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

diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
index bb4affbd591c379023a3d84963e30ce38b9804a6..e451c3cb6a56e863e8da71170b3e676de1b0cb16 100644 (file)
--- a/crypto/chacha20_generic.c
+++ b/crypto/chacha20_generic.c
@@ -18,20 +18,20 @@
 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 ea4dbfa3065747a0cd24754abc8e51e08403cbc1..f04cadb7c92d2a522ff979ed98a158b9599b468b 100644 (file)
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -433,9 +433,9 @@ 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);
 
@@ -911,7 +911,7 @@ 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;
 
@@ -958,7 +958,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 }
 
 static void _extract_crng(struct crng_state *crng,
-                         __u8 out[CHACHA20_BLOCK_SIZE])
+                         __u32 out[CHACHA20_BLOCK_WORDS])
 {
        unsigned long v, flags;
 
@@ -975,7 +975,7 @@ 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;
 
@@ -993,7 +993,7 @@ 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;
@@ -1005,14 +1005,14 @@ 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;
 
@@ -1028,7 +1028,7 @@ 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) {
@@ -1614,7 +1614,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
  */
 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_);
 
@@ -2224,7 +2224,7 @@ u64 get_random_u64(void)
        if (use_lock)
                read_lock_irqsave(&batched_entropy_reset_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++];
@@ -2254,7 +2254,7 @@ u32 get_random_u32(void)
        if (use_lock)
                read_lock_irqsave(&batched_entropy_reset_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++];

diff --git a/include/crypto/chacha20.h b/include/crypto/chacha20.h
index caaa470389e0ea0c5e29f446590822d2c7d82f06..b83d66073db0390d59d98f1ac12d9adbddc1afc3 100644 (file)
--- a/include/crypto/chacha20.h
+++ b/include/crypto/chacha20.h
@@ -13,12 +13,13 @@
 #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_skcipher *tfm, const u8 *key,
                           unsigned int keysize);

diff --git a/lib/chacha20.c b/lib/chacha20.c
index 250ceed9ec9a88b9efaedb24c3895b4feec3f7f0..29d3801dee24f5a3b1a6290a578d1ef5baf710c0 100644 (file)
--- 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;