| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
When checking for a dependency fence for belonging to the same entity
compare it with scheduled as well finished fence. Earlier we were only
comparing it with the scheduled fence.
Signed-off-by: Nayan Deshmukh <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
To free the fence from the amdgpu_fence_slab, need twice call_rcu, to avoid
the amdgpu_fence_slab_fini call kmem_cache_destroy(amdgpu_fence_slab) before
kmem_cache_free(amdgpu_fence_slab, fence), add rcu_barrier after drm_sched_entity_fini.
The kmem_cache_free(amdgpu_fence_slab, fence)'s call trace as below:
1.drm_sched_entity_fini ->
drm_sched_entity_cleanup ->
dma_fence_put(entity->last_scheduled) ->
drm_sched_fence_release_finished ->
drm_sched_fence_release_scheduled ->
call_rcu(&fence->finished.rcu, drm_sched_fence_free)
2.drm_sched_fence_free ->
dma_fence_put(fence->parent) ->
amdgpu_fence_release ->
call_rcu(&f->rcu, amdgpu_fence_free) ->
kmem_cache_free(amdgpu_fence_slab, fence);
v2:put the barrier before the kmem_cache_destroy
v3:put the dma_fence_put(fence->parent) before call_rcu in
drm_sched_fence_release_scheduled
Signed-off-by: Emily Deng <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
That got missed while moving the files outside of amdgpu.
Signed-off-by: Nayan Deshmukh <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
This spinlock is superfluous, any call to drm_sched_entity_push_job
should already be under a lock together with matching drm_sched_job_init
to match the order of insertion into queue with job's fence seqence
number.
v2:
Improve patch description.
Add functions documentation describing the locking considerations
Signed-off-by: Andrey Grodzovsky <[email protected]>
Acked-by: Chunming Zhou <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
this patch also effect the amdgpu and etnaviv drivers which
use the function drm_sched_entity_init
Signed-off-by: Nayan Deshmukh <[email protected]>
Suggested-by: Christian König <[email protected]>
Acked-by: Lucas Stach <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
The current sequence in scheduler thread is:
1. update last sched fence
2. job begin (adding to mirror list)
3. job finish (remove from mirror list)
4. back to 1
Since we update last sched prior to joining mirror list, the jobs
in mirror list already pass the last sched fence. TDR just run
the jobs in mirror list, so we should not update the last sched
fences in TDR.
Signed-off-by: Pixel Ding <[email protected]>
Reviewed-by: Monk Liu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Make sure main thread won't update last_sched fence when entity
is cleanup.
Fix a racing issue which is caused by putting last_sched fence
twice. Running vulkaninfo in tight loop can produce this issue
as seeing wild fence pointer.
v2: squash in build fix (Christian)
Signed-off-by: Pixel Ding <[email protected]>
Reviewed-by: Christian König <[email protected]>
Reviewed-by: Monk Liu <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Fix the potential memleak since scheduler main thread always
hold one last_sched fence.
Signed-off-by: Pixel Ding <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
issue:
there are VMC page fault occurred if force APP kill during
3dmark test, the cause is in entity_fini we manually signal
all those jobs in entity's queue which confuse the sync/dep
mechanism:
1)page fault occurred in sdma's clear job which operate on
shadow buffer, and shadow buffer's Gart table is cleaned by
ttm_bo_release since the fence in its reservation was fake signaled
by entity_fini() under the case of SIGKILL received.
2)page fault occurred in gfx' job because during the lifetime
of gfx job we manually fake signal all jobs from its entity
in entity_fini(), thus the unmapping/clear PTE job depend on those
result fence is satisfied and sdma start clearing the PTE and lead
to GFX page fault.
fix:
1)should at least wait all jobs already scheduled complete in entity_fini()
if SIGKILL is the case.
2)if a fence signaled and try to clear some entity's dependency, should
set this entity guilty to prevent its job really run since the dependency
is fake signaled.
v2:
splitting drm_sched_entity_fini() into two functions:
1)The first one is does the waiting, removes the entity from the
runqueue and returns an error when the process was killed.
2)The second one then goes over the entity, install it as
completion signal for the remaining jobs and signals all jobs
with an error code.
v3:
1)Replace the fini1 and fini2 with better name
2)Call the first part before the VM teardown in
amdgpu_driver_postclose_kms() and the second part
after the VM teardown
3)Keep the original function drm_sched_entity_fini to
refine the code.
v4:
1)Rename entity->finished to entity->last_scheduled;
2)Rename drm_sched_entity_fini_job_cb() to
drm_sched_entity_kill_jobs_cb();
3)Pass NULL to drm_sched_entity_fini_job_cb() if -ENOENT;
4)Replace the type of entity->fini_status with "int";
5)Remove the check about entity->finished.
Signed-off-by: Monk Liu <[email protected]>
Signed-off-by: Emily Deng <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Move it with the scheduler code. This is mostly a straight forward
rename with no code change except for updating the TRACE_INCLUDE_PATH
Signed-off-by: Nayan Deshmukh <[email protected]>
Suggested-by: Christian König <[email protected]>
Reviewed-by: Christian König <[email protected]>
Acked-by: Lucas Stach <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
There is no @kernel parameter anymore and document the
@guilty parameter
Signed-off-by: Nayan Deshmukh <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
The trailing semicolon is an empty statement that does no operation.
Removing it since it doesn't do anything.
Signed-off-by: Luis de Bethencourt <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
Was missing before.
Reviewed-by: Chunming Zhou <[email protected]>
Acked-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
This is the only part of the scheduler which must not be called from
different drivers. Move it to module init/exit so it is done a single
time when loading the scheduler.
Reviewed-by: Chunming Zhou <[email protected]>
Tested-by: Dieter Nützel <[email protected]>
Acked-by: Alex Deucher <[email protected]>
Signed-off-by: Lucas Stach <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|
|
This moves and renames the AMDGPU scheduler to a common location in DRM
in order to facilitate re-use by other drivers. This is mostly a straight
forward rename with no code changes.
One notable exception is the function to_drm_sched_fence(), which is no
longer a inline header function to avoid the need to export the
drm_sched_fence_ops_scheduled and drm_sched_fence_ops_finished structures.
Reviewed-by: Chunming Zhou <[email protected]>
Tested-by: Dieter Nützel <[email protected]>
Acked-by: Alex Deucher <[email protected]>
Signed-off-by: Lucas Stach <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
|