On Fri, Jan 26, 2018 at 01:30:46PM -0800, Dennis Dalessandro wrote:
> From: Don Hiatt <don.hiatt@xxxxxxxxx>
>
> iWarp devices do not support the creation of address handles
> so return AH_ATTR_TYPE_UNDEFINED for all iWarp devices.
>
> While we are here reduce the size of port_num to u8 and add
> a comment.
>
> Fixes: 44c58487d51a ("IB/core: Define 'ib' and 'roce' rdma_ah_attr types")
> Reported-by: Parav Pandit <parav@xxxxxxxxxxxx>
> CC: Sean Hefty <sean.hefty@xxxxxxxxx>
> Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>
> Reviewed-by: Shiraz Saleem <shiraz.saleem@xxxxxxxxx>
> Signed-off-by: Don Hiatt <don.hiatt@xxxxxxxxx>
> Signed-off-by: Dennis Dalessandro <dennis.dalessandro@xxxxxxxxx>
>
> Changes since v1: Add Shiraz RB tag, move undefined to be 0 not 3
> include/rdma/ib_verbs.h | 12 ++++++++++--
> 1 files changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
> index 5e32fe7..0eb3074 100644
> +++ b/include/rdma/ib_verbs.h
> @@ -878,6 +878,7 @@ struct ib_mr_status {
> __attribute_const__ enum ib_rate mult_to_ib_rate(int mult);
>
> enum rdma_ah_attr_type {
> + RDMA_AH_ATTR_TYPE_UNDEFINED,
> RDMA_AH_ATTR_TYPE_IB,
> RDMA_AH_ATTR_TYPE_ROCE,
> RDMA_AH_ATTR_TYPE_OPA,
> @@ -3789,12 +3790,19 @@ static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr,
> grh->traffic_class = traffic_class;
> }
>
> -/*Get AH type */
> +/**
> + * rdma_ah_find_type - Return address handle type.
> + *
> + * @dev: Device to be checked
> + * @port_num: Port number
> + */
> static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
> - u32 port_num)
> + u8 port_num)
> {
> if (rdma_protocol_roce(dev, port_num))
> return RDMA_AH_ATTR_TYPE_ROCE;
> + else if (rdma_protocol_iwarp(dev, port_num))
> + return RDMA_AH_ATTR_TYPE_UNDEFINED;
> else if ((rdma_protocol_ib(dev, port_num)) &&
> (rdma_cap_opa_ah(dev, port_num)))
> return RDMA_AH_ATTR_TYPE_OPA;
Let's not add an UNDEFINED type in the middle of an if casecade with an all
other cases fall through please:
static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
u32 port_num)
{
if (rdma_protocol_roce(dev, port_num))
return RDMA_AH_ATTR_TYPE_ROCE;
if (rdma_protocol_ib(dev, port_num)) {
if (rdma_cap_opa_ah(dev, port_num))
return RDMA_AH_ATTR_TYPE_OPA;
return RDMA_AH_ATTR_TYPE_IB;
}
return RDMA_AH_ATTR_TYPE_UNDEFINED;
}
I'm not sure sending all these unrelated patches in one series is such
a helpful idea. Lot of trouble for everyone just to respond to one
minor comment.
This series looks like 4-5 topics to me:
- Optimize HFI
- 2 patches realted to the interrupt race
- Random driver fixes
- IPoIB fix
- This patch
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
