All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Woodhouse, David" <david.woodhouse-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
To: "jroedel-l3A5Bk7waGM@public.gmane.org"
	<jroedel-l3A5Bk7waGM@public.gmane.org>,
	Shaohua Li <shli-b10kYP2dOMg@public.gmane.org>
Cc: "iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org"
	<iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org>,
	"Kernel-team-b10kYP2dOMg@public.gmane.org"
	<Kernel-team-b10kYP2dOMg@public.gmane.org>
Subject: Re: [PATCH 2/4] iommu: add a bitmap based dma address allocator
Date: Wed, 25 Nov 2015 16:40:00 +0000	[thread overview]
Message-ID: <1448469599.44976.134.camel@intel.com> (raw)
In-Reply-To: <20151125144613.GA3763-l3A5Bk7waGM@public.gmane.org>


[-- Attachment #1.1: Type: text/plain, Size: 1033 bytes --]

On Wed, 2015-11-25 at 15:46 +0100, jroedel-l3A5Bk7waGM@public.gmane.org wrote:
> On Tue, Nov 24, 2015 at 02:05:12PM -0800, Shaohua Li wrote:
> > The lib/iommu-common.c uses a bitmap and a lock. This implementation
> > actually uses a percpu_ida which completely avoids locking. It would be
> > possible to make lib/iommu-common.c use percpu_ida too if somebody wants
> > to do it, but I think this shouldn't be a blocker for these patches
> > giving it has huge performance gain.
> 
> It doesn't "completely avoids locking", the percpu_ida code uses a lock
> internally too. Also, what is the memory and device address space
> overhead per cpu?

A percpu lock doesn't bounce cachelines between CPUs very much, so from
that point of view it might as well not exist :)

-- 
                  Sent with Evolution's ActiveSync support.

David Woodhouse                            Open Source Technology Centre
David.Woodhouse-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org                              Intel Corporation



[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 3437 bytes --]

[-- Attachment #2: Type: text/plain, Size: 0 bytes --]



  parent reply	other threads:[~2015-11-25 16:40 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-24 21:54 [PATCH 0/4] iommu: remove lock contention in iova allocation Shaohua Li
     [not found] ` <cover.1448401089.git.shli-b10kYP2dOMg@public.gmane.org>
2015-11-24 21:54   ` [PATCH 1/4] iommu: alloc_iova returns a pfn Shaohua Li
2015-11-24 21:54   ` [PATCH 2/4] iommu: add a bitmap based dma address allocator Shaohua Li
     [not found]     ` <4c0804c85404be81acfe81fcd402f1af484e9d5f.1448401089.git.shli-b10kYP2dOMg@public.gmane.org>
2015-11-24 21:56       ` Woodhouse, David
     [not found]         ` <1448402209.44976.109.camel-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2015-11-24 22:05           ` Shaohua Li
     [not found]             ` <20151124220511.GA2106568-tb7CFzD8y5b7E6g3fPdp/g2O0Ztt9esIQQ4Iyu8u01E@public.gmane.org>
2015-11-25 14:46               ` jroedel-l3A5Bk7waGM
     [not found]                 ` <20151125144613.GA3763-l3A5Bk7waGM@public.gmane.org>
2015-11-25 16:40                   ` Woodhouse, David [this message]
     [not found]                     ` <1448469599.44976.134.camel-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
2015-11-25 16:43                       ` Jens Axboe
     [not found]                         ` <5655E545.1010509-b10kYP2dOMg@public.gmane.org>
2015-11-25 17:33                           ` Shaohua Li
     [not found]                             ` <20151125173320.GA92074-tb7CFzD8y5b7E6g3fPdp/g2O0Ztt9esIQQ4Iyu8u01E@public.gmane.org>
2015-11-25 17:38                               ` Jens Axboe
     [not found]                                 ` <5655F1F8.9070203-b10kYP2dOMg@public.gmane.org>
2015-11-25 18:57                                   ` Shaohua Li
2015-11-24 21:54   ` [PATCH 3/4] iommu: enable bitmap allocation for intel iommu Shaohua Li
2015-11-24 21:54   ` [PATCH 4/4] iommu: free_iova doesn't need lock twice Shaohua Li
2015-12-07 17:52   ` [PATCH 0/4] iommu: remove lock contention in iova allocation Shaohua Li

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=1448469599.44976.134.camel@intel.com \
    --to=david.woodhouse-ral2jqcrhueavxtiumwx3w@public.gmane.org \
    --cc=Kernel-team-b10kYP2dOMg@public.gmane.org \
    --cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
    --cc=jroedel-l3A5Bk7waGM@public.gmane.org \
    --cc=shli-b10kYP2dOMg@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.