Merge changes Ic355d241,I69410667 into LW.BR.4.0.3.r1
* changes:
BACKPORT: crypto: chacha20 - Fix chacha20_block() keystream alignment (again)
UPSTREAM: crypto: chacha20 - use rol32() macro from bitops.h
diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
index 1a48d3a..94a2048 100644
--- a/crypto/chacha20_generic.c
+++ b/crypto/chacha20_generic.c
@@ -19,20 +19,21 @@
static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
unsigned int bytes)
{
- u32 stream[CHACHA20_BLOCK_WORDS];
+ /* aligned to potentially speed up crypto_xor() */
+ u8 stream[CHACHA20_BLOCK_SIZE] __aligned(sizeof(long));
if (dst != src)
memcpy(dst, src, bytes);
while (bytes >= CHACHA20_BLOCK_SIZE) {
chacha20_block(state, stream);
- crypto_xor(dst, (const u8 *)stream, CHACHA20_BLOCK_SIZE);
+ crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE);
bytes -= CHACHA20_BLOCK_SIZE;
dst += CHACHA20_BLOCK_SIZE;
}
if (bytes) {
chacha20_block(state, stream);
- crypto_xor(dst, (const u8 *)stream, bytes);
+ crypto_xor(dst, stream, bytes);
}
}
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 8b659c5..8a42bff 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -440,9 +440,9 @@ static int crng_init_cnt = 0;
static unsigned long crng_global_init_time = 0;
#define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
static void _extract_crng(struct crng_state *crng,
- __u32 out[CHACHA20_BLOCK_WORDS]);
+ __u8 out[CHACHA20_BLOCK_SIZE]);
static void _crng_backtrack_protect(struct crng_state *crng,
- __u32 tmp[CHACHA20_BLOCK_WORDS], int used);
+ __u8 tmp[CHACHA20_BLOCK_SIZE], int used);
static void process_random_ready_list(void);
static struct ratelimit_state unseeded_warning =
@@ -868,7 +868,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
unsigned long flags;
int i, num;
union {
- __u32 block[CHACHA20_BLOCK_WORDS];
+ __u8 block[CHACHA20_BLOCK_SIZE];
__u32 key[8];
} buf;
@@ -926,7 +926,7 @@ static inline void crng_wait_ready(void)
}
static void _extract_crng(struct crng_state *crng,
- __u32 out[CHACHA20_BLOCK_WORDS])
+ __u8 out[CHACHA20_BLOCK_SIZE])
{
unsigned long v, flags;
@@ -943,7 +943,7 @@ static void _extract_crng(struct crng_state *crng,
spin_unlock_irqrestore(&crng->lock, flags);
}
-static void extract_crng(__u32 out[CHACHA20_BLOCK_WORDS])
+static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
{
struct crng_state *crng = NULL;
@@ -961,7 +961,7 @@ static void extract_crng(__u32 out[CHACHA20_BLOCK_WORDS])
* enough) to mutate the CRNG key to provide backtracking protection.
