<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/kernel/dma/mapping.c, branch v5.14</title>
<subtitle>Mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/
</subtitle>
<id>https://git.shady.money/linux/atom?h=v5.14</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v5.14'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2021-03-15T09:02:31Z</updated>
<entry>
<title>dma-mapping: add a dma_alloc_noncontiguous API</title>
<updated>2021-03-15T09:02:31Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2021-01-28T13:54:18Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=7d5b5738d1514e9dd8ed452660e2a4d25beb9483'/>
<id>urn:sha1:7d5b5738d1514e9dd8ed452660e2a4d25beb9483</id>
<content type='text'>
Add a new API that returns a potentiall virtually non-contigous sg_table
and a DMA address.  This API is only properly implemented for dma-iommu
and will simply return a contigious chunk as a fallback.

The intent is that drivers can use this API if either:

 - no kernel mapping or only temporary kernel mappings are required.
   That is as a better replacement for DMA_ATTR_NO_KERNEL_MAPPING
 - a kernel mapping is required for cached and DMA mapped pages, but
   the driver also needs the pages to e.g. map them to userspace.
   In that sense it is a replacement for some aspects of the recently
   removed and never fully implemented DMA_ATTR_NON_CONSISTENT

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
Reviewed-by: Tomasz Figa &lt;tfiga@chromium.org&gt;
Tested-by: Ricardo Ribalda &lt;ribalda@chromium.org&gt;
</content>
</entry>
<entry>
<title>dma-mapping: refactor dma_{alloc,free}_pages</title>
<updated>2021-03-15T09:02:31Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2021-02-01T17:12:02Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=198c50e2ccff5c78ddbe0cb01593ac32458deb69'/>
<id>urn:sha1:198c50e2ccff5c78ddbe0cb01593ac32458deb69</id>
<content type='text'>
Factour out internal versions without the dma_debug calls in preparation
for callers that will need different dma_debug calls.

Note that this changes the dma_debug calls to get the not page aligned
size values, but as long as alloc and free agree on one variant we are
fine.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
Reviewed-by: Tomasz Figa &lt;tfiga@chromium.org&gt;
Tested-by: Ricardo Ribalda &lt;ribalda@chromium.org&gt;
</content>
</entry>
<entry>
<title>dma-mapping: add a dma_mmap_pages helper</title>
<updated>2021-03-15T09:02:31Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2021-01-28T13:53:22Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=eedb0b12d091a21909b5e84d9f3e5e649305bd12'/>
<id>urn:sha1:eedb0b12d091a21909b5e84d9f3e5e649305bd12</id>
<content type='text'>
Add a helper to map memory allocated using dma_alloc_pages into
a user address space, similar to the dma_alloc_attrs function for
coherent allocations.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
Reviewed-by: Tomasz Figa &lt;tfiga@chromium.org&gt;
Tested-by: Ricardo Ribalda &lt;ribalda@chromium.org&gt;
</content>
</entry>
<entry>
<title>Merge tag 'dma-mapping-5.12' of git://git.infradead.org/users/hch/dma-mapping</title>
<updated>2021-02-24T17:54:24Z</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2021-02-24T17:54:24Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=a4dec04c7ff4307973ba502ce7b27330d9fe04b7'/>
<id>urn:sha1:a4dec04c7ff4307973ba502ce7b27330d9fe04b7</id>
<content type='text'>
Pull dma-mapping updates from Christoph Hellwig:

 - add support to emulate processing delays in the DMA API benchmark
   selftest (Barry Song)

 - remove support for non-contiguous noncoherent allocations, which
   aren't used and will be replaced by a different API

