@@ -39,26 +39,13 @@ static int crct10dif_update(struct shash_desc *desc, const u8 *data,
unsigned int length)
{
u16 *crc = shash_desc_ctx(desc);
- unsigned int l;
- if (unlikely((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE)) {
- l = min_t(u32, length, CRC_T10DIF_PMULL_CHUNK_SIZE -
- ((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE));
-
- *crc = crc_t10dif_generic(*crc, data, l);
-
- length -= l;
- data += l;
- }
-
- if (length > 0) {
- if (may_use_simd()) {
- kernel_neon_begin();
- *crc = crc_t10dif_pmull(*crc, data, length);
- kernel_neon_end();
- } else {
- *crc = crc_t10dif_generic(*crc, data, length);
- }
+ if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+ kernel_neon_begin();
+ *crc = crc_t10dif_pmull(*crc, data, length);
+ kernel_neon_end();
+ } else {
+ *crc = crc_t10dif_generic(*crc, data, length);
}
return 0;
The SIMD routine ported from x86 used to have a special code path for inputs < 16 bytes, which got lost somewhere along the way. Instead, the current glue code aligns the input pointer to 16 bytes, which is not really necessary on this architecture (although it could be beneficial to performance to expose aligned data to the the NEON routine), but this could result in inputs of less than 16 bytes to be passed in. This not only fails the new extended tests that Eric has implemented, it also results in the code reading past the end of the input, which could potentially result in crashes when dealing with less than 16 bytes of input at the end of a page which is followed by an unmapped page. So update the glue code to only invoke the NEON routine if the input is more than 16 bytes. Reported-by: Eric Biggers <ebiggers@kernel.org> Fixes: 6ef5737f3931 ("crypto: arm64/crct10dif - port x86 SSE implementation to arm64") Cc: <stable@vger.kernel.org> # v4.10+ Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> --- arch/arm64/crypto/crct10dif-ce-glue.c | 25 +++++--------------- 1 file changed, 6 insertions(+), 19 deletions(-) -- 2.17.1