<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel.git/arch/powerpc/kernel/dma.c, branch linux-2.6.28.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.
</subtitle>
<id>https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-2.6.28.y</id>
<link rel='self' href='https://git.0xinfinity.dev/distro/kernel.git/atom?h=linux-2.6.28.y'/>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/'/>
<updated>2008-12-03T07:24:08Z</updated>
<entry>
<title>powerpc: Fix dma_map_sg() cache flushing on non coherent platforms</title>
<updated>2008-12-03T07:24:08Z</updated>
<author>
<name>Benjamin Herrenschmidt</name>
</author>
<published>2008-11-30T18:53:40Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=2434bbb30e79468c49cff3cff6005236f55ed188'/>
<id>urn:sha1:2434bbb30e79468c49cff3cff6005236f55ed188</id>
<content type='text'>
On PowerPC 4xx or other non cache-coherent platforms, we lost the
appropriate cache flushing in dma_map_sg() when merging the 32 and
64-bit DMA code (commit 4fc665b88a79a45bae8bbf3a05563c27c7337c3d,
"powerpc: Merge 32 and 64-bit dma code").  This restores it.

Signed-off-by: Benjamin Herrenschmidt &lt;benh@kernel.crashing.org&gt;
Acked-by: Becky Bruce &lt;beckyb@kernel.crashing.org&gt;
Signed-off-by: Paul Mackerras &lt;paulus@samba.org&gt;
</content>
</entry>
<entry>
<title>powerpc: Fix DMA offset for non-coherent DMA</title>
<updated>2008-10-13T23:35:26Z</updated>
<author>
<name>Benjamin Herrenschmidt</name>
</author>
<published>2008-10-09T17:06:24Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=8aa2659009714cf5f9ffe7f3e16ccfa8ff0e0d61'/>
<id>urn:sha1:8aa2659009714cf5f9ffe7f3e16ccfa8ff0e0d61</id>
<content type='text'>
After Becky's work we can almost have different DMA offsets
between on-chip devices and PCI. Almost because there's a
problem with the non-coherent DMA code that basically ignores
the programmed offset to use the global one for everything.
This fixes it.

Signed-off-by: Benjamin Herrenschmidt &lt;benh@kernel.crashing.org&gt;
</content>
</entry>
<entry>
<title>powerpc: Merge 32 and 64-bit dma code</title>
<updated>2008-09-24T21:26:45Z</updated>
<author>
<name>Becky Bruce</name>
</author>
<published>2008-09-12T10:34:46Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=4fc665b88a79a45bae8bbf3a05563c27c7337c3d'/>
<id>urn:sha1:4fc665b88a79a45bae8bbf3a05563c27c7337c3d</id>
<content type='text'>
We essentially adopt the 64-bit dma code, with some changes to support
32-bit systems, including HIGHMEM.  dma functions on 32-bit are now
invoked via accessor functions which call the correct op for a device based
on archdata dma_ops.  If there is no archdata dma_ops, this defaults
to dma_direct_ops.

In addition, the dma_map/unmap_page functions are added to dma_ops
because we can't just fall back on map/unmap_single when HIGHMEM is
enabled. In the case of dma_direct_*, we stop using map/unmap_single
and just use the page version - this saves a lot of ugly
ifdeffing.  We leave map/unmap_single in the dma_ops definition,
though, because they are needed by the iommu code, which does not
implement map/unmap_page.  Ideally, going forward, we will completely
eliminate map/unmap_single and just have map/unmap_page, if it's
workable for 64-bit.

Signed-off-by: Becky Bruce &lt;becky.bruce@freescale.com&gt;
Signed-off-by: Kumar Gala &lt;galak@kernel.crashing.org&gt;
</content>
</entry>
<entry>
<title>powerpc: Drop archdata numa_node</title>
<updated>2008-09-24T21:26:43Z</updated>
<author>
<name>Becky Bruce</name>
</author>
<published>2008-09-08T09:09:54Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=8fae0353247530d2124b2419052fa6120462fa99'/>
<id>urn:sha1:8fae0353247530d2124b2419052fa6120462fa99</id>
<content type='text'>
Use the struct device's numa_node instead; use accessor functions
to get/set numa_node.

Signed-off-by: Becky Bruce &lt;becky.bruce@freescale.com&gt;
Signed-off-by: Kumar Gala &lt;galak@kernel.crashing.org&gt;
</content>
</entry>
<entry>
<title>powerpc: Move iommu dma ops from dma.c to dma-iommu.c</title>
<updated>2008-09-24T21:26:42Z</updated>
<author>
<name>Becky Bruce</name>
</author>
<published>2008-09-08T09:09:53Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=8dd0e95206f7c33bed2aed33ac668335174684e8'/>
<id>urn:sha1:8dd0e95206f7c33bed2aed33ac668335174684e8</id>
<content type='text'>
32-bit platforms are about to start using dma.c; move the iommu
dma ops into their own file to make this a bit cleaner.

Signed-off-by: Becky Bruce &lt;becky.bruce@freescale.com&gt;
Signed-off-by: Kumar Gala &lt;galak@kernel.crashing.org&gt;
</content>
</entry>
<entry>
<title>powerpc: Rename dma_64.c to dma.c</title>
<updated>2008-09-24T21:26:41Z</updated>
<author>
<name>Becky Bruce</name>
</author>
<published>2008-09-08T09:09:52Z</published>
<link rel='alternate' type='text/html' href='https://git.0xinfinity.dev/distro/kernel.git/commit/?id=7c05d7e08d907d66b8e18515572f42c71fb709fe'/>
<id>urn:sha1:7c05d7e08d907d66b8e18515572f42c71fb709fe</id>
<content type='text'>
This is in preparation for the merge of the 32 and 64-bit
dma code in arch/powerpc.

Signed-off-by: Becky Bruce &lt;becky.bruce@freescale.com&gt;
Signed-off-by: Kumar Gala &lt;galak@kernel.crashing.org&gt;
</content>
</entry>
</feed>
