On 2022/1/11 12:12, Devesh Sharma wrote:
>
>> -----Original Message-----
>> From: Xiao Yang<yangx.jy@xxxxxxxxxxx>
>> Sent: Tuesday, January 11, 2022 7:54 AM
>> To: rpearsonhpe@xxxxxxxxx; leon@xxxxxxxxxx
>> Cc: linux-rdma@xxxxxxxxxxxxxxx; Xiao Yang<yangx.jy@xxxxxxxxxxx>
>> Subject: [PATCH rdma-core RESEND] providers/rxe: Replace '%' with '&' in
>> check_qp_queue_full()
>>
>> The expression "cons == ((qp->cur_index + 1) % q->index_mask)" mistakenly
>> assumes the queue is full when the number of entires is equal to "maximum
>> - 1"
>> (maximum is correct).
>>
>> For example:
>> If cons and qp->cur_index are 0 and q->index_mask is 1,
>> check_qp_queue_full() reports ENOSPC.
>>
>> Fixes: 1a894ca10105 ("Providers/rxe: Implement ibv_create_qp_ex verb")
>> Signed-off-by: Xiao Yang<yangx.jy@xxxxxxxxxxx>
>> ---
>> providers/rxe/rxe_queue.h | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/providers/rxe/rxe_queue.h b/providers/rxe/rxe_queue.h index
>> 6de8140c..708e76ac 100644
>> --- a/providers/rxe/rxe_queue.h
>> +++ b/providers/rxe/rxe_queue.h
>> @@ -205,7 +205,7 @@ static inline int check_qp_queue_full(struct rxe_qp
>> *qp)
>> if (qp->err)
>> goto err;
>>
>> - if (cons == ((qp->cur_index + 1) % q->index_mask))
>> + if (cons == ((qp->cur_index + 1)& q->index_mask))
> Are you sure that index_mask would always be aligned with 2^X?
Hi Deves,
I think it is. index_mask is alwasy set to 2^X -1 in kernel:
----------------------------------------------------------------
struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, int *num_elem,
unsigned int elem_size, enum queue_type type)
{
...
num_slots = *num_elem + 1;
num_slots = roundup_pow_of_two(num_slots);
q->index_mask = num_slots - 1;
...
}
----------------------------------------------------------------
Best Regards,
Xiao Yang
>> qp->err = ENOSPC;
>> err:
>> return qp->err;
>> --
>> 2.25.1
>>
>>
