All of lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Karsten Graul <kgraul@linux.ibm.com>
Cc: Robin Murphy <robin.murphy@arm.com>,
	Gerald Schaefer <gerald.schaefer@linux.ibm.com>,
	Hamza Mahfooz <someguy@effective-light.com>,
	Christoph Hellwig <hch@lst.de>,
	Dan Williams <dan.j.williams@intel.com>,
	Ioana Ciornei <ioana.ciornei@nxp.com>,
	Jeremy Linton <jeremy.linton@arm.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Marek Szyprowski <m.szyprowski@samsung.com>,
	"iommu@lists.linux-foundation.org"
	<iommu@lists.linux-foundation.org>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	linux-s390 <linux-s390@vger.kernel.org>
Subject: Re: DPAA2 triggers, [PATCH] dma debug: report -EEXIST errors in add_dma_entry
Date: Mon, 11 Oct 2021 13:47:06 +0200	[thread overview]
Message-ID: <20211011114706.GA16350@lst.de> (raw)
In-Reply-To: <fd4a2d8d-3f9d-51f3-1c86-8009ad50e6a1@linux.ibm.com>

On Thu, Oct 07, 2021 at 12:59:32PM +0200, Karsten Graul wrote:
> In our case its really that a buffer is mapped twice for 2 different devices which we use in SMC to provide failover capabilities. We see that -EEXIST is returned when a buffer is mapped for the second device. Since there is a maximum of 2 parallel mappings we never see the warning shown by active_cacheline_inc_overlap() because we don't exceed ACTIVE_CACHELINE_MAX_OVERLAP.

Mapping something twice is possible, but needs special care.
Basically one device always needs to do the first mapping and the other
one needs to use DMA_ATTR_SKIP_CPU_SYNC to opt out of the coherency
protocol.  So we have two TODO items here: 1) the driver needs to use the
above scheme and 2) this dma-debug check needs to understand
DMA_ATTR_SKIP_CPU_SYNC.  Can I trick you into doing both?

WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Karsten Graul <kgraul@linux.ibm.com>
Cc: linux-s390 <linux-s390@vger.kernel.org>,
	Hamza Mahfooz <someguy@effective-light.com>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	Dan Williams <dan.j.williams@intel.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Jeremy Linton <jeremy.linton@arm.com>,
	"iommu@lists.linux-foundation.org"
	<iommu@lists.linux-foundation.org>,
	Ioana Ciornei <ioana.ciornei@nxp.com>,
	Gerald Schaefer <gerald.schaefer@linux.ibm.com>,
	Robin Murphy <robin.murphy@arm.com>,
	Christoph Hellwig <hch@lst.de>
Subject: Re: DPAA2 triggers, [PATCH] dma debug: report -EEXIST errors in add_dma_entry
Date: Mon, 11 Oct 2021 13:47:06 +0200	[thread overview]
Message-ID: <20211011114706.GA16350@lst.de> (raw)
In-Reply-To: <fd4a2d8d-3f9d-51f3-1c86-8009ad50e6a1@linux.ibm.com>

On Thu, Oct 07, 2021 at 12:59:32PM +0200, Karsten Graul wrote:
> In our case its really that a buffer is mapped twice for 2 different devices which we use in SMC to provide failover capabilities. We see that -EEXIST is returned when a buffer is mapped for the second device. Since there is a maximum of 2 parallel mappings we never see the warning shown by active_cacheline_inc_overlap() because we don't exceed ACTIVE_CACHELINE_MAX_OVERLAP.

Mapping something twice is possible, but needs special care.
Basically one device always needs to do the first mapping and the other
one needs to use DMA_ATTR_SKIP_CPU_SYNC to opt out of the coherency
protocol.  So we have two TODO items here: 1) the driver needs to use the
above scheme and 2) this dma-debug check needs to understand
DMA_ATTR_SKIP_CPU_SYNC.  Can I trick you into doing both?
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

  parent reply	other threads:[~2021-10-11 11:47 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-18 12:54 [PATCH] dma debug: report -EEXIST errors in add_dma_entry Hamza Mahfooz
2021-05-18 12:54 ` Hamza Mahfooz
2021-06-22  7:41 ` Christoph Hellwig
2021-06-22  7:41   ` Christoph Hellwig
2021-09-09  3:33 ` DPAA2 triggers, " Jeremy Linton
2021-09-09  3:33   ` Jeremy Linton
2021-09-09 21:16   ` Ioana Ciornei
2021-09-09 21:16     ` Ioana Ciornei
2021-09-10 10:23   ` Christoph Hellwig
2021-09-10 10:23     ` Christoph Hellwig
2021-09-14 15:45   ` Ioana Ciornei
2021-09-14 15:45     ` Ioana Ciornei
2021-09-30 13:37     ` Karsten Graul
2021-09-30 13:37       ` Karsten Graul
2021-10-01 12:52       ` Gerald Schaefer
2021-10-01 12:52         ` Gerald Schaefer
2021-10-06 13:10         ` Gerald Schaefer
2021-10-06 13:10           ` Gerald Schaefer
2021-10-06 13:21           ` Gerald Schaefer
2021-10-06 13:21             ` Gerald Schaefer
2021-10-06 14:23           ` Robin Murphy
2021-10-06 14:23             ` Robin Murphy
2021-10-06 15:06             ` Gerald Schaefer
2021-10-06 15:06               ` Gerald Schaefer
2021-10-07 10:59             ` Karsten Graul
2021-10-07 10:59               ` Karsten Graul
2021-10-07 16:40               ` Gerald Schaefer
2021-10-07 16:40                 ` Gerald Schaefer
2021-10-11 11:47               ` Christoph Hellwig [this message]
2021-10-11 11:47                 ` Christoph Hellwig
2021-10-01  4:19     ` Christoph Hellwig
2021-10-01  4:19       ` Christoph Hellwig
2021-10-01  9:21       ` Ioana Ciornei
2021-10-01  9:21         ` Ioana Ciornei

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=20211011114706.GA16350@lst.de \
    --to=hch@lst.de \
    --cc=dan.j.williams@intel.com \
    --cc=gerald.schaefer@linux.ibm.com \
    --cc=ioana.ciornei@nxp.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jeremy.linton@arm.com \
    --cc=kgraul@linux.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=m.szyprowski@samsung.com \
    --cc=netdev@vger.kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=someguy@effective-light.com \
    /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.