From: Logan Gunthorpe <logang@deltatee.com>
To: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>,
linux-nvdimm@ml01.01.org, dri-devel@lists.freedesktop.org,
Stephen Bates <sbates@raithlin.com>,
dm-devel@redhat.com, target-devel@vger.kernel.org,
Christoph Hellwig <hch@lst.de>,
devel@driverdev.osuosl.org,
"James E.J. Bottomley" <jejb@linux.vnet.ibm.com>,
linux-scsi@vger.kernel.org,
Matthew Wilcox <mawilcox@microsoft.com>,
linux-rdma@vger.kernel.org,
Sumit Semwal <sumit.semwal@linaro.org>,
Ross Zwisler <ross.zwisler@linux.intel.com>,
open-iscsi@googlegroups.com, linux-media@vger.kernel.org,
Juergen Gross <jgross@suse.com>,
Julien Grall <julien.grall@arm.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
intel-gfx@lists.freedesktop.org, sparmaintainer@unisys.com,
linux-raid@vger.kernel.org,
Dan Williams <dan.j.williams@intel.com>,
megaraidlinux.pdl@broadcom.com, Jens Axboe <axboe@kernel.dk>,
"Martin K. Petersen" <martin.p>
Subject: Re: [PATCH v2 15/21] xen-blkfront: Make use of the new sg_map helper function
Date: Thu, 27 Apr 2017 17:29:08 -0600 [thread overview]
Message-ID: <eb33e0ce-987f-a345-ca95-71e4c0a4d1ea@deltatee.com> (raw)
In-Reply-To: <20170427232022.GA30398@obsidianresearch.com>
On 27/04/17 05:20 PM, Jason Gunthorpe wrote:
> It seems the most robust: test for iomem, and jump to a slow path
> copy, otherwise inline the kmap and memcpy
>
> Every place doing memcpy from sgl will need that pattern to be
> correct.
Ok, sounds like a good place to start to me. I'll see what I can do for
a v3 of this set. Though, I probably won't send anything until after the
merge window.
>>> sg_miter will still fail when the sg contains __iomem, however I would
>>> expect that the sg_copy will work with iomem, by using the __iomem
>>> memcpy variant.
>>
>> Yes, that's true. Any sg_miters that ever see iomem will need to be
>> converted to support it. This isn't much different than the other
>> kmap(sg_page()) users I was converting that will also fail if they see
>> iomem. Though, I suspect an sg_miter user would be easier to convert to
>> iomem than a random kmap user.
>
> How? sg_miter seems like the next nightmare down this path, what is
> sg_miter_next supposed to do when something hits an iomem sgl?
My proposal is roughly included in the draft I sent upthread. We add an
sg_miter flag indicating the iteratee supports iomem and if miter finds
iomem (with the support flag set) it sets ioaddr which is __iomem. The
iteratee then just needs to null check addr and ioaddr and perform the
appropriate action.
Logan
WARNING: multiple messages have this Message-ID (diff)
From: Logan Gunthorpe <logang@deltatee.com>
To: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>,
linux-nvdimm@ml01.01.org, dri-devel@lists.freedesktop.org,
Stephen Bates <sbates@raithlin.com>,
dm-devel@redhat.com, target-devel@vger.kernel.org,
Christoph Hellwig <hch@lst.de>,
devel@driverdev.osuosl.org,
"James E.J. Bottomley" <jejb@linux.vnet.ibm.com>,
linux-scsi@vger.kernel.org,
Matthew Wilcox <mawilcox@microsoft.com>,
linux-rdma@vger.kernel.org,
Sumit Semwal <sumit.semwal@linaro.org>,
Ross Zwisler <ross.zwisler@linux.intel.com>,
open-iscsi@googlegroups.com, linux-media@vger.kernel.org,
Juergen Gross <jgross@suse.com>,
Julien Grall <julien.grall@arm.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
intel-gfx@lists.freedesktop.org, sparmaintainer@unisys.com,
linux-raid@vger.kernel.org,
Dan Williams <dan.j.williams@intel.com>,
megaraidlinux.pdl@broadcom.com, Jens Axboe <axboe@kernel.dk>,
"Martin K. Petersen" <martin.p
Subject: Re: [PATCH v2 15/21] xen-blkfront: Make use of the new sg_map helper function
Date: Thu, 27 Apr 2017 17:29:08 -0600 [thread overview]
Message-ID: <eb33e0ce-987f-a345-ca95-71e4c0a4d1ea@deltatee.com> (raw)
In-Reply-To: <20170427232022.GA30398@obsidianresearch.com>
On 27/04/17 05:20 PM, Jason Gunthorpe wrote:
> It seems the most robust: test for iomem, and jump to a slow path
> copy, otherwise inline the kmap and memcpy
>
> Every place doing memcpy from sgl will need that pattern to be
> correct.
