Add SHA256

common/sha2.c

@@ -7,14 +7,29 @@
 
 #include "sha2.h"
 
-static uint64_t load_bigendian(const unsigned char *x) {
-    return (uint64_t)(x[7]) | (((uint64_t)(x[6])) << 8) | (((uint64_t)(x[5])) << 16) |
-           (((uint64_t)(x[4])) << 24) | (((uint64_t)(x[3])) << 32) |
-           (((uint64_t)(x[2])) << 40) | (((uint64_t)(x[1])) << 48) |
-           (((uint64_t)(x[0])) << 56);
+static uint32_t load_bigendian_32(const uint8_t *x) {
+    return (uint32_t)(x[3]) | (((uint32_t)(x[2])) << 8) |
+           (((uint32_t)(x[1])) << 16) | (((uint32_t)(x[0])) << 24);
 }
 
-static void store_bigendian(uint8_t *x, uint64_t u) {
+static uint64_t load_bigendian_64(const uint8_t *x) {
+    return (uint64_t)(x[7]) | (((uint64_t)(x[6])) << 8) |
+           (((uint64_t)(x[5])) << 16) | (((uint64_t)(x[4])) << 24) |
+           (((uint64_t)(x[3])) << 32) | (((uint64_t)(x[2])) << 40) |
+           (((uint64_t)(x[1])) << 48) | (((uint64_t)(x[0])) << 56);
+}
+
+static void store_bigendian_32(uint8_t *x, uint64_t u) {
+    x[3] = (uint8_t) u;
+    u >>= 8;
+    x[2] = (uint8_t) u;
+    u >>= 8;
+    x[1] = (uint8_t) u;
+    u >>= 8;
+    x[0] = (uint8_t) u;
+}
+
+static void store_bigendian_64(uint8_t *x, uint64_t u) {
     x[7] = (uint8_t) u;
     u >>= 8;
     x[6] = (uint8_t) u;
@@ -33,50 +48,244 @@ static void store_bigendian(uint8_t *x, uint64_t u) {
 }
 
 #define SHR(x, c) ((x) >> (c))
-#define ROTR(x, c) (((x) >> (c)) | ((x) << (64 - (c))))
+#define ROTR_32(x, c) (((x) >> (c)) | ((x) << (32 - (c))))
+#define ROTR_64(x, c) (((x) >> (c)) | ((x) << (64 - (c))))
 
 #define Ch(x, y, z) (((x) & (y)) ^ (~(x) & (z)))
 #define Maj(x, y, z) (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z)))
-#define Sigma0(x) (ROTR(x, 28) ^ ROTR(x, 34) ^ ROTR(x, 39))
-#define Sigma1(x) (ROTR(x, 14) ^ ROTR(x, 18) ^ ROTR(x, 41))
-#define sigma0(x) (ROTR(x, 1) ^ ROTR(x, 8) ^ SHR(x, 7))
-#define sigma1(x) (ROTR(x, 19) ^ ROTR(x, 61) ^ SHR(x, 6))
-
-#define M(w0, w14, w9, w1) w0 = sigma1(w14) + (w9) + sigma0(w1) + (w0);
-
-#define EXPAND           \
-    M(w0, w14, w9, w1)   \
-    M(w1, w15, w10, w2)  \
-    M(w2, w0, w11, w3)   \
-    M(w3, w1, w12, w4)   \
-    M(w4, w2, w13, w5)   \
-    M(w5, w3, w14, w6)   \
-    M(w6, w4, w15, w7)   \
-    M(w7, w5, w0, w8)    \
-    M(w8, w6, w1, w9)    \
-    M(w9, w7, w2, w10)   \
-    M(w10, w8, w3, w11)  \
-    M(w11, w9, w4, w12)  \
-    M(w12, w10, w5, w13) \
-    M(w13, w11, w6, w14) \
-    M(w14, w12, w7, w15) \
-    M(w15, w13, w8, w0)
-
-#define F(w, k)                                   \
-    T1 = h + Sigma1(e) + Ch(e, f, g) + (k) + (w); \
-    T2 = Sigma0(a) + Maj(a, b, c);                \
-    h = g;                                        \
-    g = f;                                        \
-    f = e;                                        \
-    e = d + T1;                                   \
-    d = c;                                        \
-    c = b;                                        \
-    b = a;                                        \
+
+#define Sigma0_32(x) (ROTR_32(x, 2) ^ ROTR_32(x,13) ^ ROTR_32(x,22))
+#define Sigma1_32(x) (ROTR_32(x, 6) ^ ROTR_32(x,11) ^ ROTR_32(x,25))
+#define sigma0_32(x) (ROTR_32(x, 7) ^ ROTR_32(x,18) ^ SHR(x, 3))
+#define sigma1_32(x) (ROTR_32(x,17) ^ ROTR_32(x,19) ^ SHR(x,10))
+
+#define Sigma0_64(x) (ROTR_64(x, 28) ^ ROTR_64(x, 34) ^ ROTR_64(x, 39))
+#define Sigma1_64(x) (ROTR_64(x, 14) ^ ROTR_64(x, 18) ^ ROTR_64(x, 41))
+#define sigma0_64(x) (ROTR_64(x, 1) ^ ROTR_64(x, 8) ^ SHR(x, 7))
+#define sigma1_64(x) (ROTR_64(x, 19) ^ ROTR_64(x, 61) ^ SHR(x, 6))
+
+#define M_32(w0, w14, w9, w1) w0 = sigma1_32(w14) + (w9) + sigma0_32(w1) + (w0);
+#define M_64(w0, w14, w9, w1) w0 = sigma1_64(w14) + (w9) + sigma0_64(w1) + (w0);
+
+#define EXPAND_32           \
+    M_32(w0, w14, w9, w1)   \
+    M_32(w1, w15, w10, w2)  \
+    M_32(w2, w0, w11, w3)   \
+    M_32(w3, w1, w12, w4)   \
+    M_32(w4, w2, w13, w5)   \
+    M_32(w5, w3, w14, w6)   \
+    M_32(w6, w4, w15, w7)   \
+    M_32(w7, w5, w0, w8)    \
+    M_32(w8, w6, w1, w9)    \
+    M_32(w9, w7, w2, w10)   \
+    M_32(w10, w8, w3, w11)  \
+    M_32(w11, w9, w4, w12)  \
+    M_32(w12, w10, w5, w13) \
+    M_32(w13, w11, w6, w14) \
+    M_32(w14, w12, w7, w15) \
+    M_32(w15, w13, w8, w0)
+
+#define EXPAND_64           \
+    M_64(w0, w14, w9, w1)   \
+    M_64(w1, w15, w10, w2)  \
+    M_64(w2, w0, w11, w3)   \
+    M_64(w3, w1, w12, w4)   \
+    M_64(w4, w2, w13, w5)   \
+    M_64(w5, w3, w14, w6)   \
+    M_64(w6, w4, w15, w7)   \
+    M_64(w7, w5, w0, w8)    \
+    M_64(w8, w6, w1, w9)    \
+    M_64(w9, w7, w2, w10)   \
+    M_64(w10, w8, w3, w11)  \
+    M_64(w11, w9, w4, w12)  \
+    M_64(w12, w10, w5, w13) \
+    M_64(w13, w11, w6, w14) \
+    M_64(w14, w12, w7, w15) \
+    M_64(w15, w13, w8, w0)
+
+#define F_32(w, k)                                   \
+    T1 = h + Sigma1_32(e) + Ch(e, f, g) + (k) + (w); \
+    T2 = Sigma0_32(a) + Maj(a, b, c);                \
+    h = g;                                           \
+    g = f;                                           \
+    f = e;                                           \
+    e = d + T1;                                      \
+    d = c;                                           \
+    c = b;                                           \
+    b = a;                                           \
+    a = T1 + T2;
+
+#define F_64(w, k)                                   \
+    T1 = h + Sigma1_64(e) + Ch(e, f, g) + (k) + (w); \
+    T2 = Sigma0_64(a) + Maj(a, b, c);                \
+    h = g;                                           \
+    g = f;                                           \
+    f = e;                                           \
+    e = d + T1;                                      \
+    d = c;                                           \
+    c = b;                                           \
+    b = a;                                           \
     a = T1 + T2;
 
