diff mbox

[RFC] mlx4_ib: Make steering support independent of MLX4_BMME_FLAG_TYPE_2_WIN

Message ID 2a929a48-559e-41ad-c42e-a722801c11d0@sandisk.com (mailing list archive)
State RFC
Headers show

Commit Message

Bart Van Assche June 2, 2016, 12:07 a.m. UTC
Hello,

Can anyone who is familiar with the mlx4 driver tell me whether or not
the patch below makes sense? I ran into this code by analyzing the mlx4
source code with smatch.

Thanks,

Bart.

---
 drivers/infiniband/hw/mlx4/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

Comments

Or Gerlitz June 2, 2016, 5:51 a.m. UTC | #1
On Thu, Jun 2, 2016 at 3:07 AM, Bart Van Assche
<bart.vanassche@sandisk.com> wrote:
> Hello,
>
> Can anyone who is familiar with the mlx4 driver

Hi Bart,

We have set entries in the maintainers for file for both mlx4/5 core
and IB drivers, as you were asking
people to look there for srp patches... use the same practice (here
it's Yishai H.)
--
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
Leon Romanovsky June 2, 2016, 8:18 a.m. UTC | #2
On Wed, Jun 01, 2016 at 05:07:17PM -0700, Bart Van Assche wrote:
> Hello,
> 
> Can anyone who is familiar with the mlx4 driver tell me whether or not
> the patch below makes sense? I ran into this code by analyzing the mlx4
> source code with smatch.

Hi Bart,
Thank you bringing it to our attention. I had a fast chit-chat with
Matan who was the last person who touched that area. It looks like an
unharmful issue with the code, because we had support for memory window
feature literally forever.

Thanks.

> 
> Thanks,
> 
> Bart.
> 
> ---
>  drivers/infiniband/hw/mlx4/main.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
> index b01ef6e..db7d0bc 100644
> --- a/drivers/infiniband/hw/mlx4/main.c
> +++ b/drivers/infiniband/hw/mlx4/main.c
> @@ -505,9 +505,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
>  			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
>  		else
>  			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
> +	}
>  	if (dev->steering_support ==  MLX4_STEERING_MODE_DEVICE_MANAGED)
>  		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
> -	}
>  
>  	props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
>  
> -- 
> 2.8.3
>
Sagi Grimberg June 2, 2016, 11:59 a.m. UTC | #3
Nice catch Bart, looks good to me,

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
--
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
Leon Romanovsky June 3, 2016, 1:10 p.m. UTC | #4
On Thu, Jun 02, 2016 at 11:18:19AM +0300, Leon Romanovsky wrote:
> On Wed, Jun 01, 2016 at 05:07:17PM -0700, Bart Van Assche wrote:
> > Hello,
> > 
> > Can anyone who is familiar with the mlx4 driver tell me whether or not
> > the patch below makes sense? I ran into this code by analyzing the mlx4
> > source code with smatch.
> 
> Hi Bart,
> Thank you bringing it to our attention. I had a fast chit-chat with
> Matan who was the last person who touched that area. It looks like an
> unharmful issue with the code, because we had support for memory window
> feature literally forever.

hi Bart,
Do you want us to handle this fix (improve title, fill commit message)?
Or maybe you prefer to submit it by yourself?

Thanks.

> 
> Thanks.
> 
> > 
> > Thanks,
> > 
> > Bart.
> > 
> > ---
> >  drivers/infiniband/hw/mlx4/main.c | 2 +-
> >  1 file changed, 1 insertion(+), 1 deletion(-)
> > 
> > diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
> > index b01ef6e..db7d0bc 100644
> > --- a/drivers/infiniband/hw/mlx4/main.c
> > +++ b/drivers/infiniband/hw/mlx4/main.c
> > @@ -505,9 +505,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
> >  			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
> >  		else
> >  			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
> > +	}
> >  	if (dev->steering_support ==  MLX4_STEERING_MODE_DEVICE_MANAGED)
> >  		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
> > -	}
> >  
> >  	props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
> >  
> > -- 
> > 2.8.3
> >
diff mbox

Patch

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index b01ef6e..db7d0bc 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -505,9 +505,9 @@  static int mlx4_ib_query_device(struct ib_device *ibdev,
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
 		else
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
+	}
 	if (dev->steering_support ==  MLX4_STEERING_MODE_DEVICE_MANAGED)
 		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
-	}
 
 	props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;