From mboxrd@z Thu Jan 1 00:00:00 1970 From: Matan Barak Subject: Re: [PATCH v3 for-next 01/33] IB/core: Add RoCE GID cache Date: Tue, 14 Apr 2015 12:32:21 +0300 Message-ID: <552CDEA5.6020709@mellanox.com> References: <1427318422-12004-1-git-send-email-somnath.kotur@emulex.com> <44ab0dce-c7c9-400b-af24-10b8981358a7@CMEXHTCAS2.ad.emulex.com> <1828884A29C6694DAF28B7E6B8A82373A8FBE792@ORSMSX109.amr.corp.intel.com> <7F44EA5110810A40B7DAFB605C41975D58F98121@CMEXMB1.ad.emulex.com> <1828884A29C6694DAF28B7E6B8A82373A8FC0C00@ORSMSX109.amr.corp.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="windows-1252"; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1828884A29C6694DAF28B7E6B8A82373A8FC0C00-P5GAC/sN6hkd3b2yrw5b5LfspsVTdybXVpNB7YpNyf8@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: "Hefty, Sean" , Somnath Kotur , "roland-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org" Cc: "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" List-Id: linux-rdma@vger.kernel.org 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 majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html