[PATCH] acpi/erst: fix fallthrough code upon validation failure

[Ani Sinha]

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.maydell@linaro.org>
CC: Eric DeVolder <eric.devolder@oracle.com>
Signed-off-by: Ani Sinha <ani@anisinha.ca>
---
 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 */
-- 
2.25.1