<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/linux.git/drivers/gpu/drm/amd/amdkfd, branch v4.18.18</title>
<subtitle>Linux kernel stable tree (mirror)</subtitle>
<id>https://git.radix-linux.su/kernel/linux.git/atom?h=v4.18.18</id>
<link rel='self' href='https://git.radix-linux.su/kernel/linux.git/atom?h=v4.18.18'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/'/>
<updated>2018-10-18T07:18:17+00:00</updated>
<entry>
<title>drm/amdkfd: Fix ATS capablity was not reported correctly on some APUs</title>
<updated>2018-10-18T07:18:17+00:00</updated>
<author>
<name>Yong Zhao</name>
<email>Yong.Zhao@amd.com</email>
</author>
<published>2018-09-13T01:42:20+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=3792c002b9ff85cd8551f36a8886d9ca0e3bcf8f'/>
<id>urn:sha1:3792c002b9ff85cd8551f36a8886d9ca0e3bcf8f</id>
<content type='text'>
[ Upstream commit 44d8cc6f1a905e4bb1d4221a898abb0d7e9d100a ]

Because CRAT_CU_FLAGS_IOMMU_PRESENT was not set in some BIOS crat, we
need to workaround this.

For future compatibility, we also overwrite the bit in capability according
to the value of needs_iommu_device.

Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Yong Zhao &lt;Yong.Zhao@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Sasha Levin &lt;alexander.levin@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Change the control stack MTYPE from UC to NC on GFX9</title>
<updated>2018-10-18T07:18:17+00:00</updated>
<author>
<name>Yong Zhao</name>
<email>yong.zhao@amd.com</email>
</author>
<published>2018-09-13T01:42:19+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=c2fd5b21cbd9fc777fde1509a3e709450094b1ba'/>
<id>urn:sha1:c2fd5b21cbd9fc777fde1509a3e709450094b1ba</id>
<content type='text'>
[ Upstream commit 15426dbb65c5b37680d27e84d58a1ed3b8532518 ]

CWSR fails on Raven if the control stack is MTYPE_UC, which is used
for regular GART mappings. As a workaround we map it using MTYPE_NC.

The MEC firmware expects the control stack at one page offset from the
start of the MQD so it is part of the MQD allocation on GFXv9. AMDGPU
added a memory allocation flag just for this purpose.

Acked-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Yong Zhao &lt;yong.zhao@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Sasha Levin &lt;alexander.levin@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Fix error codes in kfd_get_process</title>
<updated>2018-09-26T06:39:41+00:00</updated>
<author>
<name>Wei Lu</name>
<email>wei.lu2@amd.com</email>
</author>
<published>2018-07-12T02:32:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=1950f800faa1981d48535322ee68e9131d4ddff4'/>
<id>urn:sha1:1950f800faa1981d48535322ee68e9131d4ddff4</id>
<content type='text'>
[ Upstream commit e47cb828eb3fca3e8999a0b9aa053dda18552071 ]

Return ERR_PTR(-EINVAL) if kfd_get_process fails to find the process.
This fixes kernel oopses when a child process calls KFD ioctls with
a file descriptor inherited from the parent process.

Signed-off-by: Wei Lu &lt;wei.lu2@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Sasha Levin &lt;alexander.levin@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Fix kernel queue 64 bit doorbell offset calculation</title>
<updated>2018-09-26T06:39:41+00:00</updated>
<author>
<name>Shaoyun Liu</name>
<email>Shaoyun.Liu@amd.com</email>
</author>
<published>2018-07-12T02:33:01+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=4841f051b32c4ff0029dd84bdd9456b8b09dd1be'/>
<id>urn:sha1:4841f051b32c4ff0029dd84bdd9456b8b09dd1be</id>
<content type='text'>
[ Upstream commit 951df6d9cfd07f205f1905bf3b27d994612e0614 ]

The bitmap index calculation should reverse the logic used on allocation
so it will clear the same bit used on allocation

Signed-off-by: Shaoyun Liu &lt;Shaoyun.Liu@amd.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Sasha Levin &lt;alexander.levin@microsoft.com&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>Merge tag 'drm-amdkfd-next-2018-05-14' of git://people.freedesktop.org/~gabbayo/linux into drm-next</title>
<updated>2018-05-15T06:06:08+00:00</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2018-05-15T05:59:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=c76f0b2cc2f1be1a8a20f0fe2c0f30919bc559fb'/>
<id>urn:sha1:c76f0b2cc2f1be1a8a20f0fe2c0f30919bc559fb</id>
<content type='text'>
This is amdkfd pull for 4.18. The major new features are:

- Add support for GFXv9 dGPUs (VEGA)
- Add support for userptr memory mapping

In addition, there are a couple of small fixes and improvements, such as:
- Fix lock handling
- Fix rollback packet in kernel kfd_queue
- Optimize kfd signal handling
- Fix CP hang in APU

Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20180514070126.GA1827@odedg-x270
</content>
</entry>
<entry>
<title>drm/amdkfd: fix build, select MMU_NOTIFIER</title>
<updated>2018-04-24T09:50:04+00:00</updated>
<author>
<name>Randy Dunlap</name>
<email>rdunlap@infradead.org</email>
</author>
<published>2018-04-14T02:49:28+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=7bbc0b950f34bf11c26a32b6beb927777e7f3b93'/>
<id>urn:sha1:7bbc0b950f34bf11c26a32b6beb927777e7f3b93</id>
<content type='text'>
When CONFIG_MMU_NOTIFIER is not enabled, struct mmu_notifier has an
incomplete type definition, which causes build errors.

