leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
797,210 Commits 2 Branches 0 Tags
2b9b7502dfcb6169dbf3359702953bf756b4e273
Commit Graph

101 Commits

Author SHA1 Message Date
Christian König
d88bf583bd drm/amdgpu: move VM fields into job 
They are the same for all IBs.

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>
 2016-05-11 13:30:31 -04:00
Christian König
92f250989b drm/amdgpu: move the context from the IBs into the job 
We only have one context for all IBs.

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>
 2016-05-11 13:30:31 -04:00
Christian König
f153d2867b drm/amdgpu: move context switch handling into common code v2 
It was a source of bugs to repeat that in each IP version.

v2: rename parameter

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>
 2016-05-11 13:30:30 -04:00
Christian König
9f8fb5a2b3 drm/amdgpu: move preamble IB handling into common code 
This fixes the handling which was completely broken when you
ad more than one preamble IB.

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>
 2016-05-11 13:30:30 -04:00
Christian König
aa3b73f67b drm/amdgpu: use fence_context to judge ctx switch v2 
Use of the ctx pointer is not safe, because they are likely already
be assigned to another ctx when doing comparing.

v2: recreate from scratch, avoid all unnecessary changes.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Monk.Liu <monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-05-11 12:31:27 -04:00
Christian König
4d9c514d8c drm/amdgpu: two minor 80 char fixes 
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom St Denis <tom.stdenis@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-05-11 12:31:18 -04:00
Monk Liu
794ff5710e drm/amdgpu: hdp flush&inval should always do 
This fixes Tonga vm-fault issue when running disaster
(a multiple context GL heavy tests),
We should always flush & invalidate hdp no matter vm
used or not.

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <David1.Zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
 2016-05-11 12:31:17 -04:00
Monk Liu
c5637837ba drm/amdgpu: keep vm in job instead of ib (v2) 
ib.vm is a legacy way to get vm, after scheduler
implemented vm should be get from job, and all ibs
from one job share the same vm, no need to keep ib.vm
just move vm field to job.

this patch as well add job as paramter to ib_schedule
so it can get vm from job->vm.

v2: agd: sqaush in:
drm/amdgpu: check if ring emit_vm_flush exists in vm flush

No vm flush on engines that don't support VM.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=95195

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-05-11 12:31:16 -04:00
Nils Wallménius
06ab6832ac drm/amdgpu: Mark all instances of struct drm_info_list as const 
All these are compile time constand and the
drm_debugfs_create/remove_files functions take a const
pointer argument.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Nils Wallménius <nils.wallmenius@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-05-04 20:20:10 -04:00
Christian König
41d9eb2c5a drm/amdgpu: add a fence after the VM flush 
This way we can track when the flush is done.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-05-04 20:19:24 -04:00
Monk Liu
03ccf48198 drm/amdgpu: patch cond exec for SDMA 
More ground work for conditional execution on SDMA
necessary for preemption.

Signed-off-by: Monk Liu <monk.liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-05-02 15:11:09 -04:00
Monk Liu
128cff1af6 drm/amdgpu: support cond exec 
This adds the groundwork for conditional execution on
SDMA which is necessary for preemption.

Signed-off-by: Monk Liu <monk.liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-05-02 15:09:17 -04:00
Monk Liu
73cfa5f5ce drm/amdgpu: move ib.fence to job.fence 
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-03-17 11:54:11 -04:00
Monk Liu
cc55c45db5 drm/amdgpu: give a fence param to ib_free 
thus amdgpu_ib_free() can hook sched fence to SA manager
in later patches.

BTW:
for amdgpu_free_job(), it should only fence_put() the
fence of the last ib once, so fix it as well in this patch.

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-03-17 11:53:34 -04:00
Christian König
971fe9a941 drm/amdgpu: switch the GDS only on demand v2 
Switching the GDS space to often seems to be problematic.

