kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c, branch v5.2.13Linux kernel stable tree (mirror)https://git.radix-linux.su/kernel/linux.git/atom?h=v5.2.132019-04-19T16:32:56+00:00drm/amdgpu: amdgpu_device_recover_vram got NULL of shadow->parent2019-04-19T16:32:56+00:00wentalouWentao.Lou@amd.com2019-04-16T07:09:16+00:00urn:sha1:36e499b2490a470a9a1e8d40096b4e397efac056
amdgpu_bo_destroy had a bug by calling amdgpu_bo_unref outside mutex_lock.
If amdgpu_device_recover_vram executed between amdgpu_bo_unref and list_del_init,
it would get NULL of shadow->parent, then caused Call Trace and GPU reset failed.
Signed-off-by: Wentao Lou <Wentao.Lou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Add helper to wait for BO fences using a sync object2019-02-13T22:50:32+00:00Felix KuehlingFelix.Kuehling@amd.com2019-02-04T22:46:35+00:00urn:sha1:e8e32426b1271d3387208c3a6eaf7c166bea9975
Creates a temporary sync object to wait for the BO reservation. This
generalizes amdgpu_vm_wait_pd.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: clean up memory/GDS/GWS/OA alignment code2019-02-01T05:33:00+00:00Marek Olšákmarek.olsak@amd.com2019-01-22T20:44:54+00:00urn:sha1:fe57085a36de5813ab63a8d178ccfb5f257f028e
- move all adjustments into one place
- specify GDS/GWS/OA alignment in basic units of the heaps
- it looks like GDS alignment was 1 instead of 4
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: WARN once if amdgpu_bo_unpin is called for an unpinned BO2018-12-14T20:55:17+00:00Michel Dänzermichel.daenzer@amd.com2018-12-13T16:05:31+00:00urn:sha1:a3a0ebd10a9b6cf6c33885016393729112c85083
It indicates a pin/unpin imbalance bug somewhere. While the bug isn't
necessarily in the call chain hitting this, it's at least one part
involved.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Add KFD VRAM limit checking2018-12-07T23:13:15+00:00Felix KuehlingFelix.Kuehling@amd.com2018-11-20T01:05:54+00:00urn:sha1:611736d8447c0c48a172db0b968dddae60696a72
We don't want KFD processes evicting each other over VRAM usage.
Therefore prevent overcommitting VRAM among KFD applications with
a per-GPU limit. Also leave enough room for page tables on top
of the application memory usage.
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Eric Huang <JinHuiEric.Huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: remove amdgpu_bo_backup_to_shadow2018-12-03T16:14:48+00:00Christian Königchristian.koenig@amd.com2018-11-07T08:23:26+00:00urn:sha1:1245adf31569e117d11b4ac5839e7b6c53d21186
It is unused.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
dma-buf: allow reserving more than one shared fence slot2018-10-25T11:45:07+00:00Christian Königchristian.koenig@amd.com2018-09-19T14:12:25+00:00urn:sha1:ca05359f1e64cf8303ee532e50efe4ab7563d4a9
Let's support simultaneous submissions to multiple engines.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Link: https://patchwork.kernel.org/patch/10626149/
drm/amdgpu: fix up GDS/GWS/OA shifting2018-09-19T17:38:48+00:00Christian Königchristian.koenig@amd.com2018-09-14T14:06:31+00:00urn:sha1:77a2faa55c1a497f4e7e89eabd11830f0e3cb3dd
That only worked by pure coincident. Completely remove the shifting and
always apply correct PAGE_SHIFT.
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>
drm/amdgpu: fix shadow BO restoring2018-09-19T17:38:41+00:00Christian Königchristian.koenig@amd.com2018-09-11T09:50:57+00:00urn:sha1:403009bfba45163887398652762ed1fc6645181c
Don't grab the reservation lock any more and simplify the handling quite
a bit.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: shadow BOs don't need any alignment2018-09-19T17:38:29+00:00Christian Königchristian.koenig@amd.com2018-09-11T08:31:54+00:00urn:sha1:7fcb0657ffa93544142f6a0bb20b7fecf1cc1dca
They aren't directly used by the hardware.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>