From: Ani Sinha <a...@anisinha.ca>
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>
Message-Id: <20220513141005.1929422-1-...@anisinha.ca>
Reviewed-by: Michael S. Tsirkin <m...@redhat.com>
Signed-off-by: Michael S. Tsirkin <m...@redhat.com>
Reviewed-by: Igor Mammedov <imamm...@redhat.com>
Reviewed-by: Eric DeVolder <eric.devol...@oracle.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 */
--
MST
