<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdkfd, branch v4.6</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=v4.6</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v4.6'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2016-03-22T22:36:02Z</updated>
<entry>
<title>drivers/gpu/drm/amd/amdkfd: use in_compat_syscall to check open() caller type</title>
<updated>2016-03-22T22:36:02Z</updated>
<author>
<name>Andy Lutomirski</name>
<email>luto@kernel.org</email>
</author>
<published>2016-03-22T21:25:19Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=10f1685fd59d4ded226123550bdaef176b99f65f'/>
<id>urn:sha1:10f1685fd59d4ded226123550bdaef176b99f65f</id>
<content type='text'>
amdkfd wants to know syscall type, not task type.  Check directly.

Unfortunately, amdkfd is making nasty assumptions that a process'
bitness is a well-defined constant thing.  This isn't the case on x86.
I don't know how much this matters, but this patch has no effect on
generated code on x86, so amdkfd is equally broken with and without this
patch.

Signed-off-by: Andy Lutomirski &lt;luto@kernel.org&gt;
Cc: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Cc: David Airlie &lt;airlied@linux.ie&gt;
Signed-off-by: Andrew Morton &lt;akpm@linux-foundation.org&gt;
Signed-off-by: Linus Torvalds &lt;torvalds@linux-foundation.org&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: uninitialized variable in dbgdev_wave_control_set_registers()</title>
<updated>2016-03-15T12:09:37Z</updated>
<author>
<name>Dan Carpenter</name>
<email>dan.carpenter@oracle.com</email>
</author>
<published>2016-03-11T07:51:51Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=93fce954427effee89e44a976299b15dd75b4bbc'/>
<id>urn:sha1:93fce954427effee89e44a976299b15dd75b4bbc</id>
<content type='text'>
At the end of the function we expect "status" to be zero, but it's
either -EINVAL or uninitialized.

Fixes: 788bf83db301 ('drm/amdkfd: Add wave control operation to debugger')
Signed-off-by: Dan Carpenter &lt;dan.carpenter@oracle.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Track when module's init is complete</title>
<updated>2016-02-27T20:52:40Z</updated>
<author>
<name>Oded Gabbay</name>
<email>oded.gabbay@gmail.com</email>
</author>
<published>2016-02-13T08:14:07Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=c68f4528a2e984d044a5f6ad1c5eca7bba9b3b4c'/>
<id>urn:sha1:c68f4528a2e984d044a5f6ad1c5eca7bba9b3b4c</id>
<content type='text'>
Current dependencies between amdkfd and radeon/amdgpu force the loading
of amdkfd _before_ radeon and/or amdgpu are loaded. When all these kernel
drivers are built as modules, this ordering is enforced by the kernel
built-in mechanism of loading dependent modules.

However, there is no such mechanism in case where all these drivers are
compiled inside the kernel image (not as modules). The current way to
enforce loading of amdkfd before radeon/amdgpu, is to put amdkfd before
radeon/amdgpu in the drm Makefile, but that method is way too fragile.

In addition, there is no kernel mechanism to check whether a kernel
driver that is built inside the kernel image, has already been loaded.

To solve this, this patch adds to kfd_module.c a new static variable,
amdkfd_init_completed, that is set to 1 only when amdkfd's
module initialization function has been completed (successfully).

kgd2kfd_init(), which is the initialization function of the
kgd--&gt;kfd interface, and which is the first function in amdkfd called by
radeon/amdgpu, will return successfully only if amdkfd_init_completed is
equal 1.

If amdkfd_init_completed is not equal to 1, kgd2kfd_init() will
return -EPROBE_DEFER to signal radeon/amdgpu they need to defer
their loading until amdkfd is loaded.

Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Remove unnecessary cast in kfree</title>
<updated>2016-01-28T12:40:11Z</updated>
<author>
<name>Amitoj Kaur Chawla</name>
<email>amitoj1606@gmail.com</email>
</author>
<published>2016-01-25T17:33:57Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=642f0f2a1563b5ab6f5de896f602177ac1f06652'/>
<id>urn:sha1:642f0f2a1563b5ab6f5de896f602177ac1f06652</id>
<content type='text'>
Remove an unnecassary cast in the argument to kfree.

