<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c, branch v5.4</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=v5.4</id>
<link rel='self' href='https://git.shady.money/linux/atom?h=v5.4'/>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/'/>
<updated>2019-09-26T00:51:41Z</updated>
<entry>
<title>drm/amdgpu: untag user pointers</title>
<updated>2019-09-26T00:51:41Z</updated>
<author>
<name>Andrey Konovalov</name>
<email>andreyknvl@google.com</email>
</author>
<published>2019-09-25T23:48:47Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/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>2019-08-21T06:44:41Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2019-08-21T05:38:43Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/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>2019-08-16T11:40:58Z</updated>
<author>
<name>Chris Wilson</name>
<email>chris@chris-wilson.co.uk</email>
</author>
<published>2019-08-14T18:24:01Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/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>2019-08-13T07:09:30Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2019-08-11T08:06:32Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/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>2019-08-12T04:20:21Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2019-08-12T04:20:21Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/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>2019-08-10T10:49:28Z</updated>
<author>
<name>Christian König</name>
<email>christian.koenig@amd.com</email>
</author>
<published>2019-08-05T09:16:12Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/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>
<entry>
<title>Merge tag 'drm-misc-next-2019-08-08' of git://anongit.freedesktop.org/drm/drm-misc into drm-next</title>
<updated>2019-08-09T06:04:31Z</updated>
<author>
<name>Dave Airlie</name>
<email>airlied@redhat.com</email>
</author>
<published>2019-08-09T06:04:15Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=b0383c0653c4bd2d2732c5767ec8fa223b3d6efd'/>
<id>urn:sha1:b0383c0653c4bd2d2732c5767ec8fa223b3d6efd</id>
<content type='text'>
drm-misc-next for 5.4:

UAPI Changes:
 - HDCP: Add a Content protection type property

Cross-subsystem Changes:

Core Changes:
 - Continue to rework the include dependencies
 - fb: Remove the unused drm_gem_fbdev_fb_create function
 - drm-dp-helper: Make the link rate calculation more tolerant to
                  non-explicitly defined, yet supported, rates
 - fb-helper: Map DRM client buffer only when required, and instanciate a
              shadow buffer when the device has a dirty function or says so
 - connector: Add a helper to link the DDC adapter used by that connector to
              the userspace
 - vblank: Switch from DRM_WAIT_ON to wait_event_interruptible_timeout
 - dma-buf: Fix a stack corruption
 - ttm: Embed a drm_gem_object struct to make ttm_buffer_object a
        superclass of GEM, and convert drivers to use it.
 - hdcp: Improvements to report the content protection type to the
         userspace

Driver Changes:
 - Remove drm_gem_prime_import/export from being defined in the drivers
 - Drop DRM_AUTH usage from drivers
 - Continue to drop drmP.h
 - Convert drivers to the connector ddc helper

 - ingenic: Add support for more panel-related cases
 - komeda: Support for dual-link
 - lima: Reduce logging
 - mpag200: Fix the cursor support
 - panfrost: Export GPU features register to userspace through an ioctl
 - pl111: Remove the CLD pads wiring support from the DT
 - rockchip: Rework to use DRM PSR helpers, fix a bug in the VOP_WIN_GET
             macro
 - sun4i: Improve support for color encoding and range
 - tinydrm: Rework SPI support, improve MIPI-DBI support, move to drm/tiny
 - vkms: Rework of the CRC tracking

 - bridges:
   - sii902x: Add support for audio graph card
   - tc358767: Rework AUX data handling code
   - ti-sn65dsi86: Add Debugfs and proper DSI mode flags support

 - panels
   - Support for GiantPlus GPM940B0, Sharp LQ070Y3DG3B, Ortustech
     COM37H3M, Novatek NT39016, Sharp LS020B1DD01D, Raydium RM67191,
     Boe Himax8279d, Sharp LD-D5116Z01B
   - Conversion of the device tree bindings to the YAML description
   - jh057n00900: Rework the enable / disable path

 - fbdev:
   - ssd1307fb: Support more devices based on that controller

Signed-off-by: Dave Airlie &lt;airlied@redhat.com&gt;

From: Maxime Ripard &lt;maxime.ripard@bootlin.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20190808121423.xzpedzkpyecvsiy4@flea
</content>
</entry>
<entry>
<title>drm/amdgpu: switch driver from bo-&gt;resv to bo-&gt;base.resv</title>
<updated>2019-08-06T06:21:54Z</updated>
<author>
<name>Gerd Hoffmann</name>
<email>kraxel@redhat.com</email>
</author>
<published>2019-08-05T14:01:15Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=5a5011a72489545343a1599362e9ec126d7bd297'/>
<id>urn:sha1:5a5011a72489545343a1599362e9ec126d7bd297</id>
<content type='text'>
Signed-off-by: Gerd Hoffmann &lt;kraxel@redhat.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Link: http://patchwork.freedesktop.org/patch/msgid/20190805140119.7337-14-kraxel@redhat.com
</content>
</entry>
<entry>
<title>drm/amdgpu: Mark KFD VRAM allocations for wipe on release</title>
<updated>2019-08-02T15:18:38Z</updated>
<author>
<name>Felix Kuehling</name>
<email>Felix.Kuehling@amd.com</email>
</author>
<published>2019-07-09T00:01:22Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=6856e4b65f64eeb3f17148f79b36c1d60c627529'/>
<id>urn:sha1:6856e4b65f64eeb3f17148f79b36c1d60c627529</id>
<content type='text'>
Memory used by KFD applications can contain sensitive information that
should not be leaked to other processes. The current approach to prevent
leaks is to clear VRAM at allocation time. This is not effective because
memory can be reused in other ways without being cleared. Synchronously
clearing memory on the allocation path also carries a significant
performance penalty.

Stop clearing memory at allocation time. Instead mark the memory for
wipe on release.

Signed-off-by: Felix Kuehling &lt;Felix.Kuehling@amd.com&gt;
Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
<entry>
<title>drm/amdkfd: Fix byte align on VegaM</title>
<updated>2019-07-31T04:59:00Z</updated>
<author>
<name>Kent Russell</name>
<email>kent.russell@amd.com</email>
</author>
<published>2019-07-23T14:18:01Z</published>
<link rel='alternate' type='text/html' href='https://git.shady.money/linux/commit/?id=d65848657c3da5c0d4b685f823d0230f151ab34e'/>
<id>urn:sha1:d65848657c3da5c0d4b685f823d0230f151ab34e</id>
<content type='text'>
This was missed during the addition of VegaM support

Reviewed-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
Signed-off-by: Kent Russell &lt;kent.russell@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
</content>
</entry>
</feed>