Ok, sounds like a good place to start to me. I'll see what I can do for
a v3 of this set. Though, I probably won't send anything until after the
merge window.
>>> sg_miter will still fail when the sg contains __iomem, however I would
>>> expect that the sg_copy will work with iomem, by using the __iomem
>>> memcpy variant.
>>
>> Yes, that's true. Any sg_miters that ever see iomem will need to be
>> converted to support it. This isn't much different than the other
>> kmap(sg_page()) users I was converting that will also fail if they see
>> iomem. Though, I suspect an sg_miter user would be easier to convert to
>> iomem than a random kmap user.
>
> How? sg_miter seems like the next nightmare down this path, what is
> sg_miter_next supposed to do when something hits an iomem sgl?
My proposal is roughly included in the draft I sent upthread. We add an
sg_miter flag indicating the iteratee supports iomem and if miter finds
iomem (with the support flag set) it sets ioaddr which is __iomem. The
iteratee then just needs to null check addr and ioaddr and perform the
appropriate action.
Logan
WARNING: multiple messages have this Message-ID (diff)
From: Logan Gunthorpe <logang@deltatee.com>
To: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: "Roger Pau Monné" <roger.pau@citrix.com>,
linux-kernel@vger.kernel.org, linux-crypto@vger.kernel.org,
linux-media@vger.kernel.org, dri-devel@lists.freedesktop.org,
intel-gfx@lists.freedesktop.org, linux-raid@vger.kernel.org,
linux-mmc@vger.kernel.org, linux-nvdimm@ml01.01.org,
linux-scsi@vger.kernel.org, open-iscsi@googlegroups.com,
megaraidlinux.pdl@broadcom.com, sparmaintainer@unisys.com,
devel@driverdev.osuosl.org, target-devel@vger.kernel.org,
netdev@vger.kernel.org, linux-rdma@vger.kernel.org,
dm-devel@redhat.com, "Christoph Hellwig" <hch@lst.de>,
"Martin K. Petersen" <martin.petersen@oracle.com>,
"James E.J. Bottomley" <jejb@linux.vnet.ibm.com>,
"Jens Axboe" <axboe@kernel.dk>,
"Greg Kroah-Hartman" <gregkh@linuxfoundation.org>,
"Dan Williams" <dan.j.williams@intel.com>,
"Ross Zwisler" <ross.zwisler@linux.intel.com>,
"Matthew Wilcox" <mawilcox@microsoft.com>,
"Sumit Semwal" <sumit.semwal@linaro.org>,
"Stephen Bates" <sbates@raithlin.com>,
"Boris Ostrovsky" <boris.ostrovsky@oracle.com>,
"Juergen Gross" <jgross@suse.com>,
"Konrad Rzeszutek Wilk" <konrad.wilk@oracle.com>,
"Julien Grall" <julien.grall@arm.com>
Subject: Re: [PATCH v2 15/21] xen-blkfront: Make use of the new sg_map helper function
Date: Thu, 27 Apr 2017 17:29:08 -0600 [thread overview]
Message-ID: <eb33e0ce-987f-a345-ca95-71e4c0a4d1ea@deltatee.com> (raw)
In-Reply-To: <20170427232022.GA30398@obsidianresearch.com>
On 27/04/17 05:20 PM, Jason Gunthorpe wrote:
> It seems the most robust: test for iomem, and jump to a slow path
> copy, otherwise inline the kmap and memcpy
>
> Every place doing memcpy from sgl will need that pattern to be
> correct.
Ok, sounds like a good place to start to me. I'll see what I can do for
a v3 of this set. Though, I probably won't send anything until after the
merge window.
>>> sg_miter will still fail when the sg contains __iomem, however I would
>>> expect that the sg_copy will work with iomem, by using the __iomem
>>> memcpy variant.
>>
>> Yes, that's true. Any sg_miters that ever see iomem will need to be
>> converted to support it. This isn't much different than the other
>> kmap(sg_page()) users I was converting that will also fail if they see
>> iomem. Though, I suspect an sg_miter user would be easier to convert to
>> iomem than a random kmap user.
>
> How? sg_miter seems like the next nightmare down this path, what is
> sg_miter_next supposed to do when something hits an iomem sgl?
