public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
To: Bart Van Assche <bvanassche-HInyCGIudOg@public.gmane.org>
Cc: Roland Dreier <rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>,
	Linux-RDMA <linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: Re: About a shortcoming of the verbs API
Date: Sat, 7 Aug 2010 19:38:22 -0600	[thread overview]
Message-ID: <20100808013822.GA15146@obsidianresearch.com> (raw)
In-Reply-To: <AANLkTimc3iS8=8ZQ9u8tOLP4-q_e+o0=AncZj-Mbre2g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>

On Sat, Aug 07, 2010 at 09:56:13AM +0200, Bart Van Assche wrote:

> The above implies that one must be careful when applying a common
> Linux practice, that is to defer interrupt handling from IRQ context
> to tasklet context. Since tasklets are executed with interrupts
> enabled, invoking ib_req_notify_cq(cq, IB_CQ_NEXT_COMP) from tasklet
> context may cause concurrent execution of an IB IRQ with an IB
> tasklet. So if ib_poll_cq() is invoked from tasklet context, the
> entire polling loop has to be protected against concurrent execution.
> As far as I know such protection against concurrent execution is not
> necessary inside tasklets that handle other types of hardware.

No, all hardware pretty much works like this. The general flow is:

IRQ happens
 (if level triggered 'ack' the IRQ to the HW, to suppress the level)
SW processes
SW 'does something' to the HW to cause new IRQs to happen
IRQ happens.. repeat..

In the IB case, you get exactly one completion call back and when you
call ib_req_notify_cq/etc then you might get more. There is implicit
locking provided by the HW, in that it does not generate more IRQs
until explicitly told to.

Pretty much every bit of HW works the same way, IRQs stop until the
SW 'does something' to indicate it wants more. If this something is
the very last thing in a tasklet then everything is OK.

A trivial example for ethernet hardware would be someting like this..

IRQ happens whenever packet_buffer_wr != packet_buffer_rd
  When HW sends an IRQ it sets a HW bit to disable further IRQ
  messages
SW processes
SW writes packet_buffer_rd to HW
 HW flips off its disable further IRQ bit
IRQ happens whenever packet_buffer_wr != packet_buffer_rd, which may
 be immediately

Jason
--
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

  parent reply	other threads:[~2010-08-08  1:38 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <AANLkTi=zowawGDjyh+uKve_NiRNMXcrqjAk0hRxGSMOv@mail.gmail.com>
     [not found] ` <AANLkTi=zowawGDjyh+uKve_NiRNMXcrqjAk0hRxGSMOv-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-07-25 18:54   ` About a shortcoming of the verbs API Bart Van Assche
     [not found]     ` <AANLkTinHRnt-jvy0xBOAPUDGcfx6=V6rkRT3t0Ja52FP-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-07-26 14:21       ` Steve Wise
     [not found]         ` <4C4D99F8.3090206-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2010-07-26 17:59           ` Bart Van Assche
2010-07-26 19:22       ` Roland Dreier
     [not found]         ` <adamxtejbes.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-07-27  7:54           ` Or Gerlitz
     [not found]             ` <4C4E90B6.5070002-hKgKHo2Ms0FWk0Htik3J/w@public.gmane.org>
2010-07-28 17:44               ` Roland Dreier
     [not found]                 ` <ada1vanfqn1.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-07-29  6:27                   ` Or Gerlitz
2010-07-27  8:33           ` Bart Van Assche
     [not found]             ` <AANLkTinYuyCqJ6_wq6GH0vQGAY-mwC=7ZLicBnXO+efB-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-07-27 16:50               ` Roland Dreier
     [not found]                 ` <adafwz4g98j.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-07-27 18:03                   ` Bart Van Assche
     [not found]                     ` <AANLkTimAk0k-q1EKjaXOadoXvKXbEN9nAky0w1rjixxB-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-07-27 18:20                       ` Jason Gunthorpe
     [not found]                         ` <20100727182046.GT7920-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2010-07-27 19:28                           ` Bart Van Assche
     [not found]                             ` <AANLkTimAS6znoCCw33ipVV-W-e1BJS93Fxzp-oe0jO4u-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-07-27 20:15                               ` Jason Gunthorpe
2010-07-28 17:42                               ` Roland Dreier
     [not found]                                 ` <ada62zzfqpj.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-07-28 17:51                                   ` Ralph Campbell
     [not found]                                     ` <1280339513.31421.264.camel-/vjeY7uYZjrPXfVEPVhPGq6RkeBMCJyt@public.gmane.org>
2010-07-28 18:01                                       ` Bart Van Assche
2010-07-28 18:05                                       ` Roland Dreier
     [not found]                                         ` <adask33eb36.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-07-28 18:11                                           ` Ralph Campbell
2010-07-28 18:16                                           ` Roland Dreier
     [not found]                                             ` <adaocdreal0.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-07-28 19:05                                               ` Ralph Campbell
2010-08-07  7:56                           ` Bart Van Assche
     [not found]                             ` <AANLkTimc3iS8=8ZQ9u8tOLP4-q_e+o0=AncZj-Mbre2g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-08-07 16:32                               ` Roland Dreier
     [not found]                                 ` <adavd7mz8m9.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
2010-08-08 18:19                                   ` Bart Van Assche
     [not found]                                     ` <AANLkTinKsLNoia96AVDA6fP9Es5_2Rq_wTgY=z6wk_FE-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-08-09 14:49                                       ` David Dillow
     [not found]                                         ` <1281365347.4968.5.camel-FqX9LgGZnHWDB2HL1qBt2PIbXMQ5te18@public.gmane.org>
2010-08-09 18:45                                           ` Vladislav Bolkhovitin
     [not found]                                             ` <4C604CB4.5060705-d+Crzxg7Rs0@public.gmane.org>
2010-08-09 18:58                                               ` David Dillow
2010-08-08  1:38                               ` Jason Gunthorpe [this message]
     [not found]                                 ` <20100808013822.GA15146-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2010-08-08 18:16                                   ` Bart Van Assche
     [not found]                                     ` <AANLkTi=My1aK3VsYejeVeRSqo+7RNMX2x6osGNbBERvx-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-08-08 23:51                                       ` Jason Gunthorpe
     [not found]                                         ` <20100808235104.GA32488-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2010-08-09  7:57                                           ` Bart Van Assche

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=20100808013822.GA15146@obsidianresearch.com \
    --to=jgunthorpe-epgobjl8dl3ta4ec/59zmfatqe2ktcn/@public.gmane.org \
    --cc=bvanassche-HInyCGIudOg@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox