<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c, branch v5.4.209</title>
<subtitle>Linux kernel stable tree (mirror)</subtitle>
<id>https://git.radix-linux.su/kernel/linux.git/atom?h=v5.4.209</id>
<link rel='self' href='https://git.radix-linux.su/kernel/linux.git/atom?h=v5.4.209'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/'/>
<updated>2022-05-12T10:23:47+00:00</updated>
<entry>
<title>drm/amdkfd: Use drm_priv to pass VM from KFD to amdgpu</title>
<updated>2022-05-12T10:23:47+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2021-04-07T22:19:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=89e7a625ec5c71a06214b6cc4fbc9fbc6115fa6a'/>
<id>urn:sha1:89e7a625ec5c71a06214b6cc4fbc9fbc6115fa6a</id>
<content type='text'>
commit b40a6ab2cf9213923bf8e821ce7fa7f6a0a26990 upstream.

amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu needs the drm_priv to allow mmap
to access the BO through the corresponding file descriptor. The VM can
also be extracted from drm_priv, so drm_priv can replace the vm parameter
in the kfd2kgd interface.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Philip Yang &lt;philip.yang@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
[This is a partial cherry-pick of the upstream commit.]
Signed-off-by: Lee Jones &lt;lee.jones@linaro.org&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: use allowed domain for vmbo validation</title>
<updated>2021-07-19T06:53:10+00:00</updated>
<author>
<name>Nirmoy Das</name>
<email>nirmoy.das@amd.com</email>
</author>
<published>2021-06-08T11:23:44+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=2c028cee95a46e24a07616adfcc697bc86e249a8'/>
<id>urn:sha1:2c028cee95a46e24a07616adfcc697bc86e249a8</id>
<content type='text'>
[ Upstream commit bc05716d4fdd065013633602c5960a2bf1511b9c ]

Fixes handling when page tables are in system memory.

v3: remove struct amdgpu_vm_parser.
v2: remove unwanted variable.
    change amdgpu_amdkfd_validate instead of amdgpu_amdkfd_bo_validate.

Signed-off-by: Nirmoy Das &lt;nirmoy.das@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-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;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: fix restore worker race condition</title>
<updated>2020-10-01T11:18:03+00:00</updated>
<author>
<name>Philip Yang</name>
<email>Philip.Yang@amd.com</email>
</author>
<published>2020-05-21T13:56:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=62962e08b9c33adec71340bf1eb3429702e20457'/>
<id>urn:sha1:62962e08b9c33adec71340bf1eb3429702e20457</id>
<content type='text'>
[ Upstream commit f7646585a30ed8ef5ab300d4dc3b0c1d6afbe71d ]

In free memory of gpu path, remove bo from validate_list to make sure
restore worker don't access the BO any more, then unregister bo MMU
interval notifier. Otherwise, the restore worker will crash in the
middle of validating BO user pages if MMU interval notifer is gone.

Signed-off-by: Philip Yang &lt;Philip.Yang@amd.com&gt;
Reviewed-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;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: Use GEM obj reference for KFD BOs</title>
<updated>2020-06-03T06:21:11+00:00</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2020-05-05T18:02:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=336292c44f622565c4b9815dff975ea565b5e893'/>
<id>urn:sha1:336292c44f622565c4b9815dff975ea565b5e893</id>
<content type='text'>
[ Upstream commit 39b3128d7ffd44e400e581e6f49e88cb42bef9a1 ]

Releasing the AMDGPU BO ref directly leads to problems when BOs were
exported as DMA bufs. Releasing the GEM reference makes sure that the
AMDGPU/TTM BO is not freed too early.

Also take a GEM reference when importing BOs from DMABufs to keep
references to imported BOs balances properly.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Tested-by: Alex Sierra &lt;alex.sierra@amd.com&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Alex Sierra &lt;alex.sierra@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>drm/amdgpu: untag user pointers</title>
<updated>2019-09-26T00:51:41+00:00</updated>
<author>
<name>Andrey Konovalov</name>
<email>andreyknvl@google.com</email>
</author>
<published>2019-09-25T23:48:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=35f3fc87bebfb2fffc1a9cdaf661ee3f95c2a5f1'/>
<id>urn:sha1:35f3fc87bebfb2fffc1a9cdaf661ee3f95c2a5f1</id>
<content type='text'>
This patch is a part of a series that extends kernel ABI to allow to pass
tagged user pointers (with the top byte set to something else other than
0x00) as syscall arguments.