This patch together with the following can avoid VM faults on context switch.

v2: extend commit message a bit

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v1)
Reviewed-by: Chunming Zhou <david1.zhou@amd.com> (v1)
 2016-03-08 11:01:49 -05:00
Christian König
cffadc83c7 drm/amdgpu: move the GDS switch into vm flush as well 
After all it's an operation on the VMID.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
 2016-03-08 11:01:48 -05:00
Christian König
364beb2cc4 drm/amdgpu: return the common fence from amdgpu_fence_emit 
Try to avoid using the hardware specific fences even more.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
 2016-03-08 11:01:48 -05:00
Christian König
336d1f5efe drm/amdgpu: remove HW fence owner 
Not used any more since we now always use the sheduler.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
 2016-03-08 11:01:47 -05:00
Chunming Zhou
11afbde85e drm/amdgpu: add hdp_invalidate function 
It's called after emitting ibs.

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-03-08 11:01:41 -05:00
Christian König
4ff37a83f1 drm/amdgpu: fix VM faults caused by vm_grab_id() v4 
The owner must be per ring as long as we don't
support sharing VMIDs per process. Also move the
assigned VMID and page directory address into the
IB structure.

v3: assign the VMID to all IBs, not just the first one.
v4: use correct pointer for owner

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-02-29 11:33:46 -05:00
Christian König
e86f9ceee1 drm/amdgpu: move sync into job object 
No need to keep that for every IB.

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>
 2016-02-10 14:17:24 -05:00
Christian König
ec72b8006c drm/amdgpu: directly return fence from ib_schedule 
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>
 2016-02-10 14:17:21 -05:00
Christian König
b07c60c065 drm/amdgpu: move ring from IBs into job 
We can't submit to multiple rings at the same time anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-02-10 14:17:20 -05:00
Christian König
867d0517c7 drm/amdgpu: remove AMDGPU_NUM_SYNCS 
Just a leftover from semaphores.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-02-10 14:17:17 -05:00
Christian König
8a8f0b48a0 drm/amdgpu: remove adev and fence from amdgpu_sync_free 
Just leftovers from the semaphores.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-02-10 14:17:17 -05:00
Christian König
a27de35caa drm/amdgpu: remove the ring lock v2 
It's not needed any more because all access goes through the scheduler now.

v2: Update commit message.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-02-10 14:16:58 -05:00
Christian König
8d0a7cea82 drm/amdgpu: grab VMID before submitting job v5 
This allows the scheduler to handle the dependencies on ID contention as well.

v2: grab id only once
v3: use a separate lock for the VMIDs
v4: cleanup after semaphore removal
v5: minor coding style change

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-02-10 14:16:56 -05:00
Chunming Zhou
cadf97b196 drm/amdgpu: clean up non-scheduler code path (v2) 
Non-scheduler code is longer supported.

v2: agd: rebased on upstream

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Ken Wang  <Qingqing.Wang@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-02-10 14:16:50 -05:00
Chunming Zhou
be86c606b5 drm/amdgpu: cleanup amdgpu_sync_rings V2 
No longer needed now that semaphores are gone.

V2: remove the first amdgpu_sync_wait in amdgpu_ib_schedule

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Ken Wang  <Qingqing.Wang@amd.com> (V1)
Reviewed-by: Monk Liu <monk.liu@amd.com> (V2)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2016-02-10 14:16:50 -05:00
Junwei Zhang
bbf0b34578 drm/amdgpu: remove the unnecessary parameter adev for amdgpu_sa_bo_new() 
Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
 2015-11-16 17:01:32 -05:00
Christian König
16ae42feb0 drm/amdgpu: use common fence for amdgpu_vm_fence 
Just cleanup the function parameters.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
 2015-11-16 11:05:49 -05:00
Christian König
6ef68c17d4 drm/amdgpu: remove amdgpu_fence_ref/unref 
Just move the remaining users to fence_put/get.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
 2015-10-30 01:58:22 -04:00
Christian König
b7e4dad3e1 drm/amdgpu: remove old lockup detection infrastructure 
It didn't worked to well anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
 2015-10-21 11:35:12 -04:00
Christian König
f91b3a6941 drm/amdgpu: fix fence wait in sync_fence, instead should be in sync_rings 
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
 2015-08-25 10:39:39 -04:00
Christian König
ce882e6dc2 drm/amdgpu: remove v_seq handling from the scheduler v2 
Simply not used any more. Only keep 32bit atomic for fence sequence numbering.

