On 4/14/2015 2:50 AM, Hefty, Sean wrote:
Yes, this comment probably could use a reword..
+ IB_GID_TYPE_IB = 0,
+ IB_GID_TYPE_ROCE_V2 = 1,
+ IB_GID_TYPE_SIZE
+};
Can you explain the purpose of defining a 'GID type'. A GID is just a
global
address. Why does it matter to anyone using it how it was constructed?
This is part of RoCE V2 Specification. Please refer to Section A 17.8 .
The GID Type determines the protocol for outbound packet generation i.e
RoCE V1 (0x8915 Ether Type) or RoCEV2 (IPv4 or IPv6)
This isn't an interface for the RoCE specification. Why does this need to be
added to the verbs interface? It hasn't been needed by apps yet, and I don't
see why the apps should be made to care now how the GID is formatted.
This is a part of the GID meta info. The user should be able to choose
between RoCE V1 (which is represented here by IB_GID_TYPE_IB) and RoCE
V2 - just as a user could choose between IPv6 and IPv4.
@@ -265,7 +295,9 @@ enum ib_port_cap_flags {
IB_PORT_BOOT_MGMT_SUP = 1 << 23,
IB_PORT_LINK_LATENCY_SUP = 1 << 24,
IB_PORT_CLIENT_REG_SUP = 1 << 25,
- IB_PORT_IP_BASED_GIDS = 1 << 26
+ IB_PORT_IP_BASED_GIDS = 1 << 26,
+ IB_PORT_ROCE = 1 << 27,
+ IB_PORT_ROCE_V2 = 1 << 28,
Why does RoCE suddenly require a port capability bit? RoCE runs today
without setting any bit.
Again, this is part of RoCE V2 SPEC, please refer to Section A17.5.1-
Query HCA(Pasting snippet below)
A new "RoCE Supported" capability bit shall be added to the Port
Attributes
list. This capability bit applies exclusively to ports of the new
"RoCEv2" type
Same comment as above.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