+static size_t crypto_hashblocks_sha256(uint8_t *statebytes,
+                                       const uint8_t *in, size_t inlen) {
+    uint32_t state[8];
+    uint32_t a;
+    uint32_t b;
+    uint32_t c;
+    uint32_t d;
+    uint32_t e;
+    uint32_t f;
+    uint32_t g;
+    uint32_t h;
+    uint32_t T1;
+    uint32_t T2;
+
+    a = load_bigendian_32(statebytes + 0);
+    state[0] = a;
+    b = load_bigendian_32(statebytes + 4);
+    state[1] = b;
+    c = load_bigendian_32(statebytes + 8);
+    state[2] = c;
+    d = load_bigendian_32(statebytes + 12);
+    state[3] = d;
+    e = load_bigendian_32(statebytes + 16);
+    state[4] = e;
+    f = load_bigendian_32(statebytes + 20);
+    state[5] = f;
+    g = load_bigendian_32(statebytes + 24);
+    state[6] = g;
+    h = load_bigendian_32(statebytes + 28);
+    state[7] = h;
+
+    while (inlen >= 64) {
+        uint32_t w0  = load_bigendian_32(in + 0);
+        uint32_t w1  = load_bigendian_32(in + 4);
+        uint32_t w2  = load_bigendian_32(in + 8);
+        uint32_t w3  = load_bigendian_32(in + 12);
+        uint32_t w4  = load_bigendian_32(in + 16);
+        uint32_t w5  = load_bigendian_32(in + 20);
+        uint32_t w6  = load_bigendian_32(in + 24);
+        uint32_t w7  = load_bigendian_32(in + 28);
+        uint32_t w8  = load_bigendian_32(in + 32);
+        uint32_t w9  = load_bigendian_32(in + 36);
+        uint32_t w10 = load_bigendian_32(in + 40);
+        uint32_t w11 = load_bigendian_32(in + 44);
+        uint32_t w12 = load_bigendian_32(in + 48);
+        uint32_t w13 = load_bigendian_32(in + 52);
+        uint32_t w14 = load_bigendian_32(in + 56);
+        uint32_t w15 = load_bigendian_32(in + 60);
+
+        F_32(w0, 0x428a2f98)
+        F_32(w1, 0x71374491)
+        F_32(w2, 0xb5c0fbcf)
+        F_32(w3, 0xe9b5dba5)
+        F_32(w4, 0x3956c25b)
+        F_32(w5, 0x59f111f1)
+        F_32(w6, 0x923f82a4)
+        F_32(w7, 0xab1c5ed5)
+        F_32(w8, 0xd807aa98)
+        F_32(w9, 0x12835b01)
+        F_32(w10, 0x243185be)
+        F_32(w11, 0x550c7dc3)
+        F_32(w12, 0x72be5d74)
+        F_32(w13, 0x80deb1fe)
+        F_32(w14, 0x9bdc06a7)
+        F_32(w15, 0xc19bf174)
+
+        EXPAND_32
+
+        F_32(w0, 0xe49b69c1)
+        F_32(w1, 0xefbe4786)
+        F_32(w2, 0x0fc19dc6)
+        F_32(w3, 0x240ca1cc)
+        F_32(w4, 0x2de92c6f)
+        F_32(w5, 0x4a7484aa)
+        F_32(w6, 0x5cb0a9dc)
+        F_32(w7, 0x76f988da)
+        F_32(w8, 0x983e5152)
+        F_32(w9, 0xa831c66d)
+        F_32(w10, 0xb00327c8)
+        F_32(w11, 0xbf597fc7)
+        F_32(w12, 0xc6e00bf3)
+        F_32(w13, 0xd5a79147)
+        F_32(w14, 0x06ca6351)
+        F_32(w15, 0x14292967)
+
+        EXPAND_32
+
+        F_32(w0, 0x27b70a85)
+        F_32(w1, 0x2e1b2138)
+        F_32(w2, 0x4d2c6dfc)
+        F_32(w3, 0x53380d13)
+        F_32(w4, 0x650a7354)
+        F_32(w5, 0x766a0abb)
+        F_32(w6, 0x81c2c92e)
+        F_32(w7, 0x92722c85)
+        F_32(w8, 0xa2bfe8a1)
+        F_32(w9, 0xa81a664b)
+        F_32(w10, 0xc24b8b70)
+        F_32(w11, 0xc76c51a3)
+        F_32(w12, 0xd192e819)
+        F_32(w13, 0xd6990624)
+        F_32(w14, 0xf40e3585)
+        F_32(w15, 0x106aa070)
+
+        EXPAND_32
+
+        F_32(w0, 0x19a4c116)
+        F_32(w1, 0x1e376c08)
+        F_32(w2, 0x2748774c)
+        F_32(w3, 0x34b0bcb5)
+        F_32(w4, 0x391c0cb3)
+        F_32(w5, 0x4ed8aa4a)
+        F_32(w6, 0x5b9cca4f)
+        F_32(w7, 0x682e6ff3)
+        F_32(w8, 0x748f82ee)
+        F_32(w9, 0x78a5636f)
+        F_32(w10, 0x84c87814)
+        F_32(w11, 0x8cc70208)
+        F_32(w12, 0x90befffa)
+        F_32(w13, 0xa4506ceb)
+        F_32(w14, 0xbef9a3f7)
+        F_32(w15, 0xc67178f2)
+
+        a += state[0];
+        b += state[1];
+        c += state[2];
+        d += state[3];
+        e += state[4];
+        f += state[5];
+        g += state[6];
+        h += state[7];
+
+        state[0] = a;
+        state[1] = b;
+        state[2] = c;
+        state[3] = d;
+        state[4] = e;
+        state[5] = f;
+        state[6] = g;
+        state[7] = h;
+
+        in += 64;
+        inlen -= 64;
+    }
+
+    store_bigendian_32(statebytes + 0, state[0]);
+    store_bigendian_32(statebytes + 4, state[1]);
+    store_bigendian_32(statebytes + 8, state[2]);
+    store_bigendian_32(statebytes + 12, state[3]);
+    store_bigendian_32(statebytes + 16, state[4]);
+    store_bigendian_32(statebytes + 20, state[5]);
+    store_bigendian_32(statebytes + 24, state[6]);
+    store_bigendian_32(statebytes + 28, state[7]);
+
+    return inlen;
+}
+
 static size_t crypto_hashblocks_sha512(uint8_t *statebytes,
-                                       const uint8_t *in,
-                                       size_t inlen) {
+                                       const uint8_t *in, size_t inlen) {
     uint64_t state[8];
     uint64_t a;
     uint64_t b;
@@ -89,133 +298,133 @@ static size_t crypto_hashblocks_sha512(uint8_t *statebytes,
     uint64_t T1;
     uint64_t T2;
 
