aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
AgeCommit message (Collapse)AuthorFilesLines
2023-05-03drm/amdgpu: add a missing lock for AMDGPU_SCHEDChia-I Wu1-1/+5
mgr->ctx_handles should be protected by mgr->lock. v2: improve commit message v3: add a Fixes tag Signed-off-by: Chia-I Wu <[email protected]> Reviewed-by: Christian König <[email protected]> Fixes: 52c6a62c64fa ("drm/amdgpu: add interface for editing a foreign process's priority v3") Signed-off-by: Alex Deucher <[email protected]>
2021-09-01drm/amdgpu: rework context priority handlingNirmoy Das1-36/+8
To get a hardware queue priority for a context, we are currently mapping AMDGPU_CTX_PRIORITY_* to DRM_SCHED_PRIORITY_* and then to hardware queue priority, which is not the right way to do that as DRM_SCHED_PRIORITY_* is software scheduler's priority and it is independent from a hardware queue priority. Use userspace provided context priority, AMDGPU_CTX_PRIORITY_* to map a context to proper hardware queue priority. Signed-off-by: Nirmoy Das <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-11-13drm/amd/amdgpu/amdgpu_sched: Consume our own header containing prototypesLee Jones1-1/+1
Fixes the following W=1 kernel build warning(s): drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c:35:5: warning: no previous prototype for ‘amdgpu_to_sched_priority’ [-Wmissing-prototypes] drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c:122:5: warning: no previous prototype for ‘amdgpu_sched_ioctl’ [-Wmissing-prototypes] Cc: Alex Deucher <[email protected]> Cc: "Christian König" <[email protected]> Cc: David Airlie <[email protected]> Cc: Daniel Vetter <[email protected]> Cc: Luben Tuikov <[email protected]> Cc: Andres Rodriguez <[email protected]> Cc: [email protected] Cc: [email protected] Signed-off-by: Lee Jones <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-08-24drm/amdgpu: drm_device to amdgpu_device by inline-f (v2)Luben Tuikov1-1/+1
Get the amdgpu_device from the DRM device by use of an inline function, drm_to_adev(). The inline function resolves a pointer to struct drm_device to a pointer to struct amdgpu_device. v2: Use a typed visible static inline function instead of an invisible macro. Signed-off-by: Luben Tuikov <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-08-18drm/scheduler: Remove priority macro INVALID (v2)Luben Tuikov1-10/+30
Remove DRM_SCHED_PRIORITY_INVALID. We no longer carry around an invalid priority and cut it off at the source. Backwards compatibility behaviour of AMDGPU CTX IOCTL passing in garbage for context priority from user space and then mapping that to DRM_SCHED_PRIORITY_NORMAL is preserved. v2: Revert "res" --> "r" and "prio" --> "priority". Signed-off-by: Luben Tuikov <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-08-18drm/scheduler: Scheduler priority fixes (v2)Luben Tuikov1-3/+3
Remove DRM_SCHED_PRIORITY_LOW, as it was used in only one place. Rename and separate by a line DRM_SCHED_PRIORITY_MAX to DRM_SCHED_PRIORITY_COUNT as it represents a (total) count of said priorities and it is used as such in loops throughout the code. (0-based indexing is the the count number.) Remove redundant word HIGH in priority names, and rename *KERNEL* to *HIGH*, as it really means that, high. v2: Add back KERNEL and remove SW and HW, in lieu of a single HIGH between NORMAL and KERNEL. Signed-off-by: Luben Tuikov <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-06-10drm/amd: drop use of drmP.h in amdgpu.hSam Ravnborg1-0/+3
Delete the unused drmP.h from amdgpu.h. Fix fallout in various files. Signed-off-by: Sam Ravnborg <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Cc: "Christian König" <[email protected]> Cc: "David (ChunMing) Zhou" <[email protected]> Cc: David Airlie <[email protected]> Cc: Daniel Vetter <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-05-02amdgpu: switch to fdget()Al Viro1-12/+11
Signed-off-by: Al Viro <[email protected]>
2019-02-15drm/amdgpu: Add command to override the context priority.Bas Nieuwenhuizen1-1/+40
Given a master fd we can then override the priority of the context in another fd. Using these overrides was recommended by Christian instead of trying to submit from a master fd, and I am adding a way to override a single context instead of the entire process so we can only upgrade a single Vulkan queue and not effectively the entire process. Reused the flags field as it was checked to be 0 anyways, so nothing used it. This is source-incompatible (due to the name change), but ABI compatible. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-02-15drm/amdgpu: Check if fd really is an amdgpu fd.Bas Nieuwenhuizen1-3/+7
Otherwise we interpret the file private data as drm & amdgpu data while it might not be, possibly allowing one to get memory corruption. Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-08-21drm/amdgpu: fix incorrect use of drm_file->pidChristian König1-15/+4
