Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:
   - Add speed testing on 1420-byte blocks for networking

  Algorithms:
   - Improve performance of chacha on ARM for network packets
   - Improve performance of aegis128 on ARM for network packets

  Drivers:
   - Add support for Keem Bay OCS AES/SM4
   - Add support for QAT 4xxx devices
   - Enable crypto-engine retry mechanism in caam
   - Enable support for crypto engine on sdm845 in qce
   - Add HiSilicon PRNG driver support"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (161 commits)
  crypto: qat - add capability detection logic in qat_4xxx
  crypto: qat - add AES-XTS support for QAT GEN4 devices
  crypto: qat - add AES-CTR support for QAT GEN4 devices
  crypto: atmel-i2c - select CONFIG_BITREVERSE
  crypto: hisilicon/trng - replace atomic_add_return()
  crypto: keembay - Add support for Keem Bay OCS AES/SM4
  dt-bindings: Add Keem Bay OCS AES bindings
  crypto: aegis128 - avoid spurious references crypto_aegis128_update_simd
  crypto: seed - remove trailing semicolon in macro definition
  crypto: x86/poly1305 - Use TEST %reg,%reg instead of CMP $0,%reg
  crypto: x86/sha512 - Use TEST %reg,%reg instead of CMP $0,%reg
  crypto: aesni - Use TEST %reg,%reg instead of CMP $0,%reg
  crypto: cpt - Fix sparse warnings in cptpf
  hwrng: ks-sa - Add dependency on IOMEM and OF
  crypto: lib/blake2s - Move selftest prototype into header file
  crypto: arm/aes-ce - work around Cortex-A57/A72 silion errata
  crypto: ecdh - avoid unaligned accesses in ecdh_set_secret()
  crypto: ccree - rework cache parameters handling
  crypto: cavium - Use dma_set_mask_and_coherent to simplify code
  crypto: marvell/octeontx - Use dma_set_mask_and_coherent to simplify code
  ...

7 files changed, 68 insertions, 159 deletions

diff --git a/lib/crypto/blake2s-selftest.c b/lib/crypto/blake2s-selftest.c
index 79ef404a990d..5d9ea53be973 100644
--- a/lib/crypto/blake2s-selftest.c
+++ b/lib/crypto/blake2s-selftest.c
@@ -3,7 +3,7 @@
  * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
  */
 
-#include <crypto/blake2s.h>
+#include <crypto/internal/blake2s.h>
 #include <linux/string.h>
 
 /*
diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c
index 41025a30c524..6a4b6b78d630 100644
--- a/lib/crypto/blake2s.c
+++ b/lib/crypto/blake2s.c
@@ -17,8 +17,6 @@
 #include <linux/bug.h>
 #include <asm/unaligned.h>
 
-bool blake2s_selftest(void);
-
 void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen)
 {
 	const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen;
diff --git a/lib/crypto/curve25519.c b/lib/crypto/curve25519.c
index 288a62cd29b2..fb29739e8c29 100644
--- a/lib/crypto/curve25519.c
+++ b/lib/crypto/curve25519.c
@@ -13,8 +13,6 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
-bool curve25519_selftest(void);
-
 static int __init mod_init(void)
 {
 	if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) &&
diff --git a/lib/crypto/sha256.c b/lib/crypto/sha256.c
index 2321f6cb322f..72a4b0b1df28 100644
--- a/lib/crypto/sha256.c
+++ b/lib/crypto/sha256.c
@@ -15,9 +15,28 @@
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/string.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <asm/unaligned.h>
 
+static const u32 SHA256_K[] = {
+	0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5,
+	0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
+	0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
+	0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
+	0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc,
+	0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+	0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7,
+	0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
+	0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
+	0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
+	0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3,
+	0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+	0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5,
+	0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
+	0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
+	0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2,
+};
+
 static inline u32 Ch(u32 x, u32 y, u32 z)
 {
 	return z ^ (x & (y ^ z));
@@ -43,173 +62,68 @@ static inline void BLEND_OP(int I, u32 *W)
 	W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
 }
 