In amdgpu_gem_userptr_ioctl() and amdgpu_amdkfd_gpuvm.c/init_user_pages()
an MMU notifier is set up with a (tagged) userspace pointer.  The untagged
address should be used so that MMU notifiers for the untagged address get
correctly matched up with the right BO.  This patch untag user pointers in
amdgpu_gem_userptr_ioctl() for the GEM case and in amdgpu_amdkfd_gpuvm_
alloc_memory_of_gpu() for the KFD case.  This also makes sure that an
untagged pointer is passed to amdgpu_ttm_tt_get_user_pages(), which uses
it for vma lookups.

Link: http://lkml.kernel.org/r/d684e1df08f2ecb6bc292e222b64fa9efbc26e69.1563904656.git.andreyknvl@google.com
Signed-off-by: Andrey Konovalov &lt;andreyknvl@google.com&gt;
Reviewed-by: Kees Cook &lt;keescook@chromium.org&gt;
Suggested-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Acked-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Cc: Al Viro &lt;viro@zeniv.linux.org.uk&gt;
Cc: Catalin Marinas &lt;catalin.marinas@arm.com&gt;
Cc: Dave Hansen &lt;dave.hansen@intel.com&gt;
Cc: Eric Auger &lt;eric.auger@redhat.com&gt;
Cc: Jens Wiklander &lt;jens.wiklander@linaro.org&gt;
Cc: Khalid Aziz &lt;khalid.aziz@oracle.com&gt;
Cc: Mauro Carvalho Chehab &lt;mchehab+samsung@kernel.org&gt;
Cc: Mike Rapoport &lt;rppt@linux.ibm.com&gt;
Cc: Vincenzo Frascino &lt;vincenzo.frascino@arm.com&gt;
Cc: Will Deacon &lt;will@kernel.org&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>Merge tag 'drm-misc-next-2019-08-19' of git://anongit.freedesktop.org/drm/drm-misc into drm-next</title>
<updated>2019-08-21T06:44:41+00:00</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2019-08-21T05:38:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=5f680625d9765a2f936707465659acac8e44f514'/>
<id>urn:sha1:5f680625d9765a2f936707465659acac8e44f514</id>
<content type='text'>
drm-misc-next for 5.4:

UAPI Changes:

Cross-subsystem Changes:

Core Changes:
  - dma-buf: add reservation_object_fences helper, relax
             reservation_object_add_shared_fence, remove
             reservation_object seq number (and then
             restored)
  - dma-fence: Shrinkage of the dma_fence structure,
               Merge dma_fence_signal and dma_fence_signal_locked,
               Store the timestamp in struct dma_fence in a union with
               cb_list

Driver Changes:
  - More dt-bindings YAML conversions
  - More removal of drmP.h includes
  - dw-hdmi: Support get_eld and various i2s improvements
  - gm12u320: Few fixes
  - meson: Global cleanup
  - panfrost: Few refactors, Support for GPU heap allocations
  - sun4i: Support for DDC enable GPIO
  - New panels: TI nspire, NEC NL8048HL11, LG Philips LB035Q02,
                Sharp LS037V7DW01, Sony ACX565AKM, Toppoly TD028TTEC1
                Toppoly TD043MTEA1

Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
[airlied: fixup dma_resv rename fallout]