-    a = load_bigendian(statebytes + 0);
+    a = load_bigendian_64(statebytes + 0);
     state[0] = a;
-    b = load_bigendian(statebytes + 8);
+    b = load_bigendian_64(statebytes + 8);
     state[1] = b;
-    c = load_bigendian(statebytes + 16);
+    c = load_bigendian_64(statebytes + 16);
     state[2] = c;
-    d = load_bigendian(statebytes + 24);
+    d = load_bigendian_64(statebytes + 24);
     state[3] = d;
-    e = load_bigendian(statebytes + 32);
+    e = load_bigendian_64(statebytes + 32);
     state[4] = e;
-    f = load_bigendian(statebytes + 40);
+    f = load_bigendian_64(statebytes + 40);
     state[5] = f;
-    g = load_bigendian(statebytes + 48);
+    g = load_bigendian_64(statebytes + 48);
     state[6] = g;
-    h = load_bigendian(statebytes + 56);
+    h = load_bigendian_64(statebytes + 56);
     state[7] = h;
 
     while (inlen >= 128) {
-        uint64_t w0 = load_bigendian(in + 0);
-        uint64_t w1 = load_bigendian(in + 8);
-        uint64_t w2 = load_bigendian(in + 16);
-        uint64_t w3 = load_bigendian(in + 24);
-        uint64_t w4 = load_bigendian(in + 32);
-        uint64_t w5 = load_bigendian(in + 40);
-        uint64_t w6 = load_bigendian(in + 48);
-        uint64_t w7 = load_bigendian(in + 56);
-        uint64_t w8 = load_bigendian(in + 64);
-        uint64_t w9 = load_bigendian(in + 72);
-        uint64_t w10 = load_bigendian(in + 80);
-        uint64_t w11 = load_bigendian(in + 88);
-        uint64_t w12 = load_bigendian(in + 96);
-        uint64_t w13 = load_bigendian(in + 104);
-        uint64_t w14 = load_bigendian(in + 112);
-        uint64_t w15 = load_bigendian(in + 120);
-
-        F(w0, 0x428a2f98d728ae22ULL)
-        F(w1, 0x7137449123ef65cdULL)
-        F(w2, 0xb5c0fbcfec4d3b2fULL)
-        F(w3, 0xe9b5dba58189dbbcULL)
-        F(w4, 0x3956c25bf348b538ULL)
-        F(w5, 0x59f111f1b605d019ULL)
-        F(w6, 0x923f82a4af194f9bULL)
-        F(w7, 0xab1c5ed5da6d8118ULL)
-        F(w8, 0xd807aa98a3030242ULL)
-        F(w9, 0x12835b0145706fbeULL)
-        F(w10, 0x243185be4ee4b28cULL)
-        F(w11, 0x550c7dc3d5ffb4e2ULL)
-        F(w12, 0x72be5d74f27b896fULL)
-        F(w13, 0x80deb1fe3b1696b1ULL)
-        F(w14, 0x9bdc06a725c71235ULL)
-        F(w15, 0xc19bf174cf692694ULL)
-
-        EXPAND
-
-        F(w0, 0xe49b69c19ef14ad2ULL)
-        F(w1, 0xefbe4786384f25e3ULL)
-        F(w2, 0x0fc19dc68b8cd5b5ULL)
-        F(w3, 0x240ca1cc77ac9c65ULL)
-        F(w4, 0x2de92c6f592b0275ULL)
-        F(w5, 0x4a7484aa6ea6e483ULL)
-        F(w6, 0x5cb0a9dcbd41fbd4ULL)
-        F(w7, 0x76f988da831153b5ULL)
-        F(w8, 0x983e5152ee66dfabULL)
-        F(w9, 0xa831c66d2db43210ULL)
-        F(w10, 0xb00327c898fb213fULL)
-        F(w11, 0xbf597fc7beef0ee4ULL)
-        F(w12, 0xc6e00bf33da88fc2ULL)
-        F(w13, 0xd5a79147930aa725ULL)
-        F(w14, 0x06ca6351e003826fULL)
-        F(w15, 0x142929670a0e6e70ULL)
-
-        EXPAND
-
-        F(w0, 0x27b70a8546d22ffcULL)
-        F(w1, 0x2e1b21385c26c926ULL)