-static void sha256_transform(u32 *state, const u8 *input)
+#define SHA256_ROUND(i, a, b, c, d, e, f, g, h) do {		\
+	u32 t1, t2;						\
+	t1 = h + e1(e) + Ch(e, f, g) + SHA256_K[i] + W[i];	\
+	t2 = e0(a) + Maj(a, b, c);				\
+	d += t1;						\
+	h = t1 + t2;						\
+} while (0)
+
+static void sha256_transform(u32 *state, const u8 *input, u32 *W)
 {
-	u32 a, b, c, d, e, f, g, h, t1, t2;
-	u32 W[64];
+	u32 a, b, c, d, e, f, g, h;
 	int i;
 
 	/* load the input */
-	for (i = 0; i < 16; i++)
-		LOAD_OP(i, W, input);
+	for (i = 0; i < 16; i += 8) {
+		LOAD_OP(i + 0, W, input);
+		LOAD_OP(i + 1, W, input);
+		LOAD_OP(i + 2, W, input);
+		LOAD_OP(i + 3, W, input);
+		LOAD_OP(i + 4, W, input);
+		LOAD_OP(i + 5, W, input);
+		LOAD_OP(i + 6, W, input);
+		LOAD_OP(i + 7, W, input);
+	}
 
 	/* now blend */
-	for (i = 16; i < 64; i++)
-		BLEND_OP(i, W);
+	for (i = 16; i < 64; i += 8) {
+		BLEND_OP(i + 0, W);
+		BLEND_OP(i + 1, W);
+		BLEND_OP(i + 2, W);
+		BLEND_OP(i + 3, W);
+		BLEND_OP(i + 4, W);
+		BLEND_OP(i + 5, W);
+		BLEND_OP(i + 6, W);
+		BLEND_OP(i + 7, W);
+	}
 
 	/* load the state into our registers */
 	a = state[0];  b = state[1];  c = state[2];  d = state[3];
 	e = state[4];  f = state[5];  g = state[6];  h = state[7];
 
