From: Andrew Lunn <andrew@lunn.ch>
To: Robin Murphy <robin.murphy@arm.com>
Cc: Esben Haabendal <esben@geanix.com>,
netdev@vger.kernel.org, YueHaibing <yuehaibing@huawei.com>,
Michal Simek <michal.simek@xilinx.com>,
linux-kernel@vger.kernel.org, Yang Wei <yang.wei9@zte.com.cn>,
Luis Chamberlain <mcgrof@kernel.org>,
"David S. Miller" <davem@davemloft.net>,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH 08/12] net: ll_temac: Fix iommu/swiotlb leak
Date: Fri, 26 Apr 2019 17:37:37 +0200 [thread overview]
Message-ID: <20190426153737.GC4041@lunn.ch> (raw)
In-Reply-To: <0aab6152-82c6-b53f-6b9b-0905995de43a@arm.com>
On Fri, Apr 26, 2019 at 03:43:20PM +0100, Robin Murphy wrote:
> On 26/04/2019 15:21, Andrew Lunn wrote:
> >On Fri, Apr 26, 2019 at 09:32:27AM +0200, Esben Haabendal wrote:
> >>Unmap the actual buffer length, not the amount of data received.
> >
> >Hi Esben
> >
> >The patch Subject does not seem to match the content?
> >
> >Also, there can be performance advantages of just unmapping the
> >received length. The unmap operation does a cache invalidate, which
> >can be expensive. Consider the effort of unmapping a 64 byte ACK vs 9K
> >jumbo frame?
>
> If the size passed to dma_unmap_*() is not the same as was passed to the
> corresponding dma_map_*(), that is fundamentally incorrect use of the API
> and may lead to warnings, resource exhaustion, or possibly even corruption
> and crashes for some DMA API implementations.
>
> If there's a case where you just need to look at a small part of the buffer
> right now, but can unmap the whole thing properly later. then
> dma_sync_single_*() does allow operating on partial buffers. Even better, if
> you're able to recycle buffers in your Rx pool you could potentially replace
> the unmap/map dance altogether with some careful use of sync_single.
Hi Robin
Thanks for the info.
I went back to the driver i was thinking of, and it is using
dma_sync_single_range_for_cpu() for just the received packet length.
Sorry for the mixup.
Andrew
next prev parent reply other threads:[~2019-04-26 15:37 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-26 7:32 [PATCH 00/12] net: ll_temac: x86_64 support Esben Haabendal
2019-04-26 7:32 ` [PATCH 01/12] net: ll_temac: Fix and simplify error handling by using devres functions Esben Haabendal
2019-04-26 7:32 ` [PATCH 02/12] net: ll_temac: Extend support to non-device-tree platforms Esben Haabendal
2019-04-26 13:58 ` Andrew Lunn
2019-04-26 7:32 ` [PATCH 03/12] net: ll_temac: Fix support for 64-bit platforms Esben Haabendal
2019-04-26 18:40 ` Jakub Kicinski
2019-04-26 20:59 ` Andrew Lunn
2019-04-26 21:08 ` Jakub Kicinski
2019-04-26 22:02 ` Andrew Lunn
2019-04-26 22:30 ` Jakub Kicinski
2019-04-27 8:49 ` Esben Haabendal
2019-04-26 7:32 ` [PATCH 04/12] net: ll_temac: Add support for non-native register endianness Esben Haabendal
2019-04-26 7:32 ` [PATCH 05/12] net: ll_temac: Fix support for little-endian platforms Esben Haabendal
2019-04-26 7:32 ` [PATCH 06/12] net: ll_temac: Allow use on x86 platforms Esben Haabendal
2019-04-26 14:05 ` Andrew Lunn
2019-04-26 7:32 ` [PATCH 07/12] net: ll_temac: Support indirect_mutex share within TEMAC IP Esben Haabendal
2019-04-26 14:14 ` Andrew Lunn
2019-04-26 7:32 ` [PATCH 08/12] net: ll_temac: Fix iommu/swiotlb leak Esben Haabendal
2019-04-26 14:21 ` Andrew Lunn
2019-04-26 14:43 ` Robin Murphy
2019-04-26 15:37 ` Andrew Lunn [this message]
2019-04-26 7:32 ` [PATCH 09/12] net: ll_temac: Fix bug causing buffer descriptor overrun Esben Haabendal
2019-04-26 7:32 ` [PATCH 10/12] net: ll_temac: Replace bad usage of msleep() with usleep_range() Esben Haabendal
2019-04-26 14:01 ` Andrew Lunn