-        F(w2, 0x4d2c6dfc5ac42aedULL)
-        F(w3, 0x53380d139d95b3dfULL)
-        F(w4, 0x650a73548baf63deULL)
-        F(w5, 0x766a0abb3c77b2a8ULL)
-        F(w6, 0x81c2c92e47edaee6ULL)
-        F(w7, 0x92722c851482353bULL)
-        F(w8, 0xa2bfe8a14cf10364ULL)
-        F(w9, 0xa81a664bbc423001ULL)
-        F(w10, 0xc24b8b70d0f89791ULL)
-        F(w11, 0xc76c51a30654be30ULL)
-        F(w12, 0xd192e819d6ef5218ULL)
-        F(w13, 0xd69906245565a910ULL)
-        F(w14, 0xf40e35855771202aULL)
-        F(w15, 0x106aa07032bbd1b8ULL)
-
-        EXPAND
-
-        F(w0, 0x19a4c116b8d2d0c8ULL)
-        F(w1, 0x1e376c085141ab53ULL)
-        F(w2, 0x2748774cdf8eeb99ULL)
-        F(w3, 0x34b0bcb5e19b48a8ULL)
-        F(w4, 0x391c0cb3c5c95a63ULL)
-        F(w5, 0x4ed8aa4ae3418acbULL)
-        F(w6, 0x5b9cca4f7763e373ULL)
-        F(w7, 0x682e6ff3d6b2b8a3ULL)
-        F(w8, 0x748f82ee5defb2fcULL)
-        F(w9, 0x78a5636f43172f60ULL)
-        F(w10, 0x84c87814a1f0ab72ULL)
-        F(w11, 0x8cc702081a6439ecULL)
-        F(w12, 0x90befffa23631e28ULL)
-        F(w13, 0xa4506cebde82bde9ULL)
-        F(w14, 0xbef9a3f7b2c67915ULL)
-        F(w15, 0xc67178f2e372532bULL)
-
-        EXPAND
-
-        F(w0, 0xca273eceea26619cULL)
-        F(w1, 0xd186b8c721c0c207ULL)
-        F(w2, 0xeada7dd6cde0eb1eULL)
-        F(w3, 0xf57d4f7fee6ed178ULL)
-        F(w4, 0x06f067aa72176fbaULL)
-        F(w5, 0x0a637dc5a2c898a6ULL)
-        F(w6, 0x113f9804bef90daeULL)
-        F(w7, 0x1b710b35131c471bULL)
-        F(w8, 0x28db77f523047d84ULL)
-        F(w9, 0x32caab7b40c72493ULL)
-        F(w10, 0x3c9ebe0a15c9bebcULL)
-        F(w11, 0x431d67c49c100d4cULL)
-        F(w12, 0x4cc5d4becb3e42b6ULL)
-        F(w13, 0x597f299cfc657e2aULL)
-        F(w14, 0x5fcb6fab3ad6faecULL)
-        F(w15, 0x6c44198c4a475817ULL)
+        uint64_t w0 = load_bigendian_64(in + 0);
+        uint64_t w1 = load_bigendian_64(in + 8);
+        uint64_t w2 = load_bigendian_64(in + 16);
+        uint64_t w3 = load_bigendian_64(in + 24);
+        uint64_t w4 = load_bigendian_64(in + 32);
+        uint64_t w5 = load_bigendian_64(in + 40);
+        uint64_t w6 = load_bigendian_64(in + 48);
+        uint64_t w7 = load_bigendian_64(in + 56);
+        uint64_t w8 = load_bigendian_64(in + 64);
+        uint64_t w9 = load_bigendian_64(in + 72);
+        uint64_t w10 = load_bigendian_64(in + 80);
+        uint64_t w11 = load_bigendian_64(in + 88);
+        uint64_t w12 = load_bigendian_64(in + 96);
+        uint64_t w13 = load_bigendian_64(in + 104);
+        uint64_t w14 = load_bigendian_64(in + 112);
+        uint64_t w15 = load_bigendian_64(in + 120);
+
+        F_64(w0, 0x428a2f98d728ae22ULL)
+        F_64(w1, 0x7137449123ef65cdULL)
+        F_64(w2, 0xb5c0fbcfec4d3b2fULL)
+        F_64(w3, 0xe9b5dba58189dbbcULL)
+        F_64(w4, 0x3956c25bf348b538ULL)
+        F_64(w5, 0x59f111f1b605d019ULL)
+        F_64(w6, 0x923f82a4af194f9bULL)
+        F_64(w7, 0xab1c5ed5da6d8118ULL)
+        F_64(w8, 0xd807aa98a3030242ULL)
+        F_64(w9, 0x12835b0145706fbeULL)
