BACKPORT: crypto: chacha20 - Fix keystream alignment for chacha20_block()

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@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

(cherry picked from commit 9f480faec58cd6197a007ea1dcac6b7c3daf1139)

Conflicts:
	drivers/char/random.c

Bug: 112008522
Test: As series, see Ic61c13b53facfd2173065be715a7ee5f3af8760b
Change-Id: I7557b2ca2ace0e19e97e997659857b3fa7a2b540
Signed-off-by: Eric Biggers <ebiggers@google.com>

4 files changed, 18 insertions, 17 deletions

diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
index 8c8befb..1a48d3a 100644
--- a/crypto/chacha20_generic.c
+++ b/crypto/chacha20_generic.c
@@ -19,20 +19,20 @@
 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);
 	}
 }
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 81b65d0..4fc600d 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,
-			  __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 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 {
-		__u8	block[CHACHA20_BLOCK_SIZE];
+		__u32	block[CHACHA20_BLOCK_WORDS];
 		__u32	key[8];
 	} buf;
 
@@ -926,7 +926,7 @@ static inline void crng_wait_ready(void)
 }
 
 static void _extract_crng(struct crng_state *crng,
-			  __u8 out[CHACHA20_BLOCK_SIZE])
+			  __u32 out[CHACHA20_BLOCK_WORDS])
 {
 	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(__u8 out[CHACHA20_BLOCK_SIZE])
+static void extract_crng(__u32 out[CHACHA20_BLOCK_WORDS])
 {
 	struct crng_state *crng = NULL;
 
@@ -961,7 +961,7 @@ static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
  * 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;
@@ -973,14 +973,14 @@ static void _crng_backtrack_protect(struct crng_state *crng,
 		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)
 {
 	struct crng_state *crng = NULL;
 
@@ -996,7 +996,7 @@ static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used)
 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) {
@@ -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)
 {
-	__u8 tmp[CHACHA20_BLOCK_SIZE];
+	__u32 tmp[CHACHA20_BLOCK_WORDS];
 
 #if DEBUG_RANDOM_BOOT > 0
 	if (!crng_ready())
@@ -2132,7 +2132,7 @@ unsigned long get_random_long(void)
 
 	batch = &get_cpu_var(batched_entropy_long);
 	if (batch->position % ARRAY_SIZE(batch->entropy_long) == 0) {
-		extract_crng((u8 *)batch->entropy_long);
+		extract_crng((__u32 *)batch->entropy_long);
 		batch->position = 0;
 	}
 	ret = batch->entropy_long[batch->position++];
@@ -2158,7 +2158,7 @@ unsigned int get_random_int(void)
 
 	batch = &get_cpu_var(batched_entropy_int);
 	if (batch->position % ARRAY_SIZE(batch->entropy_int) == 0) {
-		extract_crng((u8 *)batch->entropy_int);
+		extract_crng((__u32 *)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 20d20f68..254298b 100644
--- 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);
diff --git a/lib/chacha20.c b/lib/chacha20.c
index 250ceed..29d3801 100644
--- 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;