diff mbox series

[v2] crypto: x86/polyval - Fix crashes when keys are not 16-byte aligned

Message ID 20221018215623.866014-1-nhuck@google.com (mailing list archive)
State Superseded
Delegated to: Herbert Xu
Headers show
Series [v2] crypto: x86/polyval - Fix crashes when keys are not 16-byte aligned | expand

Commit Message

Nathan Huckleberry Oct. 18, 2022, 9:56 p.m. UTC
crypto_tfm::__crt_ctx is not guaranteed to be 16-byte aligned on x86-64.
This causes crashes due to movaps instructions in clmul_polyval_update.

Add logic to align polyval_tfm_ctx to 16 bytes if required.

Fixes: 34f7f6c30112 ("crypto: x86/polyval - Add PCLMULQDQ accelerated implementation of POLYVAL")
Reported-by: Bruno Goncalves <bgoncalv@redhat.com>
Signed-off-by: Nathan Huckleberry <nhuck@google.com>
---
 arch/x86/crypto/polyval-clmulni_glue.c | 29 ++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

Comments

Eric Biggers Oct. 18, 2022, 10:39 p.m. UTC | #1
On Tue, Oct 18, 2022 at 02:56:23PM -0700, Nathan Huckleberry wrote:
> -static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
> +static inline struct polyval_tfm_ctx *polyval_tfm_ctx(const void *raw_ctx)
> +{
> +	unsigned long addr = (unsigned long)raw_ctx;
> +	unsigned long align = POLYVAL_ALIGN;
> +
> +	if (align <= crypto_tfm_ctx_alignment())
> +		align = 1;
> +	return (struct polyval_tfm_ctx *)ALIGN(addr, align);
> +}

This could just use PTR_ALIGN.  Also, checking for POLYVAL_ALIGN <=
crypto_tfm_ctx_alignment() isn't necessary.

> +
> +static void internal_polyval_update(const void *raw_keys,
>  	const u8 *in, size_t nblocks, u8 *accumulator)
>  {
> +	const struct polyval_tfm_ctx *keys = polyval_tfm_ctx(raw_keys);

This is being passed a struct polyval_tfm_ctx.  There's no need to cast it back
to a void pointer and align it again redundantly.

>  	if (likely(crypto_simd_usable())) {
>  		kernel_fpu_begin();
>  		clmul_polyval_update(keys, in, nblocks, accumulator);
> @@ -102,7 +117,8 @@ static int polyval_x86_update(struct shash_desc *desc,
>  			 const u8 *src, unsigned int srclen)
>  {
>  	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
> -	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
> +	const struct polyval_tfm_ctx *tctx =
> +	    polyval_tfm_ctx(crypto_shash_ctx(desc->tfm));
>  	u8 *pos;
>  	unsigned int nblocks;
>  	unsigned int n;

It would make more sense to have the polyval_tfm_ctx() function take in the
struct crypto_shash.

How about using the following:

static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm)
{
        return PTR_ALIGN(crypto_shash_ctx(tfm), POLYVAL_ALIGN);
}

- Eric
diff mbox series

Patch

diff --git a/arch/x86/crypto/polyval-clmulni_glue.c b/arch/x86/crypto/polyval-clmulni_glue.c
index b7664d018851..79ad497c32b5 100644
--- a/arch/x86/crypto/polyval-clmulni_glue.c
+++ b/arch/x86/crypto/polyval-clmulni_glue.c
@@ -27,13 +27,17 @@ 
 #include <asm/cpu_device_id.h>
 #include <asm/simd.h>
 
+#define POLYVAL_ALIGN	16
+#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN)
+#define POLYVAL_ALIGN_EXTRA ((POLYVAL_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
+#define POLYVAL_CTX_SIZE (sizeof(struct polyval_tfm_ctx) + POLYVAL_ALIGN_EXTRA)
 #define NUM_KEY_POWERS	8
 
 struct polyval_tfm_ctx {
 	/*
 	 * These powers must be in the order h^8, ..., h^1.
 	 */
-	u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE];
+	u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE] POLYVAL_ALIGN_ATTR;
 };
 
 struct polyval_desc_ctx {
@@ -45,9 +49,20 @@  asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
 	const u8 *in, size_t nblocks, u8 *accumulator);
 asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2);
 
-static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
+static inline struct polyval_tfm_ctx *polyval_tfm_ctx(const void *raw_ctx)
+{
+	unsigned long addr = (unsigned long)raw_ctx;
+	unsigned long align = POLYVAL_ALIGN;
+
+	if (align <= crypto_tfm_ctx_alignment())
+		align = 1;
+	return (struct polyval_tfm_ctx *)ALIGN(addr, align);
+}
+
+static void internal_polyval_update(const void *raw_keys,
 	const u8 *in, size_t nblocks, u8 *accumulator)
 {
+	const struct polyval_tfm_ctx *keys = polyval_tfm_ctx(raw_keys);
 	if (likely(crypto_simd_usable())) {
 		kernel_fpu_begin();
 		clmul_polyval_update(keys, in, nblocks, accumulator);
@@ -72,7 +87,7 @@  static void internal_polyval_mul(u8 *op1, const u8 *op2)
 static int polyval_x86_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
-	struct polyval_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+	struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(crypto_shash_ctx(tfm));
 	int i;
 
 	if (keylen != POLYVAL_BLOCK_SIZE)
@@ -102,7 +117,8 @@  static int polyval_x86_update(struct shash_desc *desc,
 			 const u8 *src, unsigned int srclen)
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
-	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	const struct polyval_tfm_ctx *tctx =
+	    polyval_tfm_ctx(crypto_shash_ctx(desc->tfm));
 	u8 *pos;
 	unsigned int nblocks;
 	unsigned int n;
@@ -143,7 +159,8 @@  static int polyval_x86_update(struct shash_desc *desc,
 static int polyval_x86_final(struct shash_desc *desc, u8 *dst)
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
-	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	const struct polyval_tfm_ctx *tctx =
+	    polyval_tfm_ctx(crypto_shash_ctx(desc->tfm));
 
 	if (dctx->bytes) {
 		internal_polyval_mul(dctx->buffer,
@@ -167,7 +184,7 @@  static struct shash_alg polyval_alg = {
 		.cra_driver_name	= "polyval-clmulni",
 		.cra_priority		= 200,
 		.cra_blocksize		= POLYVAL_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct polyval_tfm_ctx),
+		.cra_ctxsize		= POLYVAL_CTX_SIZE,
 		.cra_module		= THIS_MODULE,
 	},
 };