Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753243AbbELOZN (ORCPT ); Tue, 12 May 2015 10:25:13 -0400 Received: from mx1.redhat.com ([209.132.183.28]:47100 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751901AbbELOZL (ORCPT ); Tue, 12 May 2015 10:25:11 -0400 Message-ID: <1431440667.43876.23.camel@redhat.com> Subject: Re: [PATCH v8 00/23] IB/Verbs: IB Management Helpers From: Doug Ledford To: Michael Wang Cc: "ira.weiny" , Roland Dreier , Sean Hefty , Hal Rosenstock , linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org, Tom Tucker , Steve Wise , Hoang-Nam Nguyen , Christoph Raisch , Mike Marciniszyn , Eli Cohen , Faisal Latif , Jack Morgenstein , Or Gerlitz , Haggai Eran , Tom Talpey , Jason Gunthorpe , Devesh Sharma , Liran Liss , Dave Goodell Date: Tue, 12 May 2015 10:24:27 -0400 In-Reply-To: <5551B280.5040905@profitbricks.com> References: <1430830240-32389-1-git-send-email-yun.wang@profitbricks.com> <20150511234910.GA20027@phlsvsds.ph.intel.com> <1431390420.43876.4.camel@redhat.com> <5551B280.5040905@profitbricks.com> Organization: Red Hat, Inc. Content-Type: multipart/signed; micalg="pgp-sha256"; protocol="application/pgp-signature"; boundary="=-b7MlidVCnQYfFbTkfLk9" Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 11070 Lines: 283 --=-b7MlidVCnQYfFbTkfLk9 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Tue, 2015-05-12 at 09:57 +0200, Michael Wang wrote: >=20 > On 05/12/2015 02:27 AM, Doug Ledford wrote: > > On Mon, 2015-05-11 at 19:49 -0400, ira.weiny wrote: > >> I have run with this series and the only issue I have found is not wit= h this > >> patch set directly. > >> > >> This patch: > >> > >>> IB/Verbs: Use management helper rdma_cap_ib_mad() > >> > >> causes an error when you actually use the port passed from the ib_umad= module. > >> I have a patch to fix that which I found while trying to build on this= series > >> for the use of a bit mask. > >> > >> Doug, I don't know what you would like to do for this fix. I am submi= tting it > >> shortly with a new version of the core capability bit patches. If you= want to > >> just add it after this series or force Michael to respin with the fix? > >=20 > > As I recall, there was a comment from Or requesting to squash some of > > the individual patches down, but I no longer have that email in my Inbo= x > > to double check. And it seemed like there was one other review comment > > not yet addressed. Do I have that right Michael? And if so, are you > > working on a v9? >=20 > AFAIK Or was asking to merge the #15~23, and want to reserve the changelo= g > meanwhile reply the cover of prev version (I'm still confused on that...)= , > I've replied but get no respond yet. >=20 > I can make a v9 to merge the #15~#23 if that could benefit the maintainab= ility, > please let me know your opinion :-) I don't think it would make a significant difference. I've pulled the v8 patchset out of patchworks and I'll throw a new branch with it included up to my github repo sometime today. > About the Bug, if it was not introduced in this series, maybe including t= he > fix in next series would be better? >=20 > Regards, > Michael Wang >=20 > >=20 > >> Frankly > >> I vote for the former because as it stands this series does not break = directly. > >> It was only after I changed the implementation of rdma_cap_ib_mad that= it > >> broke. > >> > >> > >> For the rest of the series. > >> > >> Reviewed-by: Ira Weiny > >> Tested-by: Ira Weiny > >> -- Limited to mlx4, qib, and OPA (with additional patches.) > >> > >> > >> On Tue, May 05, 2015 at 02:50:17PM +0200, Michael Wang wrote: > >>> Since v7: > >>> * Thanks to Doug, Ira, Devesh for the testing :-) > >>> * Thanks