Hi,
Le mardi 11 septembre 2018 à 20:05 -0700, Eric Biggers a écrit :
> From: Eric Biggers <ebiggers@xxxxxxxxxx>
>
> In commit 9f480faec58c ("crypto: chacha20 - Fix keystream alignment for
> chacha20_block()"), I had missed that chacha20_block() can be called
> directly on the buffer passed to get_random_bytes(), which can have any
> alignment. So, while my commit didn't break anything, it didn't fully
> solve the alignment problems.
>
> Revert my solution and just update chacha20_block() to use
> put_unaligned_le32(), so the output buffer need not be aligned.
> This is simpler, and on many CPUs it's the same speed.
>
> But, I kept the 'tmp' buffers in extract_crng_user() and
> _get_random_bytes() 4-byte aligned, since that alignment is actually
> needed for _crng_backtrack_protect() too.
>
> Reported-by: Stephan Müller <smueller@xxxxxxxxxx>
> Cc: Theodore Ts'o <tytso@xxxxxxx>
> Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx>
> ---
> crypto/chacha20_generic.c | 7 ++++---
> drivers/char/random.c | 24 ++++++++++++------------
> include/crypto/chacha20.h | 3 +--
> lib/chacha20.c | 6 +++---
> 4 files changed, 20 insertions(+), 20 deletions(-)
>
> diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
> index e451c3cb6a56..3ae96587caf9 100644
> --- a/crypto/chacha20_generic.c
> +++ b/crypto/chacha20_generic.c
> @@ -18,20 +18,21 @@
> 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 bf5f99fc36f1..d22d967c50f0 100644
> --- a/drivers/char/random.c
> +++ b/drivers/char/random.c
> @@ -1003,7 +1003,7 @@ 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;
> @@ -1015,14 +1015,14 @@ 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];
This introduces a alignment issue: tmp is not aligned for __u32, but is
dereferenced as such later.
> d = &crng->state[4];
> for (i=0; i < 8; i++)
> *d++ ^= *s++;
> spin_unlock_irqrestore(&crng->lock, flags);
> }
>
Regards.
--
Yann Droneaud
OPTEYA
