leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
842,966 Commits 2 Branches 0 Tags
08473888e09b0136ceb4d65784b02b537d977a2a
Commit Graph

501 Commits

Author SHA1 Message Date
Christian König
c633c00bf0 drm/amdgpu: separate PASID mapping from VM flush v2 
Stuffing the PASID mapping into the VM flush isn't flexible enough since
the PASID mapping changes not as often as we need a VM flush.

v2: add missing use of gmc_v7_0_emit_pasid_mapping

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>
 2018-02-19 14:20:18 -05:00
Christian König
29e8357b4c drm/amdgpu: sync the VM PD/PT before clearing it 
Otherwise we might overwrite stuff which is still in use.

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>
 2018-02-19 14:19:26 -05:00
Christian König
e61736daa9 drm/amdgpu: clear the shadow fence as well 
It also needs to be initialized.

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>
 2018-02-19 14:19:20 -05:00
Christian König
e5197a4c3d drm/amdgpu: release the VM shadow in the error path as well 
Without it we run into a memory leak.

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>
 2018-02-19 14:19:20 -05:00
Christian König
4584312d38 drm/amdgpu: fill only the lower range with ATS entries v2 
At least on x86-64 the upper range is purely used by the kernel,
avoid creating any ATS mappings there as security precaution and to
allow proper page fault reporting in the upper range.

v2: remove unused variable

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>
 2018-02-19 14:18:55 -05:00
Christian König
44e1baeb63 drm/amdgpu: revert "Add support for filling a buffer with 64 bit value" 
This reverts commit 7bdc53f925 and commit
330df03b3a.

Neither are needed 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>
 2018-02-19 14:18:55 -05:00
Christian König
8febe617d8 drm/amdgpu: revert "Add a parameter to amdgpu_bo_create()" 
This reverts commit 2046d46db9.

Not needed 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>
 2018-02-19 14:18:54 -05:00
Christian König
4c77edbf74 drm/amdgpu: drop root shadow sync 
Completely pointless, it is the same reservation object as the root PD
anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Roger He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-02-19 14:18:54 -05:00
Christian König
13307f7e1d drm/amdgpu: revert "drm/amdgpu: use AMDGPU_GEM_CREATE_VRAM_CLEARED for VM PD/PTs" v2 
Using the standard clear turned out to be to inflexible.

First of all it is executed on the system queue, together with buffer
moves instead on the per VM queue.

And second we need to fill in the page tables with more than just zero.

We keep the new functionality of initializing the PDEs/PTEs with ATC
routing entries intact.

v2: update commit message.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-02-19 14:18:53 -05:00
Christian König
698825653f drm/amdgpu: add optional ring to *_hdp callbacks 
This adds an optional ring to the invalidate_hdp and flush_hdp
callbacks. If the ring isn't specified or the emit_wreg function not
available the HDP operation will be done with the CPU otherwise by
writing on the ring.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-02-19 14:18:20 -05:00
Christian König
5a4633c4b8 drm/amdgpu: forward pasid to backend flush implementations 
rd the pasid from the VM code to the emit_vm_flush function and update
all implementations with the new parameter.

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>
 2018-02-19 14:17:47 -05:00
Christian König
373ac645c9 drm/amdgpu: move PD/PT address calculation into backend function 
This way we can better handle the differences 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>
 2018-02-19 14:17:45 -05:00
Christian König
132f34e4b5 drm/amdgpu: move struct gart_funcs into amdgpu_gmc.h 
And rename it to struct gmc_funcs.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Samuel Li <Samuel.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-02-19 14:17:44 -05:00
Christian König
770d13b19f drm/amdgpu: move struct amdgpu_mc into amdgpu_gmc.h 
And rename it to amdgpu_gmc as well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Samuel Li <Samuel.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-02-19 14:17:43 -05:00
Alex Deucher
64b9342f31 drm/amdgpu: drop extra tlb invalidation in gpuvm 
We only need to flush the HDP here, not invalidate the TLB.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-02-19 14:17:14 -05:00
Alex Deucher
b1d128689f drm/amdgpu: adjust HDP write queue flushing for tlb invalidation 
Separate tlb invalidation and hdp flushing and move the HDP
flush to the caller.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-02-19 14:17:14 -05:00
Christian König
d3aab672de drm/amdgpu: fix another potential cause of VM faults 
The root PD can be evicted directly after allocating it, just validate
it on first use.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-01-29 23:15:26 -05:00
Christian König
83fbb788a4 drm/amdgpu: fix CPU based VM updates 
That got accidentially removed.

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>
 2018-01-16 15:35:27 -05:00
Christian König
d958939afc drm/amdgpu: fix amdgpu_vm_pasid_fault_credit 
As soon as the lock is dropped the VM pointer can be invalid.

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>
 2018-01-16 15:35:26 -05:00
Christian König
9b8cad2047 drm/amdgpu: optimize moved handling only when vm_debug is inactive 
Otherwise we would completely circumvent that debugging feature.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Roger He <Hongbo.He@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-01-10 15:44:54 -05:00
Christian König
3cc1d3ea4a drm/amdgpu: simplify huge page handling 
Update the PDEs after resetting the huge flag.

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>
 2018-01-10 15:44:53 -05:00
Christian König
ec363e0dae drm/amdgpu: minor optimize VM moved handling v2 
Try to lock moved BOs if it's successful we can update the
PTEs directly to the new location.

v2: rebase

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2018-01-10 15:44:53 -05:00
Christian König
4d4358f3f1 drm/amdgpu: loosen the criteria for huge pages a bit 
We can actually handle invalid huge pages perfectly fine now.

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>
 2018-01-10 15:44:52 -05:00
Emily Deng
104bd2ca11 drm/amdgpu: Correct the IB size of bo update mapping. 
The amdgpu_vm_frag_ptes will call amdgpu_vm_update_ptes, and for buffer
object that has shadow buffer, need twice commands.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2017-12-30 22:24:20 -05:00
Christian König
727ffdf2ac drm/amdgpu: fix VM faults with per VM BOs 
There was a small window between unreserve and second reserve where the
freshly allocated BO could have been evicted without the VM noticing it.

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>
 2017-12-27 11:34:31 -05:00
Christian König
0e36b9b2f9 drm/amdgpu: drop client_id from VM 
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>
 2017-12-27 11:34:09 -05:00
Christian König
c4f46f22c4 drm/amdgpu: rename vm_id to vmid 
sed -i "s/vm_id/vmid/g" drivers/gpu/drm/amd/amdgpu/*.c
sed -i "s/vm_id/vmid/g" drivers/gpu/drm/amd/amdgpu/*.h

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>
 2017-12-27 11:34:02 -05:00
Christian König
620f774f46 drm/amdgpu: separate VMID and PASID handling 
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>
 2017-12-27 11:33:52 -05:00
Alex Deucher
2990a1fc01 drm/amdgpu: rename ip block helper functions 
add device to the name for consistency.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2017-12-18 10:59:40 -05:00
Chunming Zhou
196f74897b drm/amdgpu: add enumerate for PDB/PTB v3 
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>
 2017-12-14 11:01:30 -05:00
Chunming Zhou
c4c3351783 drm/amdgpu: fix huge page setting for ATS case 
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>
 2017-12-13 17:31:01 -05:00
Christian König
3de676d8e7 drm/amdgpu: allow get_vm_pde to change flags as well 
And also provide the level for which we need a PDE.

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>
 2017-12-12 14:46:19 -05:00
Christian König
6989f2460f drm/amdgpu: batch PDE updates again 
Now instead of one submission for each PDE batch them together over all
PDs who need an update.

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>
 2017-12-12 14:46:12 -05:00
Christian König
78eb2f0c71 drm/amdgpu: remove keeping the addr of the VM PDs 
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>
 2017-12-12 14:46:06 -05:00
Christian König
8f19cd78c9 drm/amdgpu: remove last_entry_used from the VM code 
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>
 2017-12-12 14:46:00 -05:00
Christian König
e3a1b32a12 drm/amdgpu: avoid the modulo in amdgpu_vm_get_entry 
We can do this with a simple mask as well.

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>
 2017-12-12 14:45:54 -05:00
Christian König
b852f3d3fb drm/amdgpu: update one PDE at a time v2 
Horrible inefficient, but avoids problems when the root PD size becomes
to big.

v2: remove incr as well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <davdi1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2017-12-12 14:45:41 -05:00
Christian König
94c6f5e4d1 drm/amdgpu: stop joining PDEs 
That doesn't hit any more most of the time anyway.

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>
 2017-12-12 14:45:34 -05:00
Lucas Stach
1b1f42d8fd drm: move amd_gpu_scheduler into common location 
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>
 2017-12-07 11:51:56 -05:00
Andrey Grodzovsky
cebb52b7bc drm/amdgpu: Get rid of dep_sync as a seperate object. 
Instead mark fence as explicit in it's amdgpu_sync_entry.

v2:
Fix use after free bug and add new parameter description.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2017-12-06 12:48:31 -05:00
Christian König
97489129c2 drm/amdgpu: allow specifying vm_block_size for multi level PDs v2 
This patch allows specifying the vm_block_size even when multi level
page directories are active.

v2: fix signed/unsigned compare warning

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>
 2017-12-06 12:48:31 -05:00
Christian König
f3368128ba drm/amdgpu: move validation of the VM size into the VM code 
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>
 2017-12-06 12:48:30 -05:00
Christian König
36539dcea3 drm/amdgpu: choose number of VM levels based on VM size 
This allows us limiting the VM size for testing even of Vega10.

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>
 2017-12-06 12:48:29 -05:00
Christian König
b38f41ebb8 drm/amdgpu: unify VM size handling of Vega10 with older generation 
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>
 2017-12-06 12:48:29 -05:00
Christian König
0410c5e514 drm/amdgpu: fix amdgpu_vm_num_entries 
The block size only affects the leave nodes, everything else is fixed.

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>
 2017-12-06 12:48:29 -05:00
Christian König
507831473f drm/amdgpu: fix VM PD addr shift 
The block size only affects the leave nodes, everything else is fixed.

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>
 2017-12-06 12:48:28 -05:00
Christian König
fdd5faaa08 drm/amdgpu: cleanup vm_size handling 
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>
 2017-12-06 12:47:21 -05:00
Monk Liu
b3eebe3d89 drm/amd/scheduler:introduce guilty pointer member 
this member will be used later, it will points to
the real var inside of context and CS_SUBMIT & gpu schdduler
can decide if skip a job depends on context->guilty or *entity->guilty

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>
 2017-12-04 16:33:09 -05:00
Dan Carpenter
78aa02c713 drm/amdgpu: Potential uninitialized variable in amdgpu_vm_update_directories() 
After commit ea09729c93 ("drm/amdgpu: rework page directory filling
v2") then it becomes a lot harder to verify that "r" is initialized.  My
static checker complains and so I've reviewed the code.  It does look
like it might be buggy... Anyway, it doesn't hurt to set "r" to zero
at the start.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
 2017-11-08 17:55:04 -05:00
Christian König
2642cf110d drm/amdgpu: reserve root PD while releasing it 
Otherwise somebody could try to evict it at the same time and try to use
half torn down structures.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-and-Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
 2017-10-19 15:27:11 -04:00