Re: [PATCH] IB/mlx5: avoid binding a new mpi unit to the same devices repeatedly

[Qing Huang <qing.huang@oracle.com>]

Hi Daniel,


On 7/23/2018 11:11 AM, Daniel Jurgens wrote:
>
> On 7/23/2018 10:36 AM, Qing Huang wrote:
>> Hi Daniel/Parav,
>>
>> Have you got a chance to review this patch? Thanks!
> Hi Qing, sorry for the delay, I just got back to the office today. I don't agree with the proposed fix, I provided an alternative suggestion below.
>>>> Or.
>>>>
>>>>> Reported-by: Gerald Gibson <gerald.gibson@oracle.com>
>>>>> Signed-off-by: Qing Huang <qing.huang@oracle.com>
>>>>> ---
>>>>>    drivers/infiniband/hw/mlx5/main.c | 3 ++-
>>>>>    1 file changed, 2 insertions(+), 1 deletion(-)
>>>>>
>>>>> diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
>>>>> index b3ba9a2..1ddd1d3 100644
>>>>> --- a/drivers/infiniband/hw/mlx5/main.c
>>>>> +++ b/drivers/infiniband/hw/mlx5/main.c
>>>>> @@ -6068,7 +6068,8 @@ static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev, u8 port_num)
>>>>>
>>>>>           mutex_lock(&mlx5_ib_multiport_mutex);
>>>>>           list_for_each_entry(dev, &mlx5_ib_dev_list, ib_dev_list) {
>>>>> -               if (dev->sys_image_guid == mpi->sys_image_guid)
>>>>> +               if (dev->sys_image_guid == mpi->sys_image_guid &&
>>>>> +                   !dev->port[mlx5_core_native_port_num(mdev) - 1].mp.mpi)
> You shouldn't check the mpi field that without holding the lock in the mp structure. Prefer you change the print from a warning in mlx5_ib_bind_slave_port to a debug message.
Thanks for the review. That works for us too. Will resend the patch.

Regards,
Qing

>
>>>>>                           bound = mlx5_ib_bind_slave_port(dev, mpi);
>>>>>
>>>>>                   if (bound) {
>>>>> -- 
>>>>> 2.9.3
>>>>>
>>>>> -- 
>>>>> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
>>>>> the body of a message to majordomo@vger.kernel.org
>>>>> More majordomo info at  http://vger.kernel.org/majordomo-info.html