--- /dev/null
+++ b/riscv/insns/aes_common.h
@@ -0,0 +1,156 @@
+
+uint8_t AES_ENC_SBOX[]= {
+  0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5,
+  0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
+  0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0,
+  0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
+  0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC,
+  0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
+  0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A,
+  0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
+  0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0,
+  0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
+  0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B,
+  0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
+  0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85,
+  0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
+  0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5,
+  0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
+  0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17,
+  0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
+  0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88,
+  0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
+  0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C,
+  0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
+  0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9,
+  0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
+  0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6,
+  0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
+  0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E,
+  0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
+  0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94,
+  0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
+  0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68,
+  0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16
+};
+
+uint8_t AES_DEC_SBOX[] = {
+  0x52, 0x09, 0x6A, 0xD5, 0x30, 0x36, 0xA5, 0x38,
+  0xBF, 0x40, 0xA3, 0x9E, 0x81, 0xF3, 0xD7, 0xFB,
+  0x7C, 0xE3, 0x39, 0x82, 0x9B, 0x2F, 0xFF, 0x87,
+  0x34, 0x8E, 0x43, 0x44, 0xC4, 0xDE, 0xE9, 0xCB,
+  0x54, 0x7B, 0x94, 0x32, 0xA6, 0xC2, 0x23, 0x3D,
+  0xEE, 0x4C, 0x95, 0x0B, 0x42, 0xFA, 0xC3, 0x4E,
+  0x08, 0x2E, 0xA1, 0x66, 0x28, 0xD9, 0x24, 0xB2,
+  0x76, 0x5B, 0xA2, 0x49, 0x6D, 0x8B, 0xD1, 0x25,
+  0x72, 0xF8, 0xF6, 0x64, 0x86, 0x68, 0x98, 0x16,
+  0xD4, 0xA4, 0x5C, 0xCC, 0x5D, 0x65, 0xB6, 0x92,
+  0x6C, 0x70, 0x48, 0x50, 0xFD, 0xED, 0xB9, 0xDA,
+  0x5E, 0x15, 0x46, 0x57, 0xA7, 0x8D, 0x9D, 0x84,
+  0x90, 0xD8, 0xAB, 0x00, 0x8C, 0xBC, 0xD3, 0x0A,
+  0xF7, 0xE4, 0x58, 0x05, 0xB8, 0xB3, 0x45, 0x06,
+  0xD0, 0x2C, 0x1E, 0x8F, 0xCA, 0x3F, 0x0F, 0x02,
+  0xC1, 0xAF, 0xBD, 0x03, 0x01, 0x13, 0x8A, 0x6B,
+  0x3A, 0x91, 0x11, 0x41, 0x4F, 0x67, 0xDC, 0xEA,
+  0x97, 0xF2, 0xCF, 0xCE, 0xF0, 0xB4, 0xE6, 0x73,
+  0x96, 0xAC, 0x74, 0x22, 0xE7, 0xAD, 0x35, 0x85,
+  0xE2, 0xF9, 0x37, 0xE8, 0x1C, 0x75, 0xDF, 0x6E,
+  0x47, 0xF1, 0x1A, 0x71, 0x1D, 0x29, 0xC5, 0x89,
+  0x6F, 0xB7, 0x62, 0x0E, 0xAA, 0x18, 0xBE, 0x1B,
