On Tue, Nov 28, 2023 at 06:37:32PM +0100, Damian Muszynski wrote:
> The input argument `sla_in` is a pointer to a structure that contains
> the parameters of the SLA which is being added or updated.
> If this pointer is NULL, the function should return an error as
> the data required for the algorithm is not available.
> By mistake, the logic jumps to the error path which dereferences
> the pointer.
>
> This results in a warnings reported by the static analyzer Smatch when
> executed without a database:
>
> drivers/crypto/intel/qat/qat_common/adf_rl.c:871 add_update_sla()
> error: we previously assumed 'sla_in' could be null (see line 812)
>
> This issue was not found in internal testing as the pointer cannot be
> NULL. The function add_update_sla() is only called (indirectly) by
> the rate limiting sysfs interface implementation in adf_sysfs_rl.c
> which ensures that the data structure is allocated and valid. This is
> also proven by the fact that Smatch executed with a database does not
> report such error.
>
> Fix it by returning with error if the pointer `sla_in` is NULL.
>
> Fixes: d9fb8408376e ("crypto: qat - add rate limiting feature to qat_4xxx")
> Reported-by: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
> Signed-off-by: Damian Muszynski <damian.muszynski@xxxxxxxxx>
> Reviewed-by: Giovanni Cabiddu <giovanni.cabiddu@xxxxxxxxx>
> ---
> drivers/crypto/intel/qat/qat_common/adf_rl.c | 3 +--
> 1 file changed, 1 insertion(+), 2 deletions(-)
Patch applied. Thanks.
--
Email: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