That's the PID of the creator of the file (usually the X server) and not the end user of the file. Signed-off-by: Christian König <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> CC: [email protected]
2018-08-21drm/amdgpu: fix incorrect use of fcheckChristian König1-1/+3
The usage isn't RCU protected. Signed-off-by: Christian König <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> CC: [email protected]
2017-12-07drm: move amd_gpu_scheduler into common locationLucas Stach1-10/+10
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]>
2017-10-19drm/amdgpu: rename context priority levelsAndres Rodriguez1-4/+4
Don't leak implementation details about how each priority behaves to usermode. This allows greater flexibility in the future. Squash into c2636dc53abd8269a0930bccd564f2f195dba729 Signed-off-by: Andres Rodriguez <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-10-09drm/amdgpu: add interface for editing a foreign process's priority v3Andres Rodriguez1-0/+109
The AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE ioctls are used to set the priority of a different process in the current system. When a request is dropped, the process's contexts will be restored to the priority specified at context creation time. A request can be dropped by setting the override priority to AMDGPU_CTX_PRIORITY_UNSET. An fd is used to identify the remote process. This is simpler than passing a pid number, which is vulnerable to re-use, etc. This functionality is limited to DRM_MASTER since abuse of this interface can have a negative impact on the system's performance. v2: removed unused output structure v3: change refcounted interface for a regular set operation Signed-off-by: Andres Rodriguez <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: rename amdgpu_sched.c to amdgpu_job.cChristian König1-151/+0
That's probably a better matching name. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: cleanup in kernel job submissionChristian König1-38/+38
Add a job_alloc_with_ib helper and proper job submission. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: directly return fence from ib_scheduleChristian König1-6/+4
Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: move ring from IBs into jobChristian König1-2/+3
We can't submit to multiple rings at the same time anyway. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: add proper job alloc/free functionsChristian König1-0/+33
And use them in the CS instead of allocating IBs and jobs separately. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: merge vm_grab_id and vm_fence v2Christian König1-9/+4
No need for an extra function any more. v2: comment cleanups Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: grab VMID before submitting job v5Christian König1-1/+25
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 <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-02-10drm/amdgpu: clean up non-scheduler code path (v2)Chunming Zhou1-26/+18
Non-scheduler code is longer supported. v2: agd: rebased on upstream Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Ken Wang <[email protected]> Reviewed-by: Monk Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-11-16drm/amdgpu: fix incorrect mutex usage v3Christian König1-17/+10
Before this patch the scheduler fence was created when we push the job into the queue, so we could only get the fence after pushing it. The mutex now was necessary to prevent the thread pushing the jobs to the hardware from running faster than the thread pushing the jobs into the queue. Otherwise the thread pushing jobs into the queue would have accessed possible freed up memory when it tries to get a reference to the fence. So what you get in the end is thread A: mutex_lock(&job->lock); ... Kick of thread B. ... mutex_unlock(&job->lock); And thread B: mutex_lock(&job->lock); .... mutex_unlock(&job->lock); kfree(job); I'm actually not sure if I'm still up to date on this, but this usage pattern used to be not allowed with mutexes. See here as well https://lwn.net/Articles/575460/. v2: remove unrelated changes, fix missing owner v3: rebased, add more commit message Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-11-16drm/amdgpu: cleanup scheduler fence get/put danceChristian König1-1/+0
The code was correct, but getting two references when the ownership is linearly moved on is a bit awkward and just overhead. Signed: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-11-16drm/amdgpu: add command submission workflow tracepointChunming Zhou1-0/+2
OGL needs these tracepoints to investigate performance issue. Change-Id: I5e58187d061253f7d665dfce8e4e163ba91d3e2b Signed-off-by: Chunming Zhou <[email protected]>
2015-10-30drm/amdgpu: remove amdgpu_fence_ref/unrefChristian König1-1/+2
Just move the remaining users to fence_put/get. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-09-23drm/amdgpu: more scheduler cleanups v2Christian König1-1/+1