../drivers/gpu/drm/amd/amdkfd/kfd_priv.h:607:22: error: field 'mmu_notifier' has incomplete type
../include/linux/kernel.h:979:32: error: dereferencing pointer to incomplete type
../include/linux/kernel.h:980:18: error: dereferencing pointer to incomplete type
../drivers/gpu/drm/amd/amdkfd/kfd_process.c:434:2: error: implicit declaration of function 'mmu_notifier_unregister_no_release' [-Werror=implicit-function-declaration]
../drivers/gpu/drm/amd/amdkfd/kfd_process.c:435:2: error: implicit declaration of function 'mmu_notifier_call_srcu' [-Werror=implicit-function-declaration]
../drivers/gpu/drm/amd/amdkfd/kfd_process.c:438:21: error: variable 'kfd_process_mmu_notifier_ops' has initializer but incomplete type
../drivers/gpu/drm/amd/amdkfd/kfd_process.c:439:2: error: unknown field 'release' specified in initializer
../drivers/gpu/drm/amd/amdkfd/kfd_process.c:439:2: warning: excess elements in struct initializer [enabled by default]
../drivers/gpu/drm/amd/amdkfd/kfd_process.c:439:2: warning: (near initialization for 'kfd_process_mmu_notifier_ops') [enabled by default]
../drivers/gpu/drm/amd/amdkfd/kfd_process.c:534:2: error: implicit declaration of function 'mmu_notifier_register' [-Werror=implicit-function-declaration]

Signed-off-by: Randy Dunlap &lt;rdunlap@infradead.org&gt;
Tested-by: Anders Roxell &lt;anders.roxell@linaro.org&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: fix clock counter retrieval for node without GPU</title>
<updated>2018-04-24T09:34:44+00:00</updated>
<author>
<name>Andres Rodriguez</name>
<email>andres.rodriguez@amd.com</email>
</author>
<published>2018-04-10T21:32:33+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=1cf6cc74bbeb85bb87c3ca3f3df97a283c3aa737'/>
<id>urn:sha1:1cf6cc74bbeb85bb87c3ca3f3df97a283c3aa737</id>
<content type='text'>
Currently if a user requests clock counters for a node without a GPU
resource we will always return EINVAL.

Instead if no GPU resource is attached, fill the gpu_clock_counter
argument with zeroes so that we may proceed and return valid CPU
counters.

Signed-off-by: Andres Rodriguez &lt;andres.rodriguez@amd.com&gt;
Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Fix the error return code in kfd_ioctl_unmap_memory_from_gpu()</title>
<updated>2018-04-24T09:14:55+00:00</updated>
<author>
<name>Wei Yongjun</name>
<email>weiyongjun1@huawei.com</email>
</author>
<published>2018-03-30T02:25:17+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=ded5e5622c38f6d0188c776bfd6793e1cdbb7606'/>
<id>urn:sha1:ded5e5622c38f6d0188c776bfd6793e1cdbb7606</id>
<content type='text'>
Passing NULL pointer to PTR_ERR will result in return value of 0
indicating success which is clearly not what it is intended here.
This patch returns -EINVAL instead.

v2: change ret code to -ENODEV

Fixes: 5ec7e02854b3 ("drm/amdkfd: Add ioctls for GPUVM memory management")
Signed-off-by: Wei Yongjun &lt;weiyongjun1@huawei.com&gt;
Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: kfd_dev_is_large_bar() can be static</title>
<updated>2018-04-24T09:05:27+00:00</updated>
<author>
<name>kbuild test robot</name>
<email>fengguang.wu@intel.com</email>
</author>
<published>2018-03-27T16:55:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=a4efd3a4e685df239805ebd57f546904d5821114'/>
<id>urn:sha1:a4efd3a4e685df239805ebd57f546904d5821114</id>
<content type='text'>
Fixes: 5ec7e02854b3 ("drm/amdkfd: Add ioctls for GPUVM memory management")
Signed-off-by: Fengguang Wu &lt;fengguang.wu@intel.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Remove vla</title>
<updated>2018-04-13T21:24:12+00:00</updated>
<author>
<name>Laura Abbott</name>
<email>labbott@redhat.com</email>
</author>
<published>2018-04-13T21:24:12+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=af47b390273f1068bdb1d01263a81948c4e2f97a'/>
<id>urn:sha1:af47b390273f1068bdb1d01263a81948c4e2f97a</id>
<content type='text'>
There's an ongoing effort to remove VLAs[1] from the kernel to eventually
turn on -Wvla. Switch to a constant value that covers all hardware.

[1] https://lkml.org/lkml/2018/3/7/621

Reviewed-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Laura Abbott &lt;labbott@redhat.com&gt;
Signed-off-by: Oded Gabbay &lt;oded.gabbay@gmail.com&gt;
</content>
</entry>
</feed>