for the comments from or, Doug, Ira, Jason :-) > >>> Please remind me if anything missed :-P > >>> * Use rdma_cap_XX() instead of cap_XX() for readability > >>> * Remove CC list in git log for maintainability > >>> * Use bool as return value > >>> * Updated github repository to v8 > >>> > >>> There are plenty of lengthy code to check the transport type of IB de= vice, > >>> or the link layer type of it's port, but actually we are just specula= ting > >>> whether a particular management/feature is supported by the device/po= rt. > >>> > >>> Thus instead of inferring, we should have our own mechanism for IB ma= nagement > >>> capability/protocol/feature checking, several proposals below. > >>> > >>> This patch set will introduce query_protocol() to check management re= quirement > >>> instead of inferring from transport and link layer respectively, alon= g with > >>> the new enum on protocol type. > >>> > >>> Mapping List: > >>> node-type link-layer transport protocol > >>> nes RNIC ETH IWARP IWARP > >>> amso1100 RNIC ETH IWARP IWARP > >>> cxgb3 RNIC ETH IWARP IWARP > >>> cxgb4 RNIC ETH IWARP IWARP > >>> usnic USNIC_UDP ETH USNIC_UDP USNIC_UDP > >>> ocrdma IB_CA ETH IB IBOE > >>> mlx4 IB_CA IB/ETH IB IB/IBOE > >>> mlx5 IB_CA IB IB IB > >>> ehca IB_CA IB IB IB > >>> ipath IB_CA IB IB IB > >>> mthca IB_CA IB IB IB > >>> qib IB_CA IB IB IB > >>> > >>> For example: > >>> if (transport =3D=3D IB) && (link-layer =3D=3D ETH) > >>> will now become: > >>> if (query_protocol() =3D=3D IBOE) > >>> > >>> Thus we will be able to get rid of the respective transport and link-= layer > >>> checking, and it will help us to add new protocol/Technology (like OP= A) more > >>> easier, also with the introduced management helpers, IB management lo= gical > >>> will be more clear and easier for extending. > >>> > >>> Highlights: > >>> The long CC list in each patches was complained consider about th= e > >>> maintainability, it was suggested folks to provide their reviewed= -by or > >>> Acked-by instead, so for those who used to be on the CC list, ple= ase > >>> provide your signature voluntarily :-) > >>> > >>> The 'mgmt-helpers' branch of 'git@github.com:ywang-pb/infiniband-= wy.git' > >>> contain this series based on the latest 'infiniband/for-next' > >>> > >>> Patch 1#~14# included all the logical reform, 15#~23# introduced = the > >>> management helpers. > >>> > >>> Doug suggested the bitmask mechanism: > >>> https://www.mail-archive.com/linux-rdma@vger.kernel.org/msg23765.htm= l > >>> which could be the plan for future reforming, we prefer that to b= e another > >>> series which focus on semantic and performance. > >>> > >>> This patch-set is somewhat 'bloated' now and it may be a good tim= ing for > >>> staging, I'd like to suggest we focus on improving existed helper= s and push > >>> all the further reforms into next series ;-) > >>> > >>> Proposals: > >>> Sean: > >>> https://www.mail-archive.com/linux-rdma@vger.kernel.org/msg23339.htm= l > >>> Doug: > >>> https://www.mail-archive.com/linux-rdma@vger.kernel.org/msg23418.htm= l > >>> https://www.mail-archive.com/linux-rdma@vger.kernel.org/msg23765.htm= l > >>> Jason: > >>> https://www.mail-archive.com/linux-rdma@vger.kernel.org/msg23425.htm= l > >>> > >>> Michael Wang (23): > >>> IB/Verbs: Implement new callback query_protocol() > >>> IB/Verbs: Implement raw management helpers > >>> IB/Verbs: Reform IB-core mad/agent/user_mad > >>> IB/Verbs: Reform IB-core cm > >>> IB/Verbs: Reform IB-core sa_query > >>> IB/Verbs: Reform IB-core multicast > >>> IB/Verbs: Reform IB-ulp ipoib > >>> IB/Verbs: Reform IB-ulp xprtrdma > >>> IB/Verbs: Reform IB-core verbs > >>> IB/Verbs: Reform cm related part