+        F_64(w10, 0x243185be4ee4b28cULL)
+        F_64(w11, 0x550c7dc3d5ffb4e2ULL)
+        F_64(w12, 0x72be5d74f27b896fULL)
+        F_64(w13, 0x80deb1fe3b1696b1ULL)
+        F_64(w14, 0x9bdc06a725c71235ULL)
+        F_64(w15, 0xc19bf174cf692694ULL)
+
+        EXPAND_64
+
+        F_64(w0, 0xe49b69c19ef14ad2ULL)
+        F_64(w1, 0xefbe4786384f25e3ULL)
+        F_64(w2, 0x0fc19dc68b8cd5b5ULL)
+        F_64(w3, 0x240ca1cc77ac9c65ULL)
+        F_64(w4, 0x2de92c6f592b0275ULL)
+        F_64(w5, 0x4a7484aa6ea6e483ULL)
+        F_64(w6, 0x5cb0a9dcbd41fbd4ULL)
+        F_64(w7, 0x76f988da831153b5ULL)
+        F_64(w8, 0x983e5152ee66dfabULL)
+        F_64(w9, 0xa831c66d2db43210ULL)
+        F_64(w10, 0xb00327c898fb213fULL)
+        F_64(w11, 0xbf597fc7beef0ee4ULL)
+        F_64(w12, 0xc6e00bf33da88fc2ULL)
+        F_64(w13, 0xd5a79147930aa725ULL)
+        F_64(w14, 0x06ca6351e003826fULL)
+        F_64(w15, 0x142929670a0e6e70ULL)
+
+        EXPAND_64
+
+        F_64(w0, 0x27b70a8546d22ffcULL)
+        F_64(w1, 0x2e1b21385c26c926ULL)
+        F_64(w2, 0x4d2c6dfc5ac42aedULL)
+        F_64(w3, 0x53380d139d95b3dfULL)
+        F_64(w4, 0x650a73548baf63deULL)
+        F_64(w5, 0x766a0abb3c77b2a8ULL)
+        F_64(w6, 0x81c2c92e47edaee6ULL)
+        F_64(w7, 0x92722c851482353bULL)
+        F_64(w8, 0xa2bfe8a14cf10364ULL)
+        F_64(w9, 0xa81a664bbc423001ULL)
+        F_64(w10, 0xc24b8b70d0f89791ULL)
+        F_64(w11, 0xc76c51a30654be30ULL)
+        F_64(w12, 0xd192e819d6ef5218ULL)
+        F_64(w13, 0xd69906245565a910ULL)
+        F_64(w14, 0xf40e35855771202aULL)
+        F_64(w15, 0x106aa07032bbd1b8ULL)
+
+        EXPAND_64
+
+        F_64(w0, 0x19a4c116b8d2d0c8ULL)
+        F_64(w1, 0x1e376c085141ab53ULL)
+        F_64(w2, 0x2748774cdf8eeb99ULL)
+        F_64(w3, 0x34b0bcb5e19b48a8ULL)
+        F_64(w4, 0x391c0cb3c5c95a63ULL)
+        F_64(w5, 0x4ed8aa4ae3418acbULL)
+        F_64(w6, 0x5b9cca4f7763e373ULL)
+        F_64(w7, 0x682e6ff3d6b2b8a3ULL)
+        F_64(w8, 0x748f82ee5defb2fcULL)
+        F_64(w9, 0x78a5636f43172f60ULL)
+        F_64(w10, 0x84c87814a1f0ab72ULL)
+        F_64(w11, 0x8cc702081a6439ecULL)
+        F_64(w12, 0x90befffa23631e28ULL)
+        F_64(w13, 0xa4506cebde82bde9ULL)
+        F_64(w14, 0xbef9a3f7b2c67915ULL)
+        F_64(w15, 0xc67178f2e372532bULL)
+
+        EXPAND_64
+
+        F_64(w0, 0xca273eceea26619cULL)
+        F_64(w1, 0xd186b8c721c0c207ULL)
+        F_64(w2, 0xeada7dd6cde0eb1eULL)
+        F_64(w3, 0xf57d4f7fee6ed178ULL)
+        F_64(w4, 0x06f067aa72176fbaULL)
+        F_64(w5, 0x0a637dc5a2c898a6ULL)
+        F_64(w6, 0x113f9804bef90daeULL)
+        F_64(w7, 0x1b710b35131c471bULL)
+        F_64(w8, 0x28db77f523047d84ULL)
+        F_64(w9, 0x32caab7b40c72493ULL)
+        F_64(w10, 0x3c9ebe0a15c9bebcULL)
+        F_64(w11, 0x431d67c49c100d4cULL)
+        F_64(w12, 0x4cc5d4becb3e42b6ULL)
+        F_64(w13, 0x597f299cfc657e2aULL)
+        F_64(w14, 0x5fcb6fab3ad6faecULL)
+        F_64(w15, 0x6c44198c4a475817ULL)
 
