aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
AgeCommit message (Collapse)AuthorFilesLines
2016-10-24drm/amdgpu: fix a vm_flush fence leakGrazvydas Ignotas1-0/+1
Looks like .last_flush reference is left at teardown. Leak reported by CONFIG_SLUB_DEBUG. Fixes: 41d9eb2c5a2a ("drm/amdgpu: add a fence after the VM flush") Reviewed-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Grazvydas Ignotas <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-10-06drm/amdgpu: revert "use more than 64KB fragment size if possible"Christian König1-8/+4
This reverts commit 1dcd32fb9c54334ec948a0f18174a748d6b14364. The block size is indeed an equal match, so this can cause performance regressions. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2016-09-30Merge branch 'drm-next-4.9' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie1-12/+55
into drm-next Some additional fixes for 4.9: - The rest of Christian's GTT rework which fixes a long standing bug in the GPUVM code among other things - Changes to the pci shutdown callbacks for certain hypervisors - Fix hpd interrupt storms on eDP panels which have the hpd interrupt enabled by the bios - misc cleanups and bug fixes * 'drm-next-4.9' of git://people.freedesktop.org/~agd5f/linux: (33 commits) drm/radeon: always apply pci shutdown callbacks drm/amdgpu: always apply pci shutdown callbacks (v2) drm/amdgpu: improve VM PTE trace points drm/amdgpu: fix GART_DEBUGFS define drm/amdgpu: free userptrs even if GTT isn't bound drm/amd/amdgpu: Various cleanups for DCEv6 drm/amdgpu: fix BO move offsets drm/amdgpu: fix amdgpu_move_blit on 32bit systems drm/amdgpu: fix gtt_mgr bo's offset drm/amdgpu: fix initializing the VM BO shadow drm/amdgpu: fix initializing the VM last eviction counter drm/amdgpu: cleanup VM shadow BO unreferencing drm/amdgpu: allocate GTT space for shadow VM page tables drm/amdgpu: rename all rbo variable to abo v2 drm/amdgpu: remove unused member from struct amdgpu_bo drm/amdgpu: add a custom GTT memory manager v2 drm/amdgpu/dce6: disable hpd on local panels drm/amdgpu/dce8: disable hpd on local panels drm/amdgpu/dce11: disable hpd on local panels drm/amdgpu/dce10: disable hpd on local panels ...
2016-09-28drm/amdgpu: improve VM PTE trace pointsChristian König1-4/+6
Use a separate one for the copy operation and log all the interesting parameters. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-09-28drm/amdgpu: fix initializing the VM BO shadowChristian König1-0/+15
We need to clear the shadows as well. Signed-off-by: Christian König <[email protected]> Acked-by: Edward O'Callaghan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-09-28drm/amdgpu: fix initializing the VM last eviction counterChristian König1-2/+6
Close a very small window where something can go wrong. Signed-off-by: Christian König <[email protected]> Acked-by: Edward O'Callaghan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-09-28drm/amdgpu: cleanup VM shadow BO unreferencingChristian König1-6/+10
Unreference the shadow BOs in the error path as well and drop the NULL checks. Signed-off-by: Christian König <[email protected]> Acked-by: Edward O'Callaghan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-09-28drm/amdgpu: allocate GTT space for shadow VM page tablesChristian König1-0/+17
We need to access those with the system domain. Fixes fallout from only allocating GTT space on demand. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-09-28Merge tag 'v4.8-rc8' into drm-nextDave Airlie1-1/+4
Linux 4.8-rc8 There was a lot of fallout in the imx/amdgpu/i915 drivers, so backmerge it now to avoid troubles. * tag 'v4.8-rc8': (1442 commits) Linux 4.8-rc8 fault_in_multipages_readable() throws set-but-unused error mm: check VMA flags to avoid invalid PROT_NONE NUMA balancing radix tree: fix sibling entry handling in radix_tree_descend() radix tree test suite: Test radix_tree_replace_slot() for multiorder entries fix memory leaks in tracing_buffers_splice_read() tracing: Move mutex to protect against resetting of seq data MIPS: Fix delay slot emulation count in debugfs MIPS: SMP: Fix possibility of deadlock when bringing CPUs online mm: delete unnecessary and unsafe init_tlb_ubc() huge tmpfs: fix Committed_AS leak shmem: fix tmpfs to handle the huge= option properly blk-mq: skip unmapped queues in blk_mq_alloc_request_hctx MIPS: Fix pre-r6 emulation FPU initialisation arm64: kgdb: handle read-only text / modules arm64: Call numa_store_cpu_info() earlier. locking/hung_task: Fix typo in CONFIG_DETECT_HUNG_TASK help text nvme-rdma: only clear queue flags after successful connect i2c: qup: skip qup_i2c_suspend if the device is already runtime suspended perf/core: Limit matching exclusive events to one PMU ...