* tag 'dma-mapping-5.12' of git://git.infradead.org/users/hch/dma-mapping:
  dma-mapping: remove the {alloc,free}_noncoherent methods
  dma-mapping: benchmark: pretend DMA is transmitting
</content>
</entry>
<entry>
<title>driver core: lift dma_default_coherent into common code</title>
<updated>2021-02-13T08:51:45Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2021-02-10T09:56:39Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=6d4e9a8efe3d59f31367d79e970c2f328da139a4'/>
<id>urn:sha1:6d4e9a8efe3d59f31367d79e970c2f328da139a4</id>
<content type='text'>
Lift the dma_default_coherent variable from the mips architecture code
to the driver core.  This allows an architecture to sdefault all device
to be DMA coherent at run time, even if the kernel is build with support
for DMA noncoherent device.  By allowing device_initialize to set the
-&gt;dma_coherent field to this default the amount of arch hooks required
for this behavior can be greatly reduced.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
Acked-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
Signed-off-by: Thomas Bogendoerfer &lt;tsbogend@alpha.franken.de&gt;
</content>
</entry>
<entry>
<title>dma-mapping: remove the {alloc,free}_noncoherent methods</title>
<updated>2021-02-09T17:01:38Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2020-11-24T15:38:40Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=81d88ce55092edf1a1f928efb373f289c6b90efd'/>
<id>urn:sha1:81d88ce55092edf1a1f928efb373f289c6b90efd</id>
<content type='text'>
It turns out allowing non-contigous allocations here was a rather bad
idea, as we'll now need to define ways to get the pages for mmaping
or dma_buf sharing.  Revert this change and stick to the original
concept.  A different API for the use case of non-contigous allocations
will be added back later.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
Reviewed-by: Tomasz Figa &lt;tfiga@chromium.org&gt;
Tested-by: Ricardo Ribalda &lt;ribalda@chromium.org&gt;:wq
</content>
</entry>
<entry>
<title>dma-mapping: Allow mixing bypass and mapped DMA operation</title>
<updated>2020-11-27T09:33:40Z</updated>
<author>
<name>Alexey Kardashevskiy</name>
<email>aik@ozlabs.ru</email>
</author>
<published>2020-10-29T01:52:40Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=8d8d53cf8fd028310b1189165b939cde124895d7'/>
<id>urn:sha1:8d8d53cf8fd028310b1189165b939cde124895d7</id>
<content type='text'>
At the moment we allow bypassing DMA ops only when we can do this for
the entire RAM. However there are configs with mixed type memory
where we could still allow bypassing IOMMU in most cases;
POWERPC with persistent memory is one example.

This adds an arch hook to determine where bypass can still work and
we invoke direct DMA API. The following patch checks the bus limit
on POWERPC to allow or disallow direct mapping.

This adds a ARCH_HAS_DMA_MAP_DIRECT config option to make the arch_xxxx
hooks no-op by default.

Signed-off-by: Alexey Kardashevskiy &lt;aik@ozlabs.ru&gt;
Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
</content>
</entry>
<entry>
<title>dma-mapping: move large parts of &lt;linux/dma-direct.h&gt; to kernel/dma</title>
<updated>2020-10-06T05:07:06Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2020-09-22T13:34:22Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=19c65c3d30bb5a97170e425979d2e44ab2096c7d'/>
<id>urn:sha1:19c65c3d30bb5a97170e425979d2e44ab2096c7d</id>
<content type='text'>
Most of the dma_direct symbols should only be used by direct.c and
mapping.c, so move them to kernel/dma.  In fact more of dma-direct.h
should eventually move, but that will require more coordination with
other subsystems.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
</content>
</entry>
<entry>
<title>dma-mapping: move dma-debug.h to kernel/dma/</title>
<updated>2020-10-06T05:07:05Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2020-09-11T08:12:44Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=a1fd09e8e6ae35228ecc7c1e4bfff1fd725f78a0'/>
<id>urn:sha1:a1fd09e8e6ae35228ecc7c1e4bfff1fd725f78a0</id>
<content type='text'>
Most of dma-debug.h is not required by anything outside of kernel/dma.
Move the four declarations needed by dma-mappin.h or dma-ops providers
into dma-mapping.h and dma-map-ops.h, and move the remainder of the
file to kernel/dma/debug.h.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
</content>
</entry>
<entry>
<title>dma-mapping: split &lt;linux/dma-mapping.h&gt;</title>
<updated>2020-10-06T05:07:03Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2020-09-22T13:31:03Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=0a0f0d8be76dcd4390ff538e7060fda34db79717'/>
<id>urn:sha1:0a0f0d8be76dcd4390ff538e7060fda34db79717</id>
<content type='text'>
Split out all the bits that are purely for dma_map_ops implementations
and related code into a new &lt;linux/dma-map-ops.h&gt; header so that they
don't get pulled into all the drivers.  That also means the architecture
specific &lt;asm/dma-mapping.h&gt; is not pulled in by &lt;linux/dma-mapping.h&gt;
any more, which leads to a missing includes that were pulled in by the
x86 or arm versions in a few not overly portable drivers.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
</content>
</entry>
</feed>