         a += state[0];
         b += state[1];
@@ -239,19 +448,24 @@ static size_t crypto_hashblocks_sha512(uint8_t *statebytes,
         inlen -= 128;
     }
 
-    store_bigendian(statebytes + 0, state[0]);
-    store_bigendian(statebytes + 8, state[1]);
-    store_bigendian(statebytes + 16, state[2]);
-    store_bigendian(statebytes + 24, state[3]);
-    store_bigendian(statebytes + 32, state[4]);
-    store_bigendian(statebytes + 40, state[5]);
-    store_bigendian(statebytes + 48, state[6]);
-    store_bigendian(statebytes + 56, state[7]);
+    store_bigendian_64(statebytes + 0, state[0]);
+    store_bigendian_64(statebytes + 8, state[1]);
+    store_bigendian_64(statebytes + 16, state[2]);
+    store_bigendian_64(statebytes + 24, state[3]);
+    store_bigendian_64(statebytes + 32, state[4]);
+    store_bigendian_64(statebytes + 40, state[5]);
+    store_bigendian_64(statebytes + 48, state[6]);
+    store_bigendian_64(statebytes + 56, state[7]);
 
     return inlen;
 }
 
-#define blocks crypto_hashblocks_sha512
+static const uint8_t iv_256[32] = {
+    0x6a, 0x09, 0xe6, 0x67, 0xbb, 0x67, 0xae, 0x85,
+    0x3c, 0x6e, 0xf3, 0x72, 0xa5, 0x4f, 0xf5, 0x3a,
+    0x51, 0x0e, 0x52, 0x7f, 0x9b, 0x05, 0x68, 0x8c,
+    0x1f, 0x83, 0xd9, 0xab, 0x5b, 0xe0, 0xcd, 0x19,
+};
 
 static const uint8_t iv_384[64] = {
     0xcb, 0xbb, 0x9d, 0x5d, 0xc1, 0x05, 0x9e, 0xd8, 0x62, 0x9a, 0x29,
@@ -271,6 +485,60 @@ static const uint8_t iv_512[64] = {
     0x6b, 0x5b, 0xe0, 0xcd, 0x19, 0x13, 0x7e, 0x21, 0x79
 };
 