*/
static void _crng_backtrack_protect(struct crng_state *crng,
- __u32 tmp[CHACHA20_BLOCK_WORDS], int used)
+ __u8 tmp[CHACHA20_BLOCK_SIZE], int used)
{
unsigned long flags;
__u32 *s, *d;
@@ -973,14 +973,14 @@ static void _crng_backtrack_protect(struct crng_state *crng,
used = 0;
}
spin_lock_irqsave(&crng->lock, flags);
- s = &tmp[used / sizeof(__u32)];
+ s = (__u32 *) &tmp[used];
d = &crng->state[4];
for (i=0; i < 8; i++)
*d++ ^= *s++;
spin_unlock_irqrestore(&crng->lock, flags);
}
-static void crng_backtrack_protect(__u32 tmp[CHACHA20_BLOCK_WORDS], int used)
+static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used)
{
struct crng_state *crng = NULL;
@@ -996,7 +996,7 @@ static void crng_backtrack_protect(__u32 tmp[CHACHA20_BLOCK_WORDS], int used)
static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
{
ssize_t ret = 0, i = CHACHA20_BLOCK_SIZE;
- __u32 tmp[CHACHA20_BLOCK_WORDS];
+ __u8 tmp[CHACHA20_BLOCK_SIZE] __aligned(4);
int large_request = (nbytes > 256);
while (nbytes) {
@@ -1564,7 +1564,7 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
*/
void get_random_bytes(void *buf, int nbytes)
{
- __u32 tmp[CHACHA20_BLOCK_WORDS];
+ __u8 tmp[CHACHA20_BLOCK_SIZE] __aligned(4);
#if DEBUG_RANDOM_BOOT > 0
if (!crng_ready())
@@ -2124,7 +2124,7 @@ unsigned long get_random_long(void)
batch = &get_cpu_var(batched_entropy_long);
if (batch->position % ARRAY_SIZE(batch->entropy_long) == 0) {
- extract_crng((__u32 *)batch->entropy_long);
+ extract_crng((u8 *)batch->entropy_long);
batch->position = 0;
}
ret = batch->entropy_long[batch->position++];
@@ -2150,7 +2150,7 @@ unsigned int get_random_int(void)
batch = &get_cpu_var(batched_entropy_int);
if (batch->position % ARRAY_SIZE(batch->entropy_int) == 0) {
- extract_crng((__u32 *)batch->entropy_int);
+ extract_crng((u8 *)batch->entropy_int);
batch->position = 0;
}
ret = batch->entropy_int[batch->position++];
diff --git a/include/crypto/chacha20.h b/include/crypto/chacha20.h
index 254298b..01543a9 100644
--- a/include/crypto/chacha20.h
+++ b/include/crypto/chacha20.h
@@ -11,13 +11,12 @@
#define CHACHA20_IV_SIZE 16
#define CHACHA20_KEY_SIZE 32
#define CHACHA20_BLOCK_SIZE 64
-#define CHACHA20_BLOCK_WORDS (CHACHA20_BLOCK_SIZE / sizeof(u32))
struct chacha20_ctx {
u32 key[8];
};
-void chacha20_block(u32 *state, u32 *stream);
+void chacha20_block(u32 *state, u8 *stream);
void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv);
int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key,
unsigned int keysize);
diff --git a/lib/chacha20.c b/lib/chacha20.c
index 29d3801..d907fec 100644
--- a/lib/chacha20.c
+++ b/lib/chacha20.c
@@ -16,63 +16,58 @@
#include <asm/unaligned.h>
#include <crypto/chacha20.h>
-static inline u32 rotl32(u32 v, u8 n)
+void chacha20_block(u32 *state, u8 *stream)
{
- return (v << n) | (v >> (sizeof(v) * 8 - n));
-}
-
-void chacha20_block(u32 *state, u32 *stream)
-{
- u32 x[16], *out = stream;
+ u32 x[16];
int i;
for (i = 0; i < ARRAY_SIZE(x); i++)
x[i] = state[i];
for (i = 0; i < 20; i += 2) {
- x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 16);
- x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 16);
- x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 16);
- x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 16);
+ x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16);
+ x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16);
+ x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16);
+ x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16);
- x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 12);
- x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 12);
- x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 12);
- x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 12);
+ x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12);
+ x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12);
+ x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12);
+ x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12);
- x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 8);
- x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 8);
- x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 8);
- x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 8);
+ x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8);
+ x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8);
+ x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8);
+ x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8);
- x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 7);
- x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 7);
- x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 7);
- x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 7);
+ x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7);
+ x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7);
+ x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7);
+ x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7);
- x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 16);
- x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 16);
- x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 16);
- x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 16);
+ x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16);
+ x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16);
+ x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16);
+ x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16);
- x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 12);
- x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 12);
- x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 12);
- x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 12);
+ x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12);
+ x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12);
+ x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12);
+ x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12);
- x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 8);
- x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 8);
- x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 8);
- x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 8);
+ x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8);
+ x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8);
+ x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8);
+ x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8);
- x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 7);
- x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 7);
- x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 7);
- x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 7);
+ x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7);
+ x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7);
+ x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7);
+ x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7);
}
for (i = 0; i < ARRAY_SIZE(x); i++)
- out[i] = cpu_to_le32(x[i] + state[i]);
+ put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]);
state[12]++;
}