 	/* now iterate */
-	t1 = h + e1(e) + Ch(e, f, g) + 0x428a2f98 + W[0];
-	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
-	t1 = g + e1(d) + Ch(d, e, f) + 0x71374491 + W[1];
-	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
-	t1 = f + e1(c) + Ch(c, d, e) + 0xb5c0fbcf + W[2];
-	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
-	t1 = e + e1(b) + Ch(b, c, d) + 0xe9b5dba5 + W[3];
-	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
-	t1 = d + e1(a) + Ch(a, b, c) + 0x3956c25b + W[4];
-	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
-	t1 = c + e1(h) + Ch(h, a, b) + 0x59f111f1 + W[5];
-	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
-	t1 = b + e1(g) + Ch(g, h, a) + 0x923f82a4 + W[6];
-	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
-	t1 = a + e1(f) + Ch(f, g, h) + 0xab1c5ed5 + W[7];
-	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
-
-	t1 = h + e1(e) + Ch(e, f, g) + 0xd807aa98 + W[8];
-	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
-	t1 = g + e1(d) + Ch(d, e, f) + 0x12835b01 + W[9];
-	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
-	t1 = f + e1(c) + Ch(c, d, e) + 0x243185be + W[10];
-	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
-	t1 = e + e1(b) + Ch(b, c, d) + 0x550c7dc3 + W[11];
-	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
-	t1 = d + e1(a) + Ch(a, b, c) + 0x72be5d74 + W[12];
-	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
-	t1 = c + e1(h) + Ch(h, a, b) + 0x80deb1fe + W[13];
-	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
-	t1 = b + e1(g) + Ch(g, h, a) + 0x9bdc06a7 + W[14];
-	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
-	t1 = a + e1(f) + Ch(f, g, h) + 0xc19bf174 + W[15];
-	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
-
-	t1 = h + e1(e) + Ch(e, f, g) + 0xe49b69c1 + W[16];
-	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
-	t1 = g + e1(d) + Ch(d, e, f) + 0xefbe4786 + W[17];
-	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
-	t1 = f + e1(c) + Ch(c, d, e) + 0x0fc19dc6 + W[18];
-	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
-	t1 = e + e1(b) + Ch(b, c, d) + 0x240ca1cc + W[19];
-	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
-	t1 = d + e1(a) + Ch(a, b, c) + 0x2de92c6f + W[20];
-	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
-	t1 = c + e1(h) + Ch(h, a, b) + 0x4a7484aa + W[21];
-	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
-	t1 = b + e1(g) + Ch(g, h, a) + 0x5cb0a9dc + W[22];
-	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
-	t1 = a + e1(f) + Ch(f, g, h) + 0x76f988da + W[23];
-	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
-
-	t1 = h + e1(e) + Ch(e, f, g) + 0x983e5152 + W[24];
-	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
-	t1 = g + e1(d) + Ch(d, e, f) + 0xa831c66d + W[25];
-	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
-	t1 = f + e1(c) + Ch(c, d, e) + 0xb00327c8 + W[26];
-	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
-	t1 = e + e1(b) + Ch(b, c, d) + 0xbf597fc7 + W[27];
-	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
-	t1 = d + e1(a) + Ch(a, b, c) + 0xc6e00bf3 + W[28];
-	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
-	t1 = c + e1(h) + Ch(h, a, b) + 0xd5a79147 + W[29];
-	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
-	t1 = b + e1(g) + Ch(g, h, a) + 0x06ca6351 + W[30];
-	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
-	t1 = a + e1(f) + Ch(f, g, h) + 0x14292967 + W[31];
-	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
-
-	t1 = h + e1(e) + Ch(e, f, g) + 0x27b70a85 + W[32];
-	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
-	t1 = g + e1(d) + Ch(d, e, f) + 0x2e1b2138 + W[33];
-	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
-	t1 = f + e1(c) + Ch(c, d, e) + 0x4d2c6dfc + W[34];
-	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
-	t1 = e + e1(b) + Ch(b, c, d) + 0x53380d13 + W[35];
-	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
-	t1 = d + e1(a) + Ch(a, b, c) + 0x650a7354 + W[36];
-	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
-	t1 = c + e1(h) + Ch(h, a, b) + 0x766a0abb + W[37];
-	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
-	t1 = b + e1(g) + Ch(g, h, a) + 0x81c2c92e + W[38];
-	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
-	t1 = a + e1(f) + Ch(f, g, h) + 0x92722c85 + W[39];
-	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
-
-	t1 = h + e1(e) + Ch(e, f, g) + 0xa2bfe8a1 + W[40];
-	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
-	t1 = g + e1(d) + Ch(d, e, f) + 0xa81a664b + W[41];
-	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
-	t1 = f + e1(c) + Ch(c, d, e) + 0xc24b8b70 + W[42];
-	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
-	t1 = e + e1(b) + Ch(b, c, d) + 0xc76c51a3 + W[43];
-	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
-	t1 = d + e1(a) + Ch(a, b, c) + 0xd192e819 + W[44];
-	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
-	t1 = c + e1(h) + Ch(h, a, b) + 0xd6990624 + W[45];
-	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
-	t1 = b + e1(g) + Ch(g, h, a) + 0xf40e3585 + W[46];
-	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
-	t1 = a + e1(f) + Ch(f, g, h) + 0x106aa070 + W[47];
-	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
-
-	t1 = h + e1(e) + Ch(e, f, g) + 0x19a4c116 + W[48];
-	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
-	t1 = g + e1(d) + Ch(d, e, f) + 0x1e376c08 + W[49];
-	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
-	t1 = f + e1(c) + Ch(c, d, e) + 0x2748774c + W[50];
-	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
-	t1 = e + e1(b) + Ch(b, c, d) + 0x34b0bcb5 + W[51];
-	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
-	t1 = d + e1(a) + Ch(a, b, c) + 0x391c0cb3 + W[52];
-	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
-	t1 = c + e1(h) + Ch(h, a, b) + 0x4ed8aa4a + W[53];
-	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
-	t1 = b + e1(g) + Ch(g, h, a) + 0x5b9cca4f + W[54];
-	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
-	t1 = a + e1(f) + Ch(f, g, h) + 0x682e6ff3 + W[55];
-	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
-
-	t1 = h + e1(e) + Ch(e, f, g) + 0x748f82ee + W[56];
-	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
-	t1 = g + e1(d) + Ch(d, e, f) + 0x78a5636f + W[57];
-	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
-	t1 = f + e1(c) + Ch(c, d, e) + 0x84c87814 + W[58];
-	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
-	t1 = e + e1(b) + Ch(b, c, d) + 0x8cc70208 + W[59];
-	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
-	t1 = d + e1(a) + Ch(a, b, c) + 0x90befffa + W[60];
-	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
-	t1 = c + e1(h) + Ch(h, a, b) + 0xa4506ceb + W[61];
-	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
-	t1 = b + e1(g) + Ch(g, h, a) + 0xbef9a3f7 + W[62];
-	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
-	t1 = a + e1(f) + Ch(f, g, h) + 0xc67178f2 + W[63];
-	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
+	for (i = 0; i < 64; i += 8) {
+		SHA256_ROUND(i + 0, a, b, c, d, e, f, g, h);
+		SHA256_ROUND(i + 1, h, a, b, c, d, e, f, g);
+		SHA256_ROUND(i + 2, g, h, a, b, c, d, e, f);
+		SHA256_ROUND(i + 3, f, g, h, a, b, c, d, e);
+		SHA256_ROUND(i + 4, e, f, g, h, a, b, c, d);
+		SHA256_ROUND(i + 5, d, e, f, g, h, a, b, c);
+		SHA256_ROUND(i + 6, c, d, e, f, g, h, a, b);
+		SHA256_ROUND(i + 7, b, c, d, e, f, g, h, a);
+	}
 
