LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: "Håkon Bugge" <haakon.bugge@oracle.com>
To: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Doug Ledford <dledford@redhat.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>,
	OFED mailing list <linux-rdma@vger.kernel.org>,
	linux-kernel@vger.kernel.org, jackm <jackm@dev.mellanox.co.il>
Subject: Re: [PATCH] IB/core: Make ib_mad_client_id atomic
Date: Mon, 23 Apr 2018 16:19:57 +0200	[thread overview]
Message-ID: <50E3FE4A-2C6E-4493-92E1-383C349FAE3A@oracle.com> (raw)
In-Reply-To: <20180420153451.GF30433@ziepe.ca>


+Jack

> On 20 Apr 2018, at 17:34, Jason Gunthorpe <jgg@ziepe.ca> wrote:
> 
> 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.

Well, may be this holds true if the mutex and the variable is located in the same cacheline.

>>  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.

My understanding is that every lookup is using the {port, TID} tuple. As such, it is not a bug, but, very confusing.

> TIDs need to be globally unique on the entire machine.

If you are correct Jason, let me reword the commit message.


Thxs, Håkon

  reply	other threads:[~2018-04-23 14:20 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
2018-04-23 14:19     ` Håkon Bugge [this message]
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=50E3FE4A-2C6E-4493-92E1-383C349FAE3A@oracle.com \
    --to=haakon.bugge@oracle.com \
    --cc=dasaratharaman.chandramouli@intel.com \
    --cc=dledford@redhat.com \
    --cc=don.hiatt@intel.com \
    --cc=ira.weiny@intel.com \
    --cc=jackm@dev.mellanox.co.il \
    --cc=jgg@ziepe.ca \
    --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).