Ian Abbott <[email protected]> writes:

> On 08/07/2025 13:37, Edward Adam Davis wrote:
>> The irq number 0x2166 passed by the reproducer is too large and is not
>> within the supported range [2-7, 10-12, 14, or 15], which triggers the oob.
>> Fixes: ad7a370c8be4 (“staging: comedi: aio_iiro_16: add command
>> support for change of state detection”)
>> Reported-by: [email protected]
>> Closes: <https://syzkaller.appspot.com/bug?extid=f1bb7e4ea47ea12b535c>
>> Signed-off-by: Edward Adam Davis <[email protected]>
>> —
>>   drivers/comedi/drivers/aio_iiro_16.c | 3 ++-
>>   1 file changed, 2 insertions(+), 1 deletion(-)
>> diff –git a/drivers/comedi/drivers/aio_iiro_16.c
>> b/drivers/comedi/drivers/aio_iiro_16.c
>> index b00fab0b89d4..e43730f00c8b 100644
>> — a/drivers/comedi/drivers/aio_iiro_16.c
>> +++ b/drivers/comedi/drivers/aio_iiro_16.c
>> @@ -177,7 +177,8 @@ static int aio_iiro_16_attach(struct comedi_device *dev,
>>       * Digital input change of state interrupts are optionally supported
>>       * using IRQ 2-7, 10-12, 14, or 15.
>>       */
>> -    if ((1 << it->options[1]) & 0xdcfc) {
>> +    if (it->options[1] > 1 && it->options[1] < 16 &&
>> +        (1 << it->options[1]) & 0xdcfc) {
>>              ret = request_irq(it->options[1], aio_iiro_16_cos, 0,
>>                                dev->board_name, dev);
>>              if (ret == 0)
>
> The patch is fine apart from the misspelling of “invalid” in the subject
> line, but I’d already submitted a patch for this before syzbot detected
> it:
>
> <https://lore.kernel.org/lkml/[email protected]/>

#syz fix: comedi: aio_iiro_16: Fix bit shift out of bounds

Reply via email to