netdev - RE: [PATCH v2 01/17] IB/Verbs: Implement new callback query

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 8 Apr 2015 18:41:22 +0000
From:	"Hefty, Sean" <sean.hefty@...el.com>
To:	Doug Ledford <dledford@...hat.com>,
	Michael Wang <yun.wang@...fitbricks.com>
CC:	Roland Dreier <roland@...nel.org>,
	"linux-rdma@...r.kernel.org" <linux-rdma@...r.kernel.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"linux-nfs@...r.kernel.org" <linux-nfs@...r.kernel.org>,
	"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
	Hal Rosenstock <hal.rosenstock@...il.com>,
	"Tom Tucker" <tom@...ngridcomputing.com>,
	Steve Wise <swise@...ngridcomputing.com>,
	Hoang-Nam Nguyen <hnguyen@...ibm.com>,
	Christoph Raisch <raisch@...ibm.com>,
	infinipath <infinipath@...el.com>,
	"Eli Cohen" <eli@...lanox.com>,
	"Latif, Faisal" <faisal.latif@...el.com>,
	"Upinder Malhi" <umalhi@...co.com>,
	Trond Myklebust <trond.myklebust@...marydata.com>,
	"J. Bruce Fields" <bfields@...ldses.org>,
	"David S. Miller" <davem@...emloft.net>,
	"Weiny, Ira" <ira.weiny@...el.com>,
	PJ Waskiewicz <pj.waskiewicz@...idfire.com>,
	"Nikolova, Tatyana E" <tatyana.e.nikolova@...el.com>,
	Or Gerlitz <ogerlitz@...lanox.com>,
	"Jack Morgenstein" <jackm@....mellanox.co.il>,
	Haggai Eran <haggaie@...lanox.com>,
	Ilya Nelkenbaum <ilyan@...lanox.com>,
	Yann Droneaud <ydroneaud@...eya.com>,
	Bart Van Assche <bvanassche@....org>,
	Shachar Raindel <raindel@...lanox.com>,
	Sagi Grimberg <sagig@...lanox.com>,
	Devesh Sharma <devesh.sharma@...lex.com>,
	Matan Barak <matanb@...lanox.com>,
	Moni Shoua <monis@...lanox.com>,
	"Jiri Kosina" <jkosina@...e.cz>,
	Selvin Xavier <selvin.xavier@...lex.com>,
	"Mitesh Ahuja" <mitesh.ahuja@...lex.com>,
	Li RongQing <roy.qing.li@...il.com>,
	Rasmus Villemoes <linux@...musvillemoes.dk>,
	"Estrin, Alex" <alex.estrin@...el.com>,
	Eric Dumazet <edumazet@...gle.com>,
	Erez Shitrit <erezsh@...lanox.com>,
	Tom Gundersen <teg@...m.no>,
	Chuck Lever <chuck.lever@...cle.com>
Subject: RE: [PATCH v2 01/17] IB/Verbs: Implement new callback
 query_transport() for each HW

> I'm concerned about the performance implications of this.  The size of
> this patchset already points out just how many places in the code we
> have to check for various aspects of the device transport in order to do
> the right thing.  Without going through the entire list to see how many
> are on critical hot paths, I'm sure some of them are on at least
> partially critical hot paths (like creation of new connections).  I
> would prefer to see this change be implemented via a device attribute,
> not a functional call query.  That adds a needless function call in
> these paths.

My impression of these changes were that they would eventually lead to the mechanism that you outlined: 


> I'm also concerned about this.  I would like to see this enum
> essentially turned into a bitmap.  One that is constructed in such a way
> that we can always get the specific test we need with only one compare
> against the overall value.  In order to do so, we need to break it down
> into the essential elements that are part of each of the transports.
> So, for instance, we can define the two link layers we have so far, plus
> reserve one for OPA which we know is coming:
> 
> RDMA_LINK_LAYER_IB       = 0x00000001,
> RDMA_LINK_LAYER_ETH      = 0x00000002,
> RDMA_LINK_LAYER_OPA      = 0x00000004,
> RDMA_LINK_LAYER_MASK     = 0x0000000f,
> 
> We can then define the currently known high level transport types:
> 
> RDMA_TRANSPORT_IB        = 0x00000010,
> RDMA_TRANSPORT_IWARP     = 0x00000020,
> RDMA_TRANSPORT_USNIC     = 0x00000040,
> RDMA_TRANSPORT_USNIC_UDP = 0x00000080,
> RDMA_TRANSPORT_MASK      = 0x000000f0,
> 
> We could then define bits for the IB management types:
> 
> RDMA_MGMT_IB             = 0x00000100,
> RDMA_MGMT_OPA            = 0x00000200,
> RDMA_MGMT_MASK           = 0x00000f00,
> 
> Then we have space to define specific quirks:
> 
> RDMA_SEPARATE_READ_SGE   = 0x00001000,
> RDMA_QUIRKS_MASK         = 0xfffff000

I too would like to see this as the end result, but I think it's possible to stage the changes by having the static inline calls being added convert to using these sort of attributes.

- Sean