in IB-core cma/ucm > >>> IB/Verbs: Reform route related part in IB-core cma > >>> IB/Verbs: Reform mcast related part in IB-core cma > >>> IB/Verbs: Reform cma_acquire_dev() > >>> IB/Verbs: Reform rest part in IB-core cma > >>> IB/Verbs: Use management helper rdma_cap_ib_mad() > >>> IB/Verbs: Use management helper rdma_cap_ib_smi() > >>> IB/Verbs: Use management helper rdma_cap_ib_cm() > >>> IB/Verbs: Use management helper rdma_cap_iw_cm() > >>> IB/Verbs: Use management helper rdma_cap_ib_sa() > >>> IB/Verbs: Use management helper rdma_cap_ib_mcast() > >>> IB/Verbs: Use management helper rdma_cap_read_multi_sge() > >>> IB/Verbs: Use management helper rdma_cap_af_ib() > >>> IB/Verbs: Use management helper rdma_cap_eth_ah() > >>> > >>> drivers/infiniband/core/agent.c | 2 +- > >>> drivers/infiniband/core/cm.c | 20 ++- > >>> drivers/infiniband/core/cma.c | 257 +++++++++++------= ---------- > >>> drivers/infiniband/core/device.c | 1 + > >>> drivers/infiniband/core/mad.c | 43 +++-- > >>> drivers/infiniband/core/multicast.c | 12 +- > >>> drivers/infiniband/core/sa_query.c | 30 ++-- > >>> drivers/infiniband/core/ucm.c | 3 +- > >>> drivers/infiniband/core/ucma.c | 25 +-- > >>> drivers/infiniband/core/user_mad.c | 26 ++- > >>> drivers/infiniband/core/verbs.c | 6 +- > >>> drivers/infiniband/hw/amso1100/c2_provider.c | 7 + > >>> drivers/infiniband/hw/cxgb3/iwch_provider.c | 7 + > >>> drivers/infiniband/hw/cxgb4/provider.c | 7 + > >>> drivers/infiniband/hw/ehca/ehca_hca.c | 6 + > >>> drivers/infiniband/hw/ehca/ehca_iverbs.h | 3 + > >>> drivers/infiniband/hw/ehca/ehca_main.c | 1 + > >>> drivers/infiniband/hw/ipath/ipath_verbs.c | 7 + > >>> drivers/infiniband/hw/mlx4/main.c | 10 ++ > >>> drivers/infiniband/hw/mlx5/main.c | 7 + > >>> drivers/infiniband/hw/mthca/mthca_provider.c | 7 + > >>> drivers/infiniband/hw/nes/nes_verbs.c | 6 + > >>> drivers/infiniband/hw/ocrdma/ocrdma_main.c | 1 + > >>> drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 6 + > >>> drivers/infiniband/hw/ocrdma/ocrdma_verbs.h | 3 + > >>> drivers/infiniband/hw/qib/qib_verbs.c | 7 + > >>> drivers/infiniband/hw/usnic/usnic_ib_main.c | 1 + > >>> drivers/infiniband/hw/usnic/usnic_ib_verbs.c | 6 + > >>> drivers/infiniband/hw/usnic/usnic_ib_verbs.h | 2 + > >>> drivers/infiniband/ulp/ipoib/ipoib_main.c | 15 +- > >>> include/rdma/ib_verbs.h | 167 +++++++++++++++++ > >>> net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 4 +- > >>> net/sunrpc/xprtrdma/svc_rdma_transport.c | 45 ++--- > >>> 33 files changed, 477 insertions(+), 273 deletions(-) > >>> > >>> --=20 > >>> 2.1.0 > >>> > >> -- > >> 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 > >=20 > >=20 > -- > 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 --=20 Doug Ledford GPG KeyID: 0E572FDD --=-b7MlidVCnQYfFbTkfLk9 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQIcBAABCAAGBQJVUg0bAAoJELgmozMOVy/dlg0QAIDsfTcwbcn/8tOg3XEi8sCI J7ySZ6loE9ypYihRfFTD+vg6xuXnMUiIr2uWNCyqgCGvIK5S1kVQ844yRQk8ZbEt 9IpS7q6bCFxR8VAdKb9qFD0oNvU1Z+6hqcejl5jR2gUlQfLkg8JLl2yZ/N1aryxK ehpAfKwPi8Q2e5ctPKalR81DRm7g2XfeKDRfPujYytxXJ2+JGovTT4GasMQBUUN0 m7PlpIbDwqwalFazvENE4hGl7WfEMy39cLhZ9q51f7LkCsqKsmEq5wf52Pfk0iu4 mLZNLqvdcJqaRQTn9McqfPf+u7MKDNfgGhhXEtO7ZXn/epZlfIm4zpF7PdkCEqsv ThzgcX68lKNEsQa6+28lUe9MiUNvq4PQzEvjea2/Hdxv0U1j7QnQ9dy8n6Nmw8g0 8AZG6tzw7sZFVEPlh6EsUSo1FusMV32WKtQed7shmxorHR0nmyek0ND6Jy21sd6m sgb3zoeRsQVRVmkSEy5dw7DqaFd5hbDfPF7RI/EW5IMeTDxHmm1zWvhALZRK8i/P n+mepwrbxT/e/Wq9T1djd3Cut9kQdsKQCCgk3sVRbzRVLxr6MxMMqV5j8mre6aX9 1Mx7guuZlr+lly2LHPMCZQheUn97HUIS+xVtQt6PB5PzZxiScGuJP3DQjsvSKNi3 WoeWHg5xR++mZEiGoZ5s =wxzO -----END PGP SIGNATURE----- --=-b7MlidVCnQYfFbTkfLk9-- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/