My proposal is roughly included in the draft I sent upthread. We add an
sg_miter flag indicating the iteratee supports iomem and if miter finds
iomem (with the support flag set) it sets ioaddr which is __iomem. The
iteratee then just needs to null check addr and ioaddr and perform the
appropriate action.
Logan
next prev parent reply other threads:[~2017-04-27 23:29 UTC|newest]
Thread overview: 183+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-25 18:20 [PATCH v2 00/21] Introduce common scatterlist map function Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 01/21] scatterlist: Introduce sg_map helper functions Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-26 7:44 ` Christoph Hellwig
2017-04-26 7:44 ` Christoph Hellwig
2017-04-26 7:44 ` Christoph Hellwig
2017-04-26 7:44 ` Christoph Hellwig
2017-04-26 7:44 ` Christoph Hellwig
2017-04-26 18:11 ` Logan Gunthorpe
2017-04-26 18:11 ` Logan Gunthorpe
2017-04-26 18:11 ` Logan Gunthorpe
2017-04-26 18:11 ` Logan Gunthorpe
2017-04-27 6:53 ` Christoph Hellwig
2017-04-27 6:53 ` Christoph Hellwig
2017-04-27 6:53 ` Christoph Hellwig
2017-04-27 6:53 ` Christoph Hellwig
2017-04-27 6:53 ` Christoph Hellwig
[not found] ` <20170427065338.GA20677-jcswGhMUV9g@public.gmane.org>
2017-04-27 15:27 ` Jason Gunthorpe
2017-04-27 15:27 ` Jason Gunthorpe
[not found] ` <20170427152720.GA7662-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-04-27 15:57 ` Logan Gunthorpe
2017-04-27 15:57 ` Logan Gunthorpe
2017-04-27 15:44 ` Logan Gunthorpe
2017-04-27 15:44 ` Logan Gunthorpe
2017-04-27 15:44 ` Logan Gunthorpe
2017-04-27 15:44 ` Logan Gunthorpe
2017-04-27 20:13 ` Logan Gunthorpe
2017-04-27 20:13 ` Logan Gunthorpe
2017-04-27 20:13 ` Logan Gunthorpe
2017-04-27 20:13 ` Logan Gunthorpe
2017-04-26 8:59 ` Christian König
2017-04-26 8:59 ` Christian König
2017-04-26 8:59 ` Christian König
2017-04-26 8:59 ` Christian König
2017-04-26 8:59 ` Christian König
2017-04-26 23:30 ` Logan Gunthorpe
2017-04-26 23:30 ` Logan Gunthorpe
2017-04-26 23:30 ` Logan Gunthorpe
2017-04-26 23:30 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 02/21] libiscsi: Add an internal error code Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-26 7:48 ` Christoph Hellwig
2017-04-26 7:48 ` Christoph Hellwig
2017-04-26 7:48 ` Christoph Hellwig
2017-04-26 7:48 ` Christoph Hellwig
2017-04-26 7:48 ` Christoph Hellwig
2017-04-25 18:20 ` [PATCH v2 03/21] libiscsi: Make use of new the sg_map helper function Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 04/21] target: Make use of the new sg_map function at 16 call sites Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 05/21] drm/i915: Make use of the new sg_map helper function Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 06/21] crypto: hifn_795x: " Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 07/21] crypto: shash, caam: " Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-27 3:56 ` Herbert Xu
2017-04-27 3:56 ` Herbert Xu
2017-04-27 3:56 ` Herbert Xu
2017-04-27 3:56 ` Herbert Xu
2017-04-27 3:56 ` Herbert Xu
2017-04-27 15:45 ` Logan Gunthorpe
2017-04-27 15:45 ` Logan Gunthorpe
2017-04-27 15:45 ` Logan Gunthorpe
2017-04-27 15:45 ` Logan Gunthorpe
2017-04-28 6:30 ` Herbert Xu
2017-04-28 6:30 ` Herbert Xu
2017-04-28 6:30 ` Herbert Xu
2017-04-28 6:30 ` Herbert Xu
2017-04-28 16:53 ` Logan Gunthorpe
2017-04-28 16:53 ` Logan Gunthorpe
2017-04-28 16:53 ` Logan Gunthorpe
2017-04-28 16:53 ` Logan Gunthorpe
2017-04-28 17:51 ` Herbert Xu
2017-04-28 17:51 ` Herbert Xu
2017-04-28 17:51 ` Herbert Xu
2017-04-28 17:51 ` Herbert Xu
2017-04-28 19:01 ` Logan Gunthorpe
2017-04-28 19:01 ` Logan Gunthorpe
2017-04-28 19:01 ` Logan Gunthorpe
2017-04-28 19:01 ` Logan Gunthorpe