+int sha256(uint8_t *out, const uint8_t *in, size_t inlen) {
+    uint8_t h[32];
+    uint8_t padded[128];
+    uint64_t bytes = inlen;
+
+    for (size_t i = 0; i < 32; ++i) {
+        h[i] = iv_256[i];
+    }
+
+    crypto_hashblocks_sha256(h, in, inlen);
+    in += inlen;
+    inlen &= 63;
+    in -= inlen;
+
+    for (size_t i = 0; i < inlen; ++i) {
+        padded[i] = in[i];
+    }
+    padded[inlen] = 0x80;
+
+    if (inlen < 56) {
+        for (size_t i = inlen + 1; i < 56; ++i) {
+            padded[i] = 0;
+        }
+        padded[56] = (uint8_t) (bytes >> 53);
+        padded[57] = (uint8_t) (bytes >> 45);
+        padded[58] = (uint8_t) (bytes >> 37);
+        padded[59] = (uint8_t) (bytes >> 29);
+        padded[60] = (uint8_t) (bytes >> 21);
+        padded[61] = (uint8_t) (bytes >> 13);
+        padded[62] = (uint8_t) (bytes >> 5);
+        padded[63] = (uint8_t) (bytes << 3);
+        crypto_hashblocks_sha256(h, padded, 64);
+    } else {
+        for (size_t i = inlen + 1; i < 120; ++i) {
+            padded[i] = 0;
+        }
+        padded[120] = (uint8_t) (bytes >> 53);
+        padded[121] = (uint8_t) (bytes >> 45);
+        padded[122] = (uint8_t) (bytes >> 37);
+        padded[123] = (uint8_t) (bytes >> 29);
+        padded[124] = (uint8_t) (bytes >> 21);
+        padded[125] = (uint8_t) (bytes >> 13);
+        padded[126] = (uint8_t) (bytes >> 5);
+        padded[127] = (uint8_t) (bytes << 3);
+        crypto_hashblocks_sha256(h, padded, 128);
+    }
+
+    for (size_t i = 0; i < 32; ++i) {
+        out[i] = h[i];
+    }
+
+    return 0;
+}
+
 int sha384(uint8_t *out, const uint8_t *in, size_t inlen) {
     uint8_t h[64];
     uint8_t padded[256];
@@ -280,7 +548,7 @@ int sha384(uint8_t *out, const uint8_t *in, size_t inlen) {
         h[i] = iv_384[i];
     }
 
-    blocks(h, in, inlen);
+    crypto_hashblocks_sha512(h, in, inlen);
     in += inlen;
     inlen &= 127;
     in -= inlen;
@@ -303,7 +571,7 @@ int sha384(uint8_t *out, const uint8_t *in, size_t inlen) {
         padded[125] = (uint8_t) (bytes >> 13);
         padded[126] = (uint8_t) (bytes >> 5);
         padded[127] = (uint8_t) (bytes << 3);
-        blocks(h, padded, 128);
+        crypto_hashblocks_sha512(h, padded, 128);
     } else {
         for (size_t i = inlen + 1; i < 247; ++i) {
             padded[i] = 0;
@@ -317,7 +585,7 @@ int sha384(uint8_t *out, const uint8_t *in, size_t inlen) {
         padded[253] = (uint8_t) (bytes >> 13);
         padded[254] = (uint8_t) (bytes >> 5);
         padded[255] = (uint8_t) (bytes << 3);
-        blocks(h, padded, 256);
+        crypto_hashblocks_sha512(h, padded, 256);
     }
 
     for (size_t i = 0; i < 48; ++i) {
@@ -336,7 +604,7 @@ int sha512(uint8_t *out, const uint8_t *in, size_t inlen) {
         h[i] = iv_512[i];
     }
 
-    blocks(h, in, inlen);
+    crypto_hashblocks_sha512(h, in, inlen);
     in += inlen;
     inlen &= 127;
     in -= inlen;
@@ -359,7 +627,7 @@ int sha512(uint8_t *out, const uint8_t *in, size_t inlen) {
         padded[125] = (uint8_t) (bytes >> 13);
         padded[126] = (uint8_t) (bytes >> 5);
         padded[127] = (uint8_t) (bytes << 3);
-        blocks(h, padded, 128);
+        crypto_hashblocks_sha512(h, padded, 128);
     } else {
         for (size_t i = inlen + 1; i < 247; ++i) {
             padded[i] = 0;
@@ -373,7 +641,7 @@ int sha512(uint8_t *out, const uint8_t *in, size_t inlen) {
         padded[253] = (uint8_t) (bytes >> 13);
         padded[254] = (uint8_t) (bytes >> 5);
         padded[255] = (uint8_t) (bytes << 3);
-        blocks(h, padded, 256);
+        crypto_hashblocks_sha512(h, padded, 256);
     }
 
     for (size_t i = 0; i < 64; ++i) {

common/sha2.h

@@ -1,7 +1,13 @@
 #ifndef SHA2_H
 #define SHA2_H
 
+#include <stddef.h>
+#include <stdint.h>
+
+int sha256(uint8_t *out, const uint8_t *in, size_t inlen);
+
 int sha384(uint8_t *out, const uint8_t *in, size_t inlen);
+
 int sha512(uint8_t *out, const uint8_t *in, size_t inlen);
 
 #endif

test/Makefile

@@ -37,6 +37,10 @@ $(DEST_DIR)/test_fips202: common/fips202.c $(COMMON_FILES)
 	mkdir -p $(DEST_DIR)
 	$(CC) $(CFLAGS) $< $(COMMON_FILES) -o $@
 
