ACK/cmnt: [X][E][CVE-2020-11608][SRU][PATCH 1/1] media: ov519: add missing endpoint sanity checks

Kleber Souza kleber.souza at canonical.com
Fri Apr 17 07:40:23 UTC 2020


Hi Sam,

We are not tracking disco/linux on the CVE matrix but we have some
derivatives, like oem-osp1 and gke-5.0, so it's definitely a benefit
applying this to Disco as well.


Thanks,
Kleber


On 17.04.20 09:18, Po-Hsu Lin wrote:
> BTW,
> I just found this can be cherry-picked into Disco as well,
> as we're not tracking Disco directly on our CVE matrix, should we add
> [D] here in this case?
> Perhaps the 5.0 variants could benefit from this?
> 
> Thanks.
> Sam
> 
> On Thu, Apr 16, 2020 at 7:56 PM Kleber Souza <kleber.souza at canonical.com> wrote:
>>
>> On 16.04.20 11:33, Kleber Souza wrote:
>>> On 16.04.20 10:50, Po-Hsu Lin wrote:
>>>> From: Johan Hovold <johan at kernel.org>
>>>>
>>>> CVE-2020-11608
>>>>
>>>> Make sure to check that we have at least one endpoint before accessing
>>>> the endpoint array to avoid dereferencing a NULL-pointer on stream
>>>> start.
>>>>
>>>> Note that these sanity checks are not redundant as the driver is mixing
>>>> looking up altsettings by index and by number, which need not coincide.
>>>>
>>>> Fixes: 1876bb923c98 ("V4L/DVB (12079): gspca_ov519: add support for the ov511 bridge")
>>>> Fixes: b282d87332f5 ("V4L/DVB (12080): gspca_ov519: Fix ov518+ with OV7620AE (Trust spacecam 320)")
>>>> Cc: stable <stable at vger.kernel.org>     # 2.6.31
>>>> Cc: Hans de Goede <hdegoede at redhat.com>
>>>> Signed-off-by: Johan Hovold <johan at kernel.org>
>>>> Signed-off-by: Hans Verkuil <hverkuil-cisco at xs4all.nl>
>>>> Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei at kernel.org>
>>>> (cherry picked from commit 998912346c0da53a6dbb71fab3a138586b596b30)
>>>> Signed-off-by: Po-Hsu Lin <po-hsu.lin at canonical.com>
>>>
>>> LGTM.
>>>
>>> Acked-by: Kleber Sacilotto de Souza <kleber.souza at canonical.com>
>>>
>>>
>>> The CVE matrix says this fix is needed for Xenial as well. Does it apply cleanly on X or
>>> does it need to be backported for it?
>>
>> Never mind, I failed miserably to notice the tag for Xenial...
>>
>>>
>>>> ---
>>>>  drivers/media/usb/gspca/ov519.c | 10 ++++++++++
>>>>  1 file changed, 10 insertions(+)
>>>>
>>>> diff --git a/drivers/media/usb/gspca/ov519.c b/drivers/media/usb/gspca/ov519.c
>>>> index c7aafdb..9a49b50 100644
>>>> --- a/drivers/media/usb/gspca/ov519.c
>>>> +++ b/drivers/media/usb/gspca/ov519.c
>>>> @@ -3507,6 +3507,11 @@ static void ov511_mode_init_regs(struct sd *sd)
>>>>              return;
>>>>      }
>>>>
>>>> +    if (alt->desc.bNumEndpoints < 1) {
>>>> +            sd->gspca_dev.usb_err = -ENODEV;
>>>> +            return;
>>>> +    }
>>>> +
>>>>      packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
>>>>      reg_w(sd, R51x_FIFO_PSIZE, packet_size >> 5);
>>>>
>>>> @@ -3632,6 +3637,11 @@ static void ov518_mode_init_regs(struct sd *sd)
>>>>              return;
>>>>      }
>>>>
>>>> +    if (alt->desc.bNumEndpoints < 1) {
>>>> +            sd->gspca_dev.usb_err = -ENODEV;
>>>> +            return;
>>>> +    }
>>>> +
>>>>      packet_size = le16_to_cpu(alt->endpoint[0].desc.wMaxPacketSize);
>>>>      ov518_reg_w32(sd, R51x_FIFO_PSIZE, packet_size & ~7, 2);
>>>>
>>>>
>>>
>>




More information about the kernel-team mailing list