Embed the scheduler into the ring structure instead of allocating it. Use the ring name directly instead of the id. v2: rebased, whitespace cleanup Signed-off-by: Christian König <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> Reviewed-by: Chunming Zhou<[email protected]>
2015-09-23drm/amdgpu: rename fence->scheduler to sched v2Christian König1-1/+1
Just to be consistent with the other members. v2: rename the ring member as well. Signed-off-by: Christian König <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> (v1) Reviewed-by: Chunming Zhou<[email protected]>
2015-09-23drm/amdgpu: refine the scheduler job type conversionJunwei Zhang1-3/+3
Use container_of rather than casting. Reviewed-by: Christian König <[email protected]> Reviewed-by: David Zhou <[email protected]> Signed-off-by: Junwei Zhang <[email protected]>
2015-09-23drm/amdgpu: refine the job naming for amdgpu_job and amdgpu_sched_jobJunwei Zhang1-18/+18
Use consistent naming across functions. Reviewed-by: Christian König <[email protected]> Reviewed-by: David Zhou <[email protected]> Signed-off-by: Junwei Zhang <[email protected]>
2015-09-23drm/amdgpu: remove process_job callback from the schedulerChristian König1-22/+7
Just free the resources immediately after submitting the job. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-08-28drm/amdgpu: add scheduler dependency callback v2Christian König1-0/+7
This way the scheduler doesn't wait in it's work thread any more. v2: fix race conditions Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-08-26drm/amdgpu: remove extra parameters from scheduler callbacksChristian König1-7/+4
Signed-off-by: Christian König <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Chunming Zhou <[email protected]>
2015-08-25drm/amdgpu: fix last_vm_update fence is not effetive for sched fenceChunming Zhou1-0/+1
Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]>
2015-08-25drm/amdgpu: add owner for sched fenceChunming Zhou1-2/+2
Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]>
2015-08-25drm/amdgpu: fix and cleanup amd_sched_entity_push_jobChristian König1-1/+1
Calling schedule() is probably the worse things we can do. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]>
2015-08-25drm/amdgpu: remove v_seq handling from the scheduler v2Christian König1-1/+0
Simply not used any more. Only keep 32bit atomic for fence sequence numbering. v2: trivial rebase Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> (v1) Reviewed-by: Jammy Zhou <[email protected]> (v1) Reviewed-by: Chunming Zhou <[email protected]> (v1)
2015-08-20drm/amdgpu: free the job immediately after dispatching itChristian König1-4/+3
Fixes a whole bunch of lockdep warnings. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]>
2015-08-20drm/amdgpu: abstract amdgpu_job for schedulerChunming Zhou1-54/+34
Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]>
2015-08-17drm/amdgpu: add reference for **fenceChunming Zhou1-2/+2
fix fence is released when pass to **fence sometimes. add reference for it. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]>
2015-08-17drm/amdgpu: remove amd_sched_wait_emit v2Christian König1-2/+0
Not used any more. v2: remove amd_sched_emit as well. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]>
2015-08-17drm/amd: add scheduler fence implementation (v2)Chunming Zhou1-17/+17
scheduler fence is based on kernel fence framework. v2: squash in Christian's build fix Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]>
2015-08-17drm/amdgpu: use kernel submit helper in vmChunming Zhou1-2/+2
Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]>
2015-08-17drm/amdgpu: use amd_sched_job in its backend opsChunming Zhou1-17/+17
Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]>
2015-08-17drm/amdgpu: cleanup and fix scheduler fence handling v2Christian König1-18/+8
v2: rebased Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> (v1) Reviewed-by: Chunming Zhou <[email protected]>
2015-08-17drm/amdgpu: merge amd_sched_entity and amd_context_entity v2Christian König1-6/+6
Avoiding a couple of casts. v2: rename c_entity to entity as well Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]>
2015-08-17drm/amdgpu: process sched job exactly triggered by fence signalChunming Zhou1-6/+13
Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian K?nig <[email protected]>
2015-08-17Revert "drm/amdgpu: return new seq_no for amd_sched_push_job"Chunming Zhou1-2/+7
This reverts commit d1d33da8eb86b8ca41dd9ed95738030df5267b95. Reviewed-by: Christian K?nig <[email protected]> Conflicts: drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
2015-08-17drm/amdgpu: cleanup amdgpu_ctx inti/fini v2Christian König1-5/+3
Cleanup the kernel context handling. v2: rebased Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> (v1)
Powered by cgit, Gruvboxed by Blaster4385.