2019-04-26 7:32 ` [PATCH 11/12] net: ll_temac: Allow configuration of IRQ coalescing Esben Haabendal
2019-04-26 7:32 ` [PATCH 12/12] net: ll_temac: Enable DMA when ready, not before Esben Haabendal
2019-04-29 8:34 ` [PATCH 00/12] net: ll_temac: x86_64 support Esben Haabendal
2019-04-29 8:34 ` [PATCH 01/12] net: ll_temac: Fix and simplify error handling by using devres functions Esben Haabendal
2019-04-29 8:34 ` [PATCH 02/12] net: ll_temac: Extend support to non-device-tree platforms Esben Haabendal
2019-04-29 8:34 ` [PATCH 03/12] net: ll_temac: Fix support for 64-bit platforms Esben Haabendal
2019-04-29 22:06 ` Andrew Lunn
2019-04-29 8:34 ` [PATCH 04/12] net: ll_temac: Add support for non-native register endianness Esben Haabendal
2019-04-29 8:34 ` [PATCH 05/12] net: ll_temac: Fix support for little-endian platforms Esben Haabendal
2019-04-29 8:34 ` [PATCH 06/12] net: ll_temac: Allow use on x86 platforms Esben Haabendal
2019-04-29 22:06 ` Andrew Lunn
2019-04-29 8:34 ` [PATCH 07/12] net: ll_temac: Support indirect_mutex share within TEMAC IP Esben Haabendal
2019-04-29 22:12 ` Andrew Lunn
2019-04-30 6:54 ` Esben Haabendal
2019-04-29 8:34 ` [PATCH 08/12] net: ll_temac: Fix iommu/swiotlb leak Esben Haabendal
2019-04-29 8:34 ` [PATCH 09/12] net: ll_temac: Fix bug causing buffer descriptor overrun Esben Haabendal
2019-04-29 8:34 ` [PATCH 10/12] net: ll_temac: Replace bad usage of msleep() with usleep_range() Esben Haabendal
2019-04-29 8:34 ` [PATCH 11/12] net: ll_temac: Allow configuration of IRQ coalescing Esben Haabendal
2019-04-29 8:34 ` [PATCH 12/12] net: ll_temac: Enable DMA when ready, not before Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 00/12] net: ll_temac: x86_64 support Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 01/12] net: ll_temac: Fix and simplify error handling by using devres functions Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 02/12] net: ll_temac: Extend support to non-device-tree platforms Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 03/12] net: ll_temac: Fix support for 64-bit platforms Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 04/12] net: ll_temac: Add support for non-native register endianness Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 05/12] net: ll_temac: Fix support for little-endian platforms Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 06/12] net: ll_temac: Allow use on x86 platforms Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 07/12] net: ll_temac: Support indirect_mutex share within TEMAC IP Esben Haabendal
2019-04-30 16:59 ` Andrew Lunn
2019-04-30 7:17 ` [PATCH v3 08/12] net: ll_temac: Fix iommu/swiotlb leak Esben Haabendal
2019-04-30 17:00 ` Andrew Lunn
2019-04-30 7:17 ` [PATCH v3 09/12] net: ll_temac: Fix bug causing buffer descriptor overrun Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 10/12] net: ll_temac: Replace bad usage of msleep() with usleep_range() Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 11/12] net: ll_temac: Allow configuration of IRQ coalescing Esben Haabendal
2019-04-30 7:17 ` [PATCH v3 12/12] net: ll_temac: Enable DMA when ready, not before Esben Haabendal
2019-05-01 18:33 ` [PATCH v3 00/12] net: ll_temac: x86_64 support David Miller
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=20190426153737.GC4041@lunn.ch \
--to=andrew@lunn.ch \
--cc=davem@davemloft.net \
--cc=esben@geanix.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mcgrof@kernel.org \
--cc=michal.simek@xilinx.com \
--cc=netdev@vger.kernel.org \
--cc=robin.murphy@arm.com \
--cc=yang.wei9@zte.com.cn \
--cc=yuehaibing@huawei.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 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).