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

Ani Sinha posted 1 patch 1 year, 10 months ago
hw/acpi/erst.c | 3 +++
1 file changed, 3 insertions(+)
[PATCH] acpi/erst: fix fallthrough code upon validation failure
Posted by Ani Sinha 1 year, 10 months ago
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
Re: [PATCH] acpi/erst: fix fallthrough code upon validation failure
Posted by Eric DeVolder 1 year, 10 months ago

On 5/13/22 09:10, Ani Sinha 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.maydell@linaro.org>
> CC: Eric DeVolder <eric.devolder@oracle.com>
> Signed-off-by: Ani Sinha <ani@anisinha.ca>

Reviewed-by: Eric DeVolder <eric.devolder@oracle.com>

My apologies, I've been away for the past week.
Thank you for taking the time to correct this issue!
eric

> ---
>   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 */
>
Re: [PATCH] acpi/erst: fix fallthrough code upon validation failure
Posted by Ani Sinha 1 year, 9 months ago
On Thu, May 19, 2022 at 6:35 PM Eric DeVolder <eric.devolder@oracle.com> wrote:
>
>
>
> On 5/13/22 09:10, Ani Sinha 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.maydell@linaro.org>
> > CC: Eric DeVolder <eric.devolder@oracle.com>
> > Signed-off-by: Ani Sinha <ani@anisinha.ca>
>
> Reviewed-by: Eric DeVolder <eric.devolder@oracle.com>

Michael:
Did you forget to queue this for your latest pull request?


>
> My apologies, I've been away for the past week.
> Thank you for taking the time to correct this issue!
> eric
>
> > ---
> >   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 */
> >
Re: [PATCH] acpi/erst: fix fallthrough code upon validation failure
Posted by Michael S. Tsirkin 1 year, 9 months ago
On Fri, Jun 10, 2022 at 01:48:57PM +0530, Ani Sinha wrote:
> On Thu, May 19, 2022 at 6:35 PM Eric DeVolder <eric.devolder@oracle.com> wrote:
> >
> >
> >
> > On 5/13/22 09:10, Ani Sinha 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.maydell@linaro.org>
> > > CC: Eric DeVolder <eric.devolder@oracle.com>
> > > Signed-off-by: Ani Sinha <ani@anisinha.ca>
> >
> > Reviewed-by: Eric DeVolder <eric.devolder@oracle.com>
> 
> Michael:
> Did you forget to queue this for your latest pull request?
> 

I did, thanks for the reminder!

> >
> > My apologies, I've been away for the past week.
> > Thank you for taking the time to correct this issue!
> > eric
> >
> > > ---
> > >   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 */
> > >
Re: [PATCH] acpi/erst: fix fallthrough code upon validation failure
Posted by Igor Mammedov 1 year, 10 months ago
On Fri, 13 May 2022 19:40:05 +0530
Ani Sinha <ani@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.maydell@linaro.org>
> CC: Eric DeVolder <eric.devolder@oracle.com>
> Signed-off-by: Ani Sinha <ani@anisinha.ca>

Reviewed-by: Igor Mammedov <imammedo@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 */