2017-04-28 19:01 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 08/21] dm-crypt: Make use of the new sg_map helper in 4 call sites Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 09/21] staging: unisys: visorbus: Make use of the new sg_map helper function Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 10/21] RDS: " Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 11/21] scsi: ipr, pmcraid, isci: Make use of the new sg_map helper Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` [PATCH v2 12/21] scsi: hisi_sas, mvsas, gdth: Make use of the new sg_map helper function Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:20 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 13/21] scsi: arcmsr, ips, megaraid: " Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 14/21] scsi: libfc, csiostor: Change to sg_copy_buffer in two drivers Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 15/21] xen-blkfront: Make use of the new sg_map helper function Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-26 7:37 ` Roger Pau Monné
2017-04-26 7:37 ` Roger Pau Monné
2017-04-26 7:37 ` Roger Pau Monné
2017-04-26 7:37 ` Roger Pau Monné
2017-04-26 7:37 ` Roger Pau Monné
2017-04-27 20:19 ` Logan Gunthorpe
2017-04-27 20:19 ` Logan Gunthorpe
2017-04-27 20:19 ` Logan Gunthorpe
2017-04-27 20:19 ` Logan Gunthorpe
2017-04-27 20:19 ` Logan Gunthorpe
[not found] ` <df6586e2-7d45-6b0b-facb-4dea882df06e-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-27 20:53 ` Jason Gunthorpe
2017-04-27 20:53 ` Jason Gunthorpe
2017-04-27 20:53 ` Jason Gunthorpe
[not found] ` <20170427205339.GB26330-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-04-27 21:53 ` Logan Gunthorpe
2017-04-27 21:53 ` Logan Gunthorpe
2017-04-27 21:53 ` Logan Gunthorpe
[not found] ` <02ba3c7b-5fab-a06c-fbbf-c3be1c0fae1b-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-27 22:11 ` Jason Gunthorpe
2017-04-27 22:11 ` Jason Gunthorpe
2017-04-27 22:11 ` Jason Gunthorpe
[not found] ` <20170427221132.GA30036-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-04-27 23:03 ` Logan Gunthorpe
2017-04-27 23:03 ` Logan Gunthorpe
2017-04-27 23:03 ` Logan Gunthorpe
[not found] ` <3a7c0d27-0744-4e91-b37f-3885c50455e8-OTvnGxWRz7hWk0Htik3J/w@public.gmane.org>
2017-04-27 23:20 ` Jason Gunthorpe
2017-04-27 23:20 ` Jason Gunthorpe
2017-04-27 23:20 ` Jason Gunthorpe
2017-04-27 23:29 ` Logan Gunthorpe [this message]
2017-04-27 23:29 ` Logan Gunthorpe
2017-04-27 23:29 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 16/21] mmc: sdhci: " Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 17/21] mmc: spi: " Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 18/21] mmc: tmio: " Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 19/21] mmc: sdricoh_cs: " Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 20/21] mmc: tifm_sd: " Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` [PATCH v2 21/21] memstick: " Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:21 ` Logan Gunthorpe
2017-04-25 18:40 ` ✓ Fi.CI.BAT: success for Introduce common scatterlist map function (rev2) Patchwork
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=eb33e0ce-987f-a345-ca95-71e4c0a4d1ea@deltatee.com \
--to=logang@deltatee.com \
--cc=axboe@kernel.dk \
--cc=boris.ostrovsky@oracle.com \
--cc=dan.j.williams@intel.com \
--cc=devel@driverdev.osuosl.org \
--cc=dm-devel@redhat.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=hch@lst.de \
--cc=intel-gfx@lists.freedesktop.org \
--cc=jejb@linux.vnet.ibm.com \
--cc=jgross@suse.com \
--cc=jgunthorpe@obsidianresearch.com \
--cc=julien.grall@arm.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-media@vger.kernel.org \
--cc=linux-nvdimm@ml01.01.org \
--cc=linux-raid@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=mawilcox@microsoft.com \
--cc=megaraidlinux.pdl@broadcom.com \
--cc=open-iscsi@googlegroups.com \
--cc=ross.zwisler@linux.intel.com \
--cc=sbates@raithlin.com \
--cc=sparmaintainer@unisys.com \
--cc=sumit.semwal@linaro.org \
--cc=target-devel@vger.kernel.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.