LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@ziepe.ca>
To: Doug Ledford <dledford@redhat.com>
Cc: "Håkon Bugge" <Haakon.Bugge@oracle.com>,
	"Don Hiatt" <don.hiatt@intel.com>,
	"Dasaratharaman Chandramouli"
	<dasaratharaman.chandramouli@intel.com>,
	"Ira Weiny" <ira.weiny@intel.com>,
	"Sean Hefty" <sean.hefty@intel.com>,
	linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] IB/core: Make ib_mad_client_id atomic
Date: Fri, 20 Apr 2018 09:34:51 -0600	[thread overview]
Message-ID: <20180420153451.GF30433@ziepe.ca> (raw)
In-Reply-To: <1524196555.11756.30.camel@redhat.com>

On Thu, Apr 19, 2018 at 11:55:55PM -0400, Doug Ledford wrote:
> On Wed, 2018-04-18 at 16:24 +0200, Håkon Bugge wrote:
> > Two kernel threads may get the same value for agent.hi_tid, if the
> > agents are registered for different ports. As of now, this works, as
> > the agent list is per port.
> > 
> > It is however confusing and not future robust. Hence, making it
> > atomic.
> > 
> 
> People sometimes underestimate the performance penalty of atomic ops. 
> Every atomic op is the equivalent of a spin_lock/spin_unlock pair.  This
> is why two atomics are worse than taking a spin_lock, doing what you
> have to do, and releasing the spin_lock.  Is this really what you want
> for a "confusing, let's make it robust" issue?

But it is on the ib_register_mad_agent() path which is not a
performance path..

This actually looks like a genuine bug, why is it described only as
'confusing'? ib_register_mad_agent is callable from userspace, so at
least two userspace agents can race and get the same TID's.

TIDs need to be globally unique on the entire machine.

Jason

  reply	other threads:[~2018-04-20 15:34 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-18 14:24 Håkon Bugge
2018-04-18 18:51 ` Weiny, Ira
2018-04-19  2:59 ` Yanjun Zhu
2018-04-20  3:55 ` Doug Ledford
2018-04-20 15:34   ` Jason Gunthorpe [this message]
2018-04-23 14:19     ` Håkon Bugge
2018-04-23 19:16       ` jackm
2018-04-26 16:06         ` Håkon Bugge
2018-04-26 18:32           ` jackm
     [not found]             ` <9fdd3ec4-ee91-5442-e753-25d2ecd27ea9@xsintricity.com>
     [not found]               ` <A58D5192-06E7-46A3-869C-273E9A2BC128@oracle.com>
2018-04-27 19:08                 ` Doug Ledford
2018-04-30 11:50                   ` Håkon Bugge
2018-04-30 14:49         ` Jason Gunthorpe
2018-04-30 17:10           ` Doug Ledford
2018-04-30 17:49             ` Weiny, Ira
2018-04-30 23:01             ` Jason Gunthorpe
2018-05-01  4:38             ` jackm
2018-05-01  6:40               ` Håkon Bugge

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180420153451.GF30433@ziepe.ca \
    --to=jgg@ziepe.ca \
    --cc=Haakon.Bugge@oracle.com \
    --cc=dasaratharaman.chandramouli@intel.com \
    --cc=dledford@redhat.com \
    --cc=don.hiatt@intel.com \
    --cc=ira.weiny@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=sean.hefty@intel.com \
    --subject='Re: [PATCH] IB/core: Make ib_mad_client_id atomic' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).