v2: trivial rebase

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v1)
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> (v1)
Reviewed-by: Chunming Zhou <david1.zhou@amd.com> (v1)
 2015-08-25 10:39:16 -04:00
Chunming Zhou
4ce9891ee1 drm/amdgpu: improve sa_bo->fence by kernel fence 
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
 2015-08-25 10:38:41 -04:00
Christian König
b203dd9594 drm/amdgpu: fix zeroing all IB fields manually v2 
The problem now is that we don't necessarily call amdgpu_ib_get()
in some error paths and so work with uninitialized data.

Better require that the memory is already zeroed.

v2: better commit message

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com> (v1)
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
 2015-08-20 17:05:34 -04:00
Chunming Zhou
f556cb0cae drm/amd: add scheduler fence implementation (v2) 
scheduler fence is based on kernel fence framework.

v2: squash in Christian's build fix

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
 2015-08-17 16:51:07 -04:00
Chunming Zhou
d1ff9086c1 drm/amdgpu: fix seq in ctx_add_fence 
if enabling scheduler, then the queued seq is assigned
when pushing job before emitting job.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian K?nig <christian.koenig@amd.com>
 2015-08-17 16:50:43 -04:00
Christian König
5430a3ffb0 drm/amdgpu: fix UVD/VCE fence handling 
We need to return the sequence number to userspace
even when we don't use user fences.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
 2015-08-17 16:50:18 -04:00
Christian König
7f8a5290f5 drm/amdgpu: rework vm_grab_id interface 
This makes assigning VM IDs independent from the use of VM IDs.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
 2015-08-17 16:50:16 -04:00
Christian König
21c16bf634 drm/amdgpu: add user fence context map v2 
This is a prerequisite for the GPU scheduler to make the order
of submission independent from the order of execution.

v2: properly implement the locking

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
 2015-08-17 16:50:14 -04:00
Christian König
91e1a5207e drm/amdgpu: deal with foreign fences in amdgpu_sync 
This also requires some error handling from the callers of that function.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
 2015-08-17 16:50:13 -04:00
monk.liu
e722b71a54 drm/amdgpu: hdp_flush is not needed for inside IB 
hdp flush is not needed for IBs that dispatched from kernel inside
because there is no video memory host access

Signed-off-by: monk.liu <monk.liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
 2015-07-29 16:06:17 -04:00
Chunming Zhou
890ee23fc6 drm/amdgpu: disable user fence interrupt (v2) 
amdgpu submits both kernel and user fences, but just need one interrupt,
disable user fence interrupt and don't effect user fence.

v2: fix merge error

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
 2015-06-05 11:02:06 -04:00
Christian König
3cb485f340 drm/amdgpu: fix context switch 
Properly protect the state and also handle submission failures.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
 2015-06-03 21:03:34 -04:00
Christian König
d919ad49ac drm/amdgpu: fix dereference before check 
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
 2015-06-03 21:03:33 -04:00
Christian König
d2edb07b10 drm/amdgpu: cleanup HDP flush handling 
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
 2015-06-03 21:03:32 -04:00
Christian König
66782cec7a drm/amdgpu: always emit GDS switch 
Otherwise a process can access the GDS data of another process.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Monk Liu <monk.liu@amd.com>
 2015-06-03 21:03:31 -04:00
Jammy Zhou
de807f818b drm/amdgpu: add flags for amdgpu_ib structure 
Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
 2015-06-03 21:03:30 -04:00