On Fri, 13 May 2022 19:40:05 +0530
Ani Sinha <a...@anisinha.ca> wrote:
> At any step when any validation fail in check_erst_backend_storage(), there is
> no need to continue further through other validation checks. Further, by
> continuing even when record_size is 0, we run the risk of triggering a divide
> by zero error if we continued with other validation checks. Hence, we should
> simply return from this function upon validation failure.
>
> CC: Peter Maydell <peter.mayd...@linaro.org>
> CC: Eric DeVolder <eric.devol...@oracle.com>
> Signed-off-by: Ani Sinha <a...@anisinha.ca>
Reviewed-by: Igor Mammedov <imamm...@redhat.com>
> ---
> hw/acpi/erst.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/hw/acpi/erst.c b/hw/acpi/erst.c
> index de509c2b48..df856b2669 100644
> --- a/hw/acpi/erst.c
> +++ b/hw/acpi/erst.c
> @@ -440,6 +440,7 @@ static void check_erst_backend_storage(ERSTDeviceState
> *s, Error **errp)
> (record_size >= 4096) /* PAGE_SIZE */
> )) {
> error_setg(errp, "ERST record_size %u is invalid", record_size);
> + return;
> }
>
> /* Validity check header */
> @@ -450,6 +451,7 @@ static void check_erst_backend_storage(ERSTDeviceState
> *s, Error **errp)
> (le16_to_cpu(header->reserved) == 0)
> )) {
> error_setg(errp, "ERST backend storage header is invalid");
> + return;
> }
>
> /* Check storage_size against record_size */
> @@ -457,6 +459,7 @@ static void check_erst_backend_storage(ERSTDeviceState
> *s, Error **errp)
> (record_size > s->storage_size)) {
> error_setg(errp, "ACPI ERST requires storage size be multiple of "
> "record size (%uKiB)", record_size);
> + return;
> }
>
> /* Compute offset of first and last record storage slot */