+  0xFC, 0x56, 0x3E, 0x4B, 0xC6, 0xD2, 0x79, 0x20,
+  0x9A, 0xDB, 0xC0, 0xFE, 0x78, 0xCD, 0x5A, 0xF4,
+  0x1F, 0xDD, 0xA8, 0x33, 0x88, 0x07, 0xC7, 0x31,
+  0xB1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xEC, 0x5F,
+  0x60, 0x51, 0x7F, 0xA9, 0x19, 0xB5, 0x4A, 0x0D,
+  0x2D, 0xE5, 0x7A, 0x9F, 0x93, 0xC9, 0x9C, 0xEF,
+  0xA0, 0xE0, 0x3B, 0x4D, 0xAE, 0x2A, 0xF5, 0xB0,
+  0xC8, 0xEB, 0xBB, 0x3C, 0x83, 0x53, 0x99, 0x61,
+  0x17, 0x2B, 0x04, 0x7E, 0xBA, 0x77, 0xD6, 0x26,
+  0xE1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0C, 0x7D
+};
+
+#define AES_UNPACK_BYTES(b0,b1,b2,b3) \
+    uint8_t  b0 = (RS1 >>  0) & 0xFF; \
+    uint8_t  b1 = (RS2 >>  8) & 0xFF; \
+    uint8_t  b2 = (RS1 >> 16) & 0xFF; \
+    uint8_t  b3 = (RS2 >> 24) & 0xFF; \
+
+#define AES_PACK_BYTES(b0,b1,b2,b3) ( \
+    (uint32_t)b0 <<  0  | \
+    (uint32_t)b1 <<  8  | \
+    (uint32_t)b2 << 16  | \
+    (uint32_t)b3 << 24  )
+
+#define AES_SBOX(b0, b1, b2, b3) \
+    b0 = AES_ENC_SBOX[b0]; \
+    b1 = AES_ENC_SBOX[b1]; \
+    b2 = AES_ENC_SBOX[b2]; \
+    b3 = AES_ENC_SBOX[b3]; \
+
+#define AES_RSBOX(b0, b1, b2, b3) \
+    b0 = AES_DEC_SBOX[b0]; \
+    b1 = AES_DEC_SBOX[b1]; \
+    b2 = AES_DEC_SBOX[b2]; \
+    b3 = AES_DEC_SBOX[b3]; \
+
+#define AES_XTIME(a) \
+    ((a << 1) ^ ((a&0x80) ? 0x1b : 0))
+
+#define AES_GFMUL(a,b) (( \
+    ( ( (b) & 0x1 ) ?                              (a)   : 0 ) ^ \
+    ( ( (b) & 0x2 ) ?                     AES_XTIME(a)   : 0 ) ^ \
+    ( ( (b) & 0x4 ) ?           AES_XTIME(AES_XTIME(a))  : 0 ) ^ \
+    ( ( (b) & 0x8 ) ? AES_XTIME(AES_XTIME(AES_XTIME(a))) : 0 ) )&0xFF)
+
+#define BY(X,I) ((X >> (8*I)) & 0xFF)
+
+#define AES_SHIFROWS_LO(RS1,RS2) ( \
+    (((RS1 >> 24) & 0xFF) << 56) | \
+    (((RS2 >> 48) & 0xFF) << 48) | \
+    (((RS2 >>  8) & 0xFF) << 40) | \
+    (((RS1 >> 32) & 0xFF) << 32) | \
+    (((RS2 >> 56) & 0xFF) << 24) | \
+    (((RS2 >> 16) & 0xFF) << 16) | \
+    (((RS1 >> 40) & 0xFF) <<  8) | \
+    (((RS1 >>  0) & 0xFF) <<  0) ) 
+
+#define AES_INVSHIFROWS_LO(RS1,RS2) ( \
+    (((RS2 >> 24) & 0xFF) << 56) | \
+    (((RS2 >> 48) & 0xFF) << 48) | \
+    (((RS1 >>  8) & 0xFF) << 40) | \
+    (((RS1 >> 32) & 0xFF) << 32) | \
+    (((RS1 >> 56) & 0xFF) << 24) | \
+    (((RS2 >> 16) & 0xFF) << 16) | \
+    (((RS2 >> 40) & 0xFF) <<  8) | \
+    (((RS1 >>  0) & 0xFF) <<  0) ) 
+
+
+#define AES_MIXBYTE(COL,B0,B1,B2,B3) ( \
+              BY(COL,B3)     ^ \
+              BY(COL,B2)     ^ \
+    AES_GFMUL(BY(COL,B1), 3) ^ \
+    AES_GFMUL(BY(COL,B0), 2)   \
+)
+
+#define AES_MIXCOLUMN(COL) ( \
+    AES_MIXBYTE(COL,3,0,1,2) << 24 | \
+    AES_MIXBYTE(COL,2,3,0,1) << 16 | \
+    AES_MIXBYTE(COL,1,2,3,0) <<  8 | \
+    AES_MIXBYTE(COL,0,1,2,3) <<  0   \
+)
+
+
+#define AES_INVMIXBYTE(COL,B0,B1,B2,B3) ( \
+    AES_GFMUL(BY(COL,B3),0x9) ^ \
+    AES_GFMUL(BY(COL,B2),0xd) ^ \
+    AES_GFMUL(BY(COL,B1),0xb) ^ \
+    AES_GFMUL(BY(COL,B0),0xe)   \
+)
+
+#define AES_INVMIXCOLUMN(COL) ( \
+    AES_INVMIXBYTE(COL,3,0,1,2) << 24 | \
+    AES_INVMIXBYTE(COL,2,3,0,1) << 16 | \
+    AES_INVMIXBYTE(COL,1,2,3,0) <<  8 | \
+    AES_INVMIXBYTE(COL,0,1,2,3) <<  0   \
+)
+