[PATCH 4.9 026/264] crypto: chacha20 - Fix keystream alignment for chacha20_block()

From: Greg Kroah-Hartman
Date: Thu Jun 23 2022 - 12:47:17 EST


From: Eric Biggers <ebiggers@xxxxxxxxxx>

commit 9f480faec58cd6197a007ea1dcac6b7c3daf1139 upstream.

When chacha20_block() outputs the keystream block, it uses 'u32' stores
directly. However, the callers (crypto/chacha20_generic.c and
drivers/char/random.c) declare the keystream buffer as a 'u8' array,
which is not guaranteed to have the needed alignment.

Fix it by having both callers declare the keystream as a 'u32' array.
For now this is preferable to switching over to the unaligned access
macros because chacha20_block() is only being used in cases where we can
easily control the alignment (stack buffers).

Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx>
Signed-off-by: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Jason A. Donenfeld <Jason@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
crypto/chacha20_generic.c | 6 +++---
drivers/char/random.c | 24 ++++++++++++------------
include/crypto/chacha20.h | 3 ++-
lib/chacha20.c | 2 +-
4 files changed, 18 insertions(+), 17 deletions(-)

--- a/crypto/chacha20_generic.c
+++ b/crypto/chacha20_generic.c
@@ -23,20 +23,20 @@ static inline u32 le32_to_cpuvp(const vo
static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
unsigned int bytes)
{
- u8 stream[CHACHA20_BLOCK_SIZE];
+ u32 stream[CHACHA20_BLOCK_WORDS];

if (dst != src)
memcpy(dst, src, bytes);

while (bytes >= CHACHA20_BLOCK_SIZE) {
chacha20_block(state, stream);
- crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE);
+ crypto_xor(dst, (const u8 *)stream, CHACHA20_BLOCK_SIZE);
bytes -= CHACHA20_BLOCK_SIZE;
dst += CHACHA20_BLOCK_SIZE;
}
if (bytes) {
chacha20_block(state, stream);
- crypto_xor(dst, stream, bytes);
+ crypto_xor(dst, (const u8 *)stream, bytes);
}
}

--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -434,9 +434,9 @@ 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,
- __u8 out[CHACHA20_BLOCK_SIZE]);
+ __u32 out[CHACHA20_BLOCK_WORDS]);
static void _crng_backtrack_protect(struct crng_state *crng,
- __u8 tmp[CHACHA20_BLOCK_SIZE], int used);
+ __u32 tmp[CHACHA20_BLOCK_WORDS], int used);
static void process_random_ready_list(void);
static void _get_random_bytes(void *buf, int nbytes);

@@ -981,7 +981,7 @@ static void crng_reseed(struct crng_stat
unsigned long flags;
int i, num;
union {
- __u8 block[CHACHA20_BLOCK_SIZE];
+ __u32 block[CHACHA20_BLOCK_WORDS];
__u32 key[8];
} buf;

@@ -1029,7 +1029,7 @@ static void crng_reseed(struct crng_stat
}

static void _extract_crng(struct crng_state *crng,
- __u8 out[CHACHA20_BLOCK_SIZE])
+ __u32 out[CHACHA20_BLOCK_WORDS])
{
unsigned long v, flags, init_time;

@@ -1049,7 +1049,7 @@ static void _extract_crng(struct crng_st
spin_unlock_irqrestore(&crng->lock, flags);
}

-static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
+static void extract_crng(__u32 out[CHACHA20_BLOCK_WORDS])
{
_extract_crng(select_crng(), out);
}
@@ -1059,7 +1059,7 @@ static void extract_crng(__u8 out[CHACHA
* enough) to mutate the CRNG key to provide backtracking protection.
*/
static void _crng_backtrack_protect(struct crng_state *crng,
- __u8 tmp[CHACHA20_BLOCK_SIZE], int used)
+ __u32 tmp[CHACHA20_BLOCK_WORDS], int used)
{
unsigned long flags;
__u32 *s, *d;
@@ -1071,14 +1071,14 @@ static void _crng_backtrack_protect(stru
used = 0;
}
spin_lock_irqsave(&crng->lock, flags);
- s = (__u32 *) &tmp[used];
+ s = &tmp[used / sizeof(__u32)];
d = &crng->state[4];
for (i=0; i < 8; i++)
*d++ ^= *s++;
spin_unlock_irqrestore(&crng->lock, flags);
}

-static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used)
+static void crng_backtrack_protect(__u32 tmp[CHACHA20_BLOCK_WORDS], int used)
{
_crng_backtrack_protect(select_crng(), tmp, used);
}
@@ -1086,7 +1086,7 @@ static void crng_backtrack_protect(__u8
static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
{
ssize_t ret = 0, i = CHACHA20_BLOCK_SIZE;
- __u8 tmp[CHACHA20_BLOCK_SIZE];
+ __u32 tmp[CHACHA20_BLOCK_WORDS];
int large_request = (nbytes > 256);

while (nbytes) {
@@ -1672,7 +1672,7 @@ static void _warn_unseeded_randomness(co
*/
static void _get_random_bytes(void *buf, int nbytes)
{
- __u8 tmp[CHACHA20_BLOCK_SIZE];
+ __u32 tmp[CHACHA20_BLOCK_WORDS];

trace_get_random_bytes(nbytes, _RET_IP_);

@@ -2273,7 +2273,7 @@ u64 get_random_u64(void)
batch = raw_cpu_ptr(&batched_entropy_u64);
spin_lock_irqsave(&batch->batch_lock, flags);
if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
- extract_crng((u8 *)batch->entropy_u64);
+ extract_crng((__u32 *)batch->entropy_u64);
batch->position = 0;
}
ret = batch->entropy_u64[batch->position++];
@@ -2297,7 +2297,7 @@ u32 get_random_u32(void)
batch = raw_cpu_ptr(&batched_entropy_u32);
spin_lock_irqsave(&batch->batch_lock, flags);
if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
- extract_crng((u8 *)batch->entropy_u32);
+ extract_crng(batch->entropy_u32);
batch->position = 0;
}
ret = batch->entropy_u32[batch->position++];
--- a/include/crypto/chacha20.h
+++ b/include/crypto/chacha20.h
@@ -11,12 +11,13 @@
#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, void *stream);
+void chacha20_block(u32 *state, u32 *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);
--- a/lib/chacha20.c
+++ b/lib/chacha20.c
@@ -21,7 +21,7 @@ static inline u32 rotl32(u32 v, u8 n)
return (v << n) | (v >> (sizeof(v) * 8 - n));
}

-extern void chacha20_block(u32 *state, void *stream)
+void chacha20_block(u32 *state, u32 *stream)
{
u32 x[16], *out = stream;
int i;