linux.git/drivers/gpu, branch v4.18.12 Clone of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git drm/amdgpu: Need to set moved to true when evict bo 2018-10-03T23:59:26+00:00 Emily Deng Emily.Deng@amd.com 2018-08-28T12:52:40+00:00 8ad1f551f802d7441938fca54a9459abdd169ab6 [ Upstream commit 6ddd9769db4fc11a98bd7e58be1764e47fdb8384 ] Fix the VMC page fault when the running sequence is as below: 1.amdgpu_gem_create_ioctl 2.ttm_bo_swapout->amdgpu_vm_bo_invalidate, as not called amdgpu_vm_bo_base_init, so won't called list_add_tail(&base->bo_list, &bo->va). Even the bo was evicted, it won't set the bo_base->moved. 3.drm_gem_open_ioctl->amdgpu_vm_bo_base_init, here only called list_move_tail(&base->vm_status, &vm->evicted), but not set the bo_base->moved. 4.amdgpu_vm_bo_map->amdgpu_vm_bo_insert_map, as the bo_base->moved is not set true, the function amdgpu_vm_bo_insert_map will call list_move(&bo_va->base.vm_status, &vm->moved) 5.amdgpu_cs_ioctl won't validate the swapout bo, as it is only in the moved list, not in the evict list. So VMC page fault occurs. Signed-off-by: Emily Deng <Emily.Deng@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 6ddd9769db4fc11a98bd7e58be1764e47fdb8384 ]

Fix the VMC page fault when the running sequence is as below:
1.amdgpu_gem_create_ioctl
2.ttm_bo_swapout->amdgpu_vm_bo_invalidate, as not called
amdgpu_vm_bo_base_init, so won't called
list_add_tail(&base->bo_list, &bo->va). Even the bo was evicted,
it won't set the bo_base->moved.
3.drm_gem_open_ioctl->amdgpu_vm_bo_base_init, here only called
list_move_tail(&base->vm_status, &vm->evicted), but not set the
bo_base->moved.
4.amdgpu_vm_bo_map->amdgpu_vm_bo_insert_map, as the bo_base->moved is
not set true, the function amdgpu_vm_bo_insert_map will call
list_move(&bo_va->base.vm_status, &vm->moved)
5.amdgpu_cs_ioctl won't validate the swapout bo, as it is only in the
moved list, not in the evict list. So VMC page fault occurs.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/amdgpu: Update power state at the end of smu hw_init. 2018-10-03T23:59:26+00:00 Rex Zhu Rex.Zhu@amd.com 2018-08-24T08:17:54+00:00 65c96da9c684946d0874bf911fdb50a3b497cb30 [ Upstream commit 2ab4d0e74256fc49b7b270f63c1d1e47c2455abc ] For SI/Kv, the power state is managed by function amdgpu_pm_compute_clocks. when dpm enabled, we should call amdgpu_pm_compute_clocks to update current power state instand of set boot state. this change can fix the oops when kfd driver was enabled on Kv. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Tested-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 2ab4d0e74256fc49b7b270f63c1d1e47c2455abc ]

For SI/Kv, the power state is managed by function
amdgpu_pm_compute_clocks.

when dpm enabled, we should call amdgpu_pm_compute_clocks
to update current power state instand of set boot state.

this change can fix the oops when kfd driver was enabled on Kv.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/amdgpu: Enable/disable gfx PG feature in rlc safe mode 2018-10-03T23:59:26+00:00 Rex Zhu Rex.Zhu@amd.com 2018-08-24T09:26:23+00:00 21a73b809735e50956b6151785f60aa6897c85f0 [ Upstream commit 8ef23364b654d44244400d79988e677e504b21ba ] This is required by gfx hw and can fix the rlc hang when do s3 stree test on Cz/St. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Hang Zhou <hang.zhou@amd.com> Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 8ef23364b654d44244400d79988e677e504b21ba ]