 	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
 	state[4] += e; state[5] += f; state[6] += g; state[7] += h;
-
-	/* clear any sensitive info... */
-	a = b = c = d = e = f = g = h = t1 = t2 = 0;
-	memzero_explicit(W, 64 * sizeof(u32));
 }
 
 void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 {
 	unsigned int partial, done;
 	const u8 *src;
+	u32 W[64];
 
 	partial = sctx->count & 0x3f;
 	sctx->count += len;
@@ -224,11 +138,13 @@ void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 		}
 
 		do {
-			sha256_transform(sctx->state, src);
+			sha256_transform(sctx->state, src, W);
 			done += 64;
 			src = data + done;
 		} while (done + 63 < len);
 
+		memzero_explicit(W, sizeof(W));
+
 		partial = 0;
 	}
 	memcpy(sctx->buf + partial, src, len - done);
@@ -265,7 +181,7 @@ static void __sha256_final(struct sha256_state *sctx, u8 *out, int digest_words)
 		put_unaligned_be32(sctx->state[i], &dst[i]);
 
 	/* Zeroize sensitive information. */
-	memset(sctx, 0, sizeof(*sctx));
+	memzero_explicit(sctx, sizeof(*sctx));
 }
 
 void sha256_final(struct sha256_state *sctx, u8 *out)
diff --git a/lib/digsig.c b/lib/digsig.c
index e0627c3e53b2..04b5e55ed95f 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -20,7 +20,7 @@
 #include <linux/key.h>
 #include <linux/crypto.h>
 #include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <keys/user-type.h>
 #include <linux/mpi.h>
 #include <linux/digsig.h>
diff --git a/lib/mpi/ec.c b/lib/mpi/ec.c
index c21470122dfc..40f5908e57a4 100644
--- a/lib/mpi/ec.c
+++ b/lib/mpi/ec.c
@@ -1252,7 +1252,6 @@ void mpi_ec_mul_point(MPI_POINT result,
 		MPI_POINT q1, q2, prd, sum;
 		unsigned long sw;
 		mpi_size_t rsize;
-		int scalar_copied = 0;
 
 		/* Compute scalar point multiplication with Montgomery Ladder.
 		 * Note that we don't use Y-coordinate in the points at all.
@@ -1314,8 +1313,6 @@ void mpi_ec_mul_point(MPI_POINT result,
 		point_free(&p2);
 		point_free(&p1_);
 		point_free(&p2_);
-		if (scalar_copied)
-			mpi_free(scalar);
 		return;
 	}
 
diff --git a/lib/sha1.c b/lib/sha1.c
index 49257a915bb6..9bd1935a1472 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -9,7 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/bitops.h>
-#include <crypto/sha.h>
+#include <crypto/sha1.h>
 #include <asm/unaligned.h>
 
 /*