RE: [PATCH rdma-core 1/2] Extend verbs_device_ops to get vendor attr as part of alloc_context

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



>Subject: [PATCH rdma-core 1/2] Extend verbs_device_ops to get vendor attr as
>part of alloc_context
>
>Extend verbs_device_ops to get vendor attr as part of alloc_context, this
>functionality is used in downstream patch by mlx5 driver to allocate a DEVX
>context.
>

[....]


>diff --git a/providers/i40iw/i40iw_umain.c b/providers/i40iw/i40iw_umain.c index
>467709f..d4aa640 100644
>--- a/providers/i40iw/i40iw_umain.c
>+++ b/providers/i40iw/i40iw_umain.c
>@@ -127,13 +127,17 @@ static const struct verbs_context_ops i40iw_uctx_ops
>= {
>  */
>
> static struct verbs_context *i40iw_ualloc_context(struct ibv_device *ibdev,
>-						  int cmd_fd)
>+						  int cmd_fd,
>+						  void *vendor_attr)
> {
> 	struct ibv_pd *ibv_pd;
> 	struct i40iw_uvcontext *iwvctx;
> 	struct i40iw_get_context cmd;
> 	struct i40iw_get_context_resp resp;
>
>+	if (vendor_attr)
>+		return NULL;
>+
How do non-mlx providers take advantage of passing vendor attrs in the future?

Also, can you update the function header comment section for vendor attr?

Shiraz




[Index of Archives]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Photo]     [Yosemite News]     [Yosemite Photos]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux