We are going to need that for recoverable page faults.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It is redundant with the job pointer.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Clean that up further and also fix another case where the BO
wasn't kmapped for CPU based updates.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Driver vote low to high pstate switch whenever there is an outstanding
XGMI mapping request. Driver vote high to low pstate when all the
outstanding XGMI mapping is terminated.
Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
And remove the existing code when it is unused.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Separate out all functions for SDMA and CPU based page table
updates into separate backends.
This way we can keep most of the complexity of those from the
core VM code.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Move the update parameter into the VM header and rename them.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Not needed any more.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Make sure that not only the entities are flush, but that
we also wait for the HW to finish all processing.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Remove the chash implementation for now since it isn't used any more.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Not needed any more since we now free PDs/PTs on demand.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Let's start to allocate VM PDs/PTs on demand instead of pre-allocating
them during mapping.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
if lru is changed, we cannot do bulk moving.
v2:
root bo isn't in bulk moving, skip its change.
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
printk_ratelimit() is much better suited to limit the number of reported
VM faults.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Instead of the double linked list. Gets the size of amdgpu_vm_pt down to
64 bytes again.
We could even reduce it down to 32 bytes, but that would require some
rather extreme hacks.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In stead of share one fault hash table per device, make it
per vm. This can avoid inter-process lock issue when fault
hash table is full.
Change-Id: I5d1281b7c41eddc8e26113e010516557588d3708
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Suggested-by: Christian Konig <Christian.Koenig@amd.com>
Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian Konig <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Correct sign extend the GMC addresses to 48bit.
v2: sign extending turned out easier than thought.
v3: clean up the defines and move them into amdgpu_gmc.h as well
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>
Allows us to avoid taking the spinlock in more places.
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>
For compute vm acquired from amdgpu, vm.pasid is managed
by kfd. Decouple pasid from such vm on process destroy
to avoid duplicate pasid release.
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
To make a amdgpu vm to a compute vm, the old pasid will be freed and
replaced with a pasid managed by kfd. Kfd can't reuse original pasid
allocated by amdgpu because kfd uses different pasid policy with amdgpu.
For example, all graphic devices share one same pasid in a process.
v2: rebase (Alex)
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Just another leftover from radeon.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Set the VM size based on system memory size between the ASIC-specific
limits given by min_vm_size and max_bits. GFXv9 GPUs will keep their
default VM size of 256TB (48 bit). Only older GPUs will adjust VM size
depending on system memory size.
This makes more VM space available for ROCm applications on GFXv8 GPUs
that want to map all available VRAM and system memory in their SVM
address space.
v2:
* Clarify comment
* Round up memory size before >> 30
* Round up automatic vm_size to power of two
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
I continue to work for bulk moving that based on the proposal by Christian.
Background:
amdgpu driver will move all PD/PT and PerVM BOs into idle list. Then move all of
them on the end of LRU list one by one. Thus, that cause so many BOs moved to
the end of the LRU, and impact performance seriously.
Then Christian provided a workaround to not move PD/PT BOs on LRU with below
patch:
Commit 0bbf32026cf5ba41e9922b30e26e1bed1ecd38ae ("drm/amdgpu: band aid
validating VM PTs")
However, the final solution should bulk move all PD/PT and PerVM BOs on the LRU
instead of one by one.
Whenever amdgpu_vm_validate_pt_bos() is called and we have BOs which need to be
validated we move all BOs together to the end of the LRU without dropping the
lock for the LRU.
While doing so we note the beginning and end of this block in the LRU list.
Now when amdgpu_vm_validate_pt_bos() is called and we don't have anything to do,
we don't move every BO one by one, but instead cut the LRU list into pieces so
that we bulk move everything to the end in just one operation.
Test data:
+--------------+-----------------+-----------+---------------------------------------+
| |The Talos |Clpeak(OCL)|BusSpeedReadback(OCL) |
| |Principle(Vulkan)| | |
+------------------------------------------------------------------------------------+
| | | |0.319 ms(1k) 0.314 ms(2K) 0.308 ms(4K) |
| Original | 147.7 FPS | 76.86 us |0.307 ms(8K) 0.310 ms(16K) |
+------------------------------------------------------------------------------------+
| Orignial + WA| | |0.254 ms(1K) 0.241 ms(2K) |
|(don't move | 162.1 FPS | 42.15 us |0.230 ms(4K) 0.223 ms(8K) 0.204 ms(16K)|
|PT BOs on LRU)| | | |
+------------------------------------------------------------------------------------+
| Bulk move | 163.1 FPS | 40.52 us |0.244 ms(1K) 0.252 ms(2K) 0.213 ms(4K) |
| | | |0.214 ms(8K) 0.225 ms(16K) |
+--------------+-----------------+-----------+---------------------------------------+
After test them with above three benchmarks include vulkan and opencl. We can
see the visible improvement than original, and even better than original with
workaround.
v2: move all BOs include idle, relocated, and moved list to the end of LRU and
put them together.
v3: remove unused parameter and use list_for_each_entry instead of the one with
save entry.
v4: move the amdgpu_vm_move_to_lru_tail after command submission, at that time,
all bo will be back on idle list.
v5: remove amdgpu_vm_move_to_lru_tail_by_list(), use bulk_moveable instread of
validated, and move ttm_bo_bulk_move_lru_tail() also into
amdgpu_vm_move_to_lru_tail().
v6: clean up and fix return value.
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Tested-by: Mike Lothian <mike@fireburn.co.uk>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Instead of the fixed round robin use let the scheduler balance the load
of page table updates.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Demangle amdgpu.h.
Signed-off-by: Huang Rui <ray.huang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This allows us to trace all VM ranges which should be valid inside a CS.
v2: dump mappings without BO as well
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-and-tested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> (v1)
Reviewed-by: Huang Rui <ray.huang@amd.com> (v1)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add process and thread names and pids and a function to extract
this info from relevant amdgpu_vm.
v2: Add documentation and fix identation.
v3: Add getter and setter functions for amdgpu_task_info.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Jim Qu <Jim.Qu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Move all BOs belonging to a VM on the LRU with every submission.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Only the moved state needs a separate spin lock protection. All other
states are protected by reserving the VM anyway.
v2: fix some more incorrect cases
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This lock isn't used any more.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This change prepares for a workaround in amdkfd for a GFX9 HW bug. It
requires the control stack memory of compute queues, which is allocated
from the second page of MQD gart BOs, to have mtype NC, rather than
the default UC.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
v2: Removed updating and checking of vm->vm_context
v3: Enable amdgpu_vm_clear_bo in amdgpu_vm_make_compute
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Remove struct amdkfd_vm and move the fields into struct amdgpu_vm.
This will allow turning a VM created by a DRM render node into a
KFD VM.
v2: Removed vm_context field
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
1MB should be more than enough, currently we use about 8K.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Monk Liu <monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Use the fence context from the scheduler entity.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Move both into the new files amdgpu_ids.[ch]. No functional change.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Instead of falling back to 2 level and very limited address space use
2+1 PD support and 128TB + 512GB of virtual address space.
v2: cleanup defines, rebase on top of level enum
v3: fix inverted check in hardware setup
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-and-Tested-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
v2:
remove SUBPTB member
v3:
remove last_level, use AMDGPU_VM_PTB directly instead.
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
No more double house keeping.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Not needed any more.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
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 <david1.zhou@amd.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This moves validation of the VM size parameter into amdgpu_vm_adjust_size().
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
One function to rule them all.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Similar to the CPU address space the VA on Vega10 has a hole in it.
v2: use dev_dbg instead of dev_err
v3: add some more comments to explain how the hw works
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It's pointless to have the same value twice, just always use max_pfn.
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>
Even when it's a small handle it as 64bit value as well.
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>
Without the additional bits set in PDEs/PTEs, the ATC memory access
would have failed on Raven.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
More new stuff for 4.15. Highlights:
- Add clock query interface for raven
- Add new FENCE_TO_HANDLE ioctl
- UVD video encode ring support on polaris
- transparent huge page DMA support
- deadlock fixes
- compute pipe lru tweaks
- powerplay cleanups and regression fixes
- fix duplicate symbol issue with radeon and amdgpu
- misc bug fixes
* 'drm-next-4.15' of git://people.freedesktop.org/~agd5f/linux: (72 commits)
drm/radeon/dp: make radeon_dp_get_dp_link_config static
drm/radeon: move ci_send_msg_to_smc to where it's used
drm/amd/sched: fix deadlock caused by unsignaled fences of deleted jobs
drm/amd/sched: NULL out the s_fence field after run_job
drm/amd/sched: move adding finish callback to amd_sched_job_begin
drm/amd/sched: fix an outdated comment
drm/amd/sched: rename amd_sched_entity_pop_job
drm/amdgpu: minor coding style fix
drm/ttm: add transparent huge page support for DMA allocations v2
drm/ttm: add support for different pool sizes
drm/ttm: remove unsued options from ttm_mem_global_alloc_page
drm/amdgpu: add uvd enc irq
drm/amdgpu: add uvd enc ib test
drm/amdgpu: add uvd enc ring test
drm/amdgpu: add uvd enc vm functions (v2)
drm/amdgpu: add uvd enc into run queue
drm/amdgpu: add uvd enc rings
drm/amdgpu: add new uvd enc ring methods
drm/amdgpu: add uvd enc command in header
drm/amdgpu: add uvd enc registers in header
...
When many wavefronts cause VM faults at the same time, it can
overwhelm the interrupt handler and cause IH ring overflows before
the driver can notify or kill the faulting application.
As a workaround I'm introducing limited per-VM fault credit. After
that number of VM faults have occurred, further VM faults are
filtered out at the prescreen stage of processing.
This depends on the PASID in the interrupt packet, so it currently
only works for KFD contexts.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