+$(DEST_DIR)/test_sha2: common/sha2.c $(COMMON_FILES)
+	mkdir -p $(DEST_DIR)
+	$(CC) $(CFLAGS) $< $(COMMON_FILES) -o $@
+
 $(DEST_DIR)/functest_$(SCHEME)_$(IMPLEMENTATION): build-scheme crypto_$(TYPE)/functest.c $(COMMON_FILES) $(COMMON_DIR)/randombytes.c $(COMMON_HEADERS)
 	mkdir -p $(DEST_DIR)
 	$(CC) $(CFLAGS) -DPQCLEAN_NAMESPACE=PQCLEAN_$(SCHEME_UPPERCASE)_$(IMPLEMENTATION_UPPERCASE) -I$(SCHEME_DIR) crypto_$(TYPE)/functest.c $(COMMON_FILES) $(COMMON_DIR)/notrandombytes.c -o $@ -L$(SCHEME_DIR) -l$(SCHEME)_$(IMPLEMENTATION)
@@ -50,3 +54,4 @@ clean:
 	$(RM) $(DEST_DIR)/functest_$(SCHEME)_$(IMPLEMENTATION)
 	$(RM) $(DEST_DIR)/testvectors_$(SCHEME)_$(IMPLEMENTATION)
 	$(RM) $(DEST_DIR)/test_fips202
+	$(RM) $(DEST_DIR)/test_sha2

test/common/sha2.c

@@ -0,0 +1,114 @@
+#include "sha2.h"
+
+#include <stdio.h>
+#include <stdint.h>
+#include <string.h>
+#include <inttypes.h>
+
+const unsigned char plaintext[44] = "The quick brown fox jumps over the lazy dog";
+
+const unsigned char expected_256[32] = {
+    0xd7, 0xa8, 0xfb, 0xb3, 0x07, 0xd7, 0x80, 0x94, 0x69, 0xca, 0x9a, 0xbc,
+    0xb0, 0x08, 0x2e, 0x4f, 0x8d, 0x56, 0x51, 0xe4, 0x6d, 0x3c, 0xdb, 0x76,
+    0x2d, 0x02, 0xd0, 0xbf, 0x37, 0xc9, 0xe5, 0x92,
+};
+
+const unsigned char expected_384[48] = {
+    0xca, 0x73, 0x7f, 0x10, 0x14, 0xa4, 0x8f, 0x4c, 0x0b, 0x6d, 0xd4, 0x3c,
+    0xb1, 0x77, 0xb0, 0xaf, 0xd9, 0xe5, 0x16, 0x93, 0x67, 0x54, 0x4c, 0x49,
+    0x40, 0x11, 0xe3, 0x31, 0x7d, 0xbf, 0x9a, 0x50, 0x9c, 0xb1, 0xe5, 0xdc,
+    0x1e, 0x85, 0xa9, 0x41, 0xbb, 0xee, 0x3d, 0x7f, 0x2a, 0xfb, 0xc9, 0xb1,
+};
+
+const unsigned char expected_512[64] = {
+    0x07, 0xe5, 0x47, 0xd9, 0x58, 0x6f, 0x6a, 0x73, 0xf7, 0x3f, 0xba, 0xc0,
+    0x43, 0x5e, 0xd7, 0x69, 0x51, 0x21, 0x8f, 0xb7, 0xd0, 0xc8, 0xd7, 0x88,
+    0xa3, 0x09, 0xd7, 0x85, 0x43, 0x6b, 0xbb, 0x64, 0x2e, 0x93, 0xa2, 0x52,
+    0xa9, 0x54, 0xf2, 0x39, 0x12, 0x54, 0x7d, 0x1e, 0x8a, 0x3b, 0x5e, 0xd6,
+    0xe1, 0xbf, 0xd7, 0x09, 0x78, 0x21, 0x23, 0x3f, 0xa0, 0x53, 0x8f, 0x3d,
+    0xb8, 0x54, 0xfe, 0xe6,
+};
+
+static int test_sha256(void) {
+    unsigned char output[32];
+    int i = 0;
+
+    sha256(output, plaintext, 43);
+
+    if (memcmp(expected_256, output, 32)) {
+        printf("ERROR sha256 output did not match test vector.\n");
+        printf("Expected: ");
+        for (i = 0; i < 32; i++) {
+            printf("%02X", expected_256[i]);
+        }
+        printf("\n");
+        printf("Received: ");
+        for (i = 0; i < 32; i++) {
+            printf("%02X", output[i]);
+        }
+        printf("\n");
+        return 1;
+    }
+
+    return 0;
+}
+
+static int test_sha384(void) {
+    unsigned char output[48];
+    int i = 0;
+
+    sha384(output, plaintext, 43);
+
+    if (memcmp(expected_384, output, 48)) {
+        printf("ERROR sha384 output did not match test vector.\n");
+        printf("Expected: ");
+        for (i = 0; i < 48; i++) {
+            printf("%02X", expected_384[i]);
+        }
+        printf("\n");
+        printf("Received: ");
+        for (i = 0; i < 48; i++) {
+            printf("%02X", output[i]);
+        }
+        printf("\n");
+        return 1;
+    }
+
+    return 0;
+}
+
+static int test_sha512(void) {
+    unsigned char output[64];
+    int i = 0;
+
+    sha512(output, plaintext, 43);
+
+    if (memcmp(expected_512, output, 64)) {
+        printf("ERROR sha512 output did not match test vector.\n");
+        printf("Expected: ");
+        for (i = 0; i < 64; i++) {
+            printf("%02X", expected_512[i]);
+        }
+        printf("\n");
+        printf("Received: ");
+        for (i = 0; i < 64; i++) {
+            printf("%02X", output[i]);
+        }
+        printf("\n");
+        return 1;
+    }
+
+    return 0;
+}
+
+int main(void) {
+    int result = 0;
+    result += test_sha256();
+    result += test_sha384();
+    result += test_sha512();
+
+    if (result != 0) {
+        puts("Errors occurred");
+    }
+    return result;
+}