Found using Coccinelle. The semantic patch used to find this is as follows:

//&lt;smpl&gt;
@@
type T;
expression *f;
@@

- kfree((T *)(f));
+ kfree(f);
//&lt;/smpl&gt;

Signed-off-by: Amitoj Kaur Chawla &lt;amitoj1606@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>amdkfd: Copy from the proper user command pointer</title>
<updated>2016-01-15T20:14:17Z</updated>
<author>
<name>Borislav Petkov</name>
<email>bp@suse.de</email>
</author>
<published>2016-01-15T18:26:44Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=39c01bf933106296e43e46cdbd9edce13ae5a5b7'/>
<id>urn:sha1:39c01bf933106296e43e46cdbd9edce13ae5a5b7</id>
<content type='text'>
8f1d57c17248 ("amdkfd: don't open-code memdup_user()") mistakenly uses
an uninitialized local pointer, gcc complains:

  drivers/gpu/drm/amd/amdkfd/kfd_chardev.c: In function ‘kfd_ioctl_dbg_address_watch’:
  drivers/gpu/drm/amd/amdkfd/kfd_chardev.c:562:12: warning: ‘args_buff’ may be used uninitialized in this function [-Wmaybe-uninitialized]
    args_buff = memdup_user(args_buff,
                ^

Fix it.

Signed-off-by: Borislav Petkov &lt;bp@suse.de&gt;
Cc: Al Viro &lt;viro@zeniv.linux.org.uk&gt;
Signed-off-by: Al Viro &lt;viro@zeniv.linux.org.uk&gt;
</content>
</entry>
<entry>
<title>amdkfd: don't open-code memdup_user()</title>
<updated>2016-01-06T13:25:25Z</updated>
<author>
<name>Al Viro</name>
<email>viro@zeniv.linux.org.uk</email>
</author>
<published>2016-01-02T20:06:19Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=8f1d57c172482c9a1568ec647fc5c2e64c6c6a57'/>
<id>urn:sha1:8f1d57c172482c9a1568ec647fc5c2e64c6c6a57</id>
<content type='text'>
Signed-off-by: Al Viro &lt;viro@zeniv.linux.org.uk&gt;
</content>
</entry>
<entry>
<title>amdkfd: use &lt;linux/mman.h&gt; instead of &lt;uapi/asm-generic/mman-common.h&gt;</title>
<updated>2015-08-30T09:36:58Z</updated>
<author>
<name>Christoph Hellwig</name>
<email>hch@lst.de</email>
</author>
<published>2015-08-28T07:27:16Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=2497ee721524be80a7690dac0956d04c0ee954f0'/>
<id>urn:sha1:2497ee721524be80a7690dac0956d04c0ee954f0</id>
<content type='text'>
The latter is a default version of &lt;asm/mman.h&gt; and not for driver use.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: fix bug when initializing sdma vm</title>
<updated>2015-07-30T06:26:15Z</updated>
<author>
<name>Oded Gabbay</name>
<email>oded.gabbay@gmail.com</email>
</author>
<published>2015-07-29T07:40:26Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=a63c580a5271b61f12cf91e768120e33792e2907'/>
<id>urn:sha1:a63c580a5271b61f12cf91e768120e33792e2907</id>
<content type='text'>
A logical AND operation was used during mask and shift, instead of a
bitwise AND operation. This patch fixes this bug by changing the
operation to bitwise AND.

Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Set correct doorbell packet type for Carrizo</title>
<updated>2015-07-20T06:16:49Z</updated>
<author>
<name>Ben Goz</name>
<email>ben.goz@amd.com</email>
</author>
<published>2015-06-06T21:15:51Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=7639a8c420f04ca9be87974416efb2848b0962d9'/>
<id>urn:sha1:7639a8c420f04ca9be87974416efb2848b0962d9</id>
<content type='text'>
Signed-off-by: Ben Goz &lt;ben.goz@amd.com&gt;
Reviewed-by: Yair Shachar &lt;yair.shachar@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Use generic defines in new amd headers</title>
<updated>2015-07-20T06:16:49Z</updated>
<author>
<name>Oded Gabbay</name>
<email>oded.gabbay@gmail.com</email>
</author>
<published>2015-06-06T18:47:01Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=3d30b28be811b0d7c0a113eab361d5e3029d6da4'/>
<id>urn:sha1:3d30b28be811b0d7c0a113eab361d5e3029d6da4</id>
<content type='text'>
This patch makes use of the new amd headers (that are part of the new
amdgpu driver), instead of private defines.

Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
</feed>