This is required by gfx hw and can fix the rlc hang when
do s3 stree test on Cz/St.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Hang Zhou <hang.zhou@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
amdgpu: fix multi-process hang issue 2018-10-03T23:59:23+00:00 Emily Deng Emily.Deng@amd.com 2018-08-22T12:18:25+00:00 9d028c09d1cf21b33030e137905846c8bebea768 [ Upstream commit 2f40c6eac74a2a60921cdec9e9a8a57e88e31434 ] SWDEV-146499: hang during multi vulkan process testing cause: the second frame's PREAMBLE_IB have clear-state and LOAD actions, those actions ruin the pipeline that is still doing process in the previous frame's work-load IB. fix: need insert pipeline sync if have context switch for SRIOV (because only SRIOV will report PREEMPTION flag to UMD) Signed-off-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Emily Deng <Emily.Deng@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 2f40c6eac74a2a60921cdec9e9a8a57e88e31434 ]

SWDEV-146499: hang during multi vulkan process testing

cause:
the second frame's PREAMBLE_IB have clear-state
and LOAD actions, those actions ruin the pipeline
that is still doing process in the previous frame's
work-load IB.

fix:
need insert pipeline sync if have context switch for
SRIOV (because only SRIOV will report PREEMPTION flag
to UMD)

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/amdgpu: fix preamble handling 2018-10-03T23:59:23+00:00 Christian König christian.koenig@amd.com 2018-08-21T13:09:39+00:00 8824ceb2580c20ac16bc235f0efe0bd461c36864 [ Upstream commit d98ff24e8e9be3329eea7c84d5e244d0c1cd0ab3 ] At this point the command submission can still be interrupted. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit d98ff24e8e9be3329eea7c84d5e244d0c1cd0ab3 ]

At this point the command submission can still be interrupted.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/amdgpu: fix VM clearing for the root PD 2018-10-03T23:59:23+00:00 Christian König christian.koenig@amd.com 2018-08-16T10:01:03+00:00 8483f3b7f4243f8c871d3d93e53ec11561088c18 [ Upstream commit 8604ffcbf04f8f4f3f55a9e46e5ff948b2ed4290 ] We need to figure out the address after validating the BO, not before. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Huang Rui <ray.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 8604ffcbf04f8f4f3f55a9e46e5ff948b2ed4290 ]

We need to figure out the address after validating the BO, not before.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/vc4: plane: Expand the lower bits by repeating the higher bits 2018-10-03T23:59:17+00:00 Maxime Ripard maxime.ripard@bootlin.com 2018-05-17T13:37:59+00:00 6b07342e25961dbd483671c130cc85603462806a [ Upstream commit 3257ec797d3a8c5232389eb1952d4451e80f3931 ] The vc4 HVS uses an internal RGB888 representation of the frames, and will by default expand formats using a lower depth using zeros. This causes an issue when we try to use other compositing software such as pixman that fill the missing bits by repeating the higher significant bits. As such, we can't check the display output in a reliable way by doing a software composition and an hardware one and compare both. To prevent this, force the same behaviour so that we can do such things. Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com> Signed-off-by: Eric Anholt <eric@anholt.net> Link: https://patchwork.freedesktop.org/patch/msgid/20180517133759.25626-1-maxime.ripard@bootlin.com Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 3257ec797d3a8c5232389eb1952d4451e80f3931 ]

The vc4 HVS uses an internal RGB888 representation of the frames, and will
by default expand formats using a lower depth using zeros.

This causes an issue when we try to use other compositing software such as
pixman that fill the missing bits by repeating the higher significant bits.
As such, we can't check the display output in a reliable way by doing a
software composition and an hardware one and compare both.

To prevent this, force the same behaviour so that we can do such things.

Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517133759.25626-1-maxime.ripard@bootlin.com
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/vc4: Add missing formats to vc4_format_mod_supported(). 2018-10-03T23:59:17+00:00 Eric Anholt eric@anholt.net 2018-03-16T22:04:34+00:00 e80225d36dca7c1897dc3b6107ee9ee87fafc9a4 [ Upstream commit 1e871d65e375280757833d9fce91dda71980bdf5 ] Daniel's format_mod_supported() patch predated Dave's for NV21/61, and I didn't catch that when rebasing. This is a problem since the formats are now getting validated before being passed to the driver's atomic hooks. Signed-off-by: Eric Anholt <eric@anholt.net> Acked-by: Daniel Stone <daniels@collabora.com> Cc: Dave Stevenson <dave.stevenson@raspberrypi.org> Fixes: 423ad7b3cbd1 ("drm/vc4: Advertise supported modifiers for planes") Link: https://patchwork.freedesktop.org/patch/msgid/20180316220435.31416-2-eric@anholt.net Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 1e871d65e375280757833d9fce91dda71980bdf5 ]

Daniel's format_mod_supported() patch predated Dave's for NV21/61, and
I didn't catch that when rebasing.  This is a problem since the
formats are now getting validated before being passed to the driver's
atomic hooks.

Signed-off-by: Eric Anholt <eric@anholt.net>
Acked-by: Daniel Stone <daniels@collabora.com>
Cc: Dave Stevenson <dave.stevenson@raspberrypi.org>
Fixes: 423ad7b3cbd1 ("drm/vc4: Advertise supported modifiers for planes")
Link: https://patchwork.freedesktop.org/patch/msgid/20180316220435.31416-2-eric@anholt.net
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/v3d: Take a lock across GPU scheduler job creation and queuing. 2018-10-03T23:59:14+00:00 Eric Anholt eric@anholt.net 2018-06-06T17:48:51+00:00 09468e65ec7db8d002102143ea0d94bc4e7f3786 [ Upstream commit 7122b68b8a9692dcc3acf89595f04c492872115f ] Between creation and queueing of a job, you need to prevent any other job from being created and queued. Otherwise the scheduler's fences may be signaled out of seqno order. v2: move mutex unlock to the error label. Signed-off-by: Eric Anholt <eric@anholt.net> Fixes: 57692c94dcbe ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+") Link: https://patchwork.freedesktop.org/patch/msgid/20180606174851.12433-1-eric@anholt.net Reviewed-by: Lucas Stach <l.stach@pengutronix.de> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 7122b68b8a9692dcc3acf89595f04c492872115f ]

Between creation and queueing of a job, you need to prevent any other
job from being created and queued.  Otherwise the scheduler's fences
may be signaled out of seqno order.

v2: move mutex unlock to the error label.

Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: 57692c94dcbe ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Link: https://patchwork.freedesktop.org/patch/msgid/20180606174851.12433-1-eric@anholt.net
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
drm/omap: gem: Fix mm_list locking 2018-10-03T23:59:13+00:00 Daniel Vetter daniel.vetter@ffwll.ch 2018-05-25T16:39:24+00:00 3fc862c26744005261ee430450d3571d07d86458 [ Upstream commit 5117bd898e8c0a31e8ab3a9b8523aecf0706e997 ] - None of the list walkings where protected. - Switch to a mutex since the list walking at device resume time can sleep when pinning buffers through the tiler. Only thing we need to be careful with here is that while we walk the list we can't unreference any gem objects, since the final unref would result in a recursive deadlock. But the only functions that walk the list is the device resume and debugfs dumping, so all safe. Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> Signed-off-by: Sasha Levin <alexander.levin@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 5117bd898e8c0a31e8ab3a9b8523aecf0706e997 ]

- None of the list walkings where protected.

- Switch to a mutex since the list walking at device resume time can
  sleep when pinning buffers through the tiler.

Only thing we need to be careful with here is that while we walk the
list we can't unreference any gem objects, since the final unref would
result in a recursive deadlock. But the only functions that walk the
list is the device resume and debugfs dumping, so all safe.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>