From: Maxime Ripard &lt;maxime.ripard@bootlin.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20190819141923.7l2adietcr2pioct@flea
</content>
</entry>
<entry>
<title>dma-buf: Restore seqlock around dma_resv updates</title>
<updated>2019-08-16T11:40:58+00:00</updated>
<author>
<name>Chris Wilson</name>
<email>chris@chris-wilson.co.uk</email>
</author>
<published>2019-08-14T18:24:01+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=b016cd6ed4b772759804e0d6082bd1f5ca63b8ee'/>
<id>urn:sha1:b016cd6ed4b772759804e0d6082bd1f5ca63b8ee</id>
<content type='text'>
This reverts
67c97fb79a7f ("dma-buf: add reservation_object_fences helper")
dd7a7d1ff2f1 ("drm/i915: use new reservation_object_fences helper")
0e1d8083bddb ("dma-buf: further relax reservation_object_add_shared_fence")
5d344f58da76 ("dma-buf: nuke reservation_object seq number")

The scenario that defeats simply grabbing a set of shared/exclusive
fences and using them blissfully under RCU is that any of those fences
may be reallocated by a SLAB_TYPESAFE_BY_RCU fence slab cache. In this
scenario, while keeping the rcu_read_lock we need to establish that no
fence was changed in the dma_resv after a read (or full) memory barrier.

Signed-off-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
Cc: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
Cc: Daniel Vetter &lt;daniel.vetter@ffwll.ch&gt;
Acked-by: Christian König &lt;christian.koenig@amd.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20190814182401.25009-1-chris@chris-wilson.co.uk
</content>
</entry>
<entry>
<title>dma-buf: rename reservation_object to dma_resv</title>
<updated>2019-08-13T07:09:30+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2019-08-11T08:06:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=52791eeec1d9f4a7e7fe08aaba0b1553149d93bc'/>
<id>urn:sha1:52791eeec1d9f4a7e7fe08aaba0b1553149d93bc</id>
<content type='text'>
Be more consistent with the naming of the other DMA-buf objects.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
Link: https://patchwork.freedesktop.org/patch/323401/
</content>
</entry>
<entry>
<title>Merge tag 'drm-next-5.4-2019-08-09' of git://people.freedesktop.org/~agd5f/linux into drm-next</title>
<updated>2019-08-12T04:20:21+00:00</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2019-08-12T04:20:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=e7f7287bf5f746d29f3607178851246a005dd398'/>
<id>urn:sha1:e7f7287bf5f746d29f3607178851246a005dd398</id>
<content type='text'>
drm-next-5.4-2019-08-09:

Same as drm-next-5.4-2019-08-06, but with the
readq/writeq stuff fixed and 5.3-rc3 backmerged.

amdgpu:
- Add navi14 support
- Add navi12 support
- Add Arcturus support
- Enable mclk DPM for Navi
- Misc DC display fixes
- Add perfmon support for DF
- Add scatter/gather display support for Raven
- Improve SMU handling for GPU reset
- RAS support for GFX
- Drop last of drmP.h
- Add support for wiping memory on buffer release
- Allow cursor async updates for fb swaps
- Misc fixes and cleanups

amdkfd:
- Add navi14 support
- Add navi12 support
- Add Arcturus support
- CWSR trap handlers updates for gfx9, 10
- Drop last of drmP.h
- Update MAINTAINERS

radeon:
- Misc fixes and cleanups
- Make kexec more reliable by tearing down the GPU

ttm:
- Add release_notify callback

uapi:
- Add wipe memory on release flag for buffer creation

Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;
[airlied: resolved conflicts with ttm resv moving]
From: Alex Deucher &lt;alexdeucher@gmail.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20190809184807.3381-1-alexander.deucher@amd.com
</content>
</entry>
<entry>
<title>dma-buf: further relax reservation_object_add_shared_fence</title>
<updated>2019-08-10T10:49:28+00:00</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2019-08-05T09:16:12+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=0e1d8083bddb38b7169f6240905422f95d3c31b9'/>
<id>urn:sha1:0e1d8083bddb38b7169f6240905422f95d3c31b9</id>
<content type='text'>
Other cores don't busy wait any more and we removed the last user of checking
the seqno for changes. Drop updating the number for shared fences altogether.

Signed-off-by: Christian König &lt;christian.koenig@amd.com&gt;
Reviewed-by: Chris Wilson &lt;chris@chris-wilson.co.uk&gt;
Link: https://patchwork.freedesktop.org/patch/322379/?series=64837&amp;rev=1
</content>
</entry>
</feed>