2016-09-27drm/amdgpu: fix addr handling in amdgpu_vm_bo_update_mappingChristian König1-0/+1
Otherwise we will look at the wrong place in the IB when GART mappings are split into smaller updates. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Tom StDenis <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-09-14drm/amdgpu: bind GTT on demandChristian König1-1/+2
We don't really need the GTT table any more most of the time. So bind it only on demand. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-22drm/amdgpu: cleanup amdgpu_vm_bo_update paramsChristian König1-10/+11
Make it more obvious what we are doing here. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-22drm/amdgpu: update pt shadow while updating pt V2Chunming Zhou1-1/+15
V2: move shadow parameter to amdgpu_pte_update_params. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Cc: [email protected] Signed-off-by: Alex Deucher <[email protected]>
2016-08-22drm/amdgpu: update pd shadow while updating pd V2Chunming Zhou1-19/+41
V2: Checking if shadow is valid. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-16drm/amdgpu: add function pointer to the pte_update_paramsChristian König1-22/+54
Remember what function to call while planning the commands instead of figuring it our later on. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-16drm/amdgpu: stop splitting PTE commands into smaller onesChristian König1-2/+4
It doesn't make much sense to create bigger commands first which we then need to split into smaller one again. Just make sure the commands we create aren't to big in the first place. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-16drm/amdgpu: remove AMDGPU_VM_NO_FLUSH defineChristian König1-3/+0
Not used any more. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-16drm/amdgpu: cleanup the write_pte implementationsChristian König1-13/+7
We don't need the gart mapping handling here any more. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-16drm/amdgpu: remove pages_addr handling from the VM codeChristian König1-9/+1
Not needed any more. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-16drm/amdgpu: write PTEs directly into the IB.Christian König1-5/+21
Write the PTEs at the end of the IB instead of directly into the SDMA commands. This can save quite some CPU cycles building the entries. This doesn't change the DW estimation because PTEs where embedded into the IB before as well. It just moves them to the end of the IB. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Edward O'Callaghan <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-16drm/amdgpu: allocate shadow for pd/pt bo V2Chunming Zhou1-3/+11
The pd/pt shadow bo will be used to backup page table, when gpu reset happens, we can restore the page table by them. V2: Free shadow bo. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-10drm/amdgpu: use more than 64KB fragment size if possibleChristian König1-4/+8
We align to 64KB, but when userspace aligns even more we can easily use more. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-10drm/amdgpu: flip frag_ptes and update_ptsChristian König1-87/+79
We can add the fragment params before we split the update for the page tables. That should save a few CPU cycles for larger updates. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-10drm/amdgpu: add adev to the pte_update_paramsChristian König1-36/+29
No need to carry that forward as a separate parameter. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-10drm/amdgpu: rename amdgpu_vm_update_paramsChristian König1-47/+44
Well those are actually page table entry parameters. This also makes the variable names used a bit shorter. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-10drm/amdgpu: cleanup VM fragment definesChristian König1-1/+1
We can actually do way more than just the 64KB we currently used as default. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-08-09drm/amdgpu: fix vm init error pathChunming Zhou1-1/+4
Signed-off-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-14drm/amdgpu: trace need_flush in grab_vm as wellChristian König1-2/+2
Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-14drm/amdgpu: check flush fence context instead of same ring v2Christian König1-3/+6
Otherwise we can run into the following situation: 1. Process A grabs ID 1 for ring 0. 2. Process B grabs ID 1 for ring 0. 3. Process A grabs ID 1 for ring 1. 4. Process A tries to reuse ID1 for ring 0 but things he doesn't need to flush. v2: check the context of the flush fence instead of messing with the owner field. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: recovery hw jobs when gpu reset V3Chunming Zhou1-1/+2
V3: directly use pd_addr. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: abstract amdgpu_vm_is_gpu_resetChunming Zhou1-1/+8
Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: add a bool to specify if needing vm flush V2Chunming Zhou1-36/+31
which avoids job->vm_pd_addr be changed. V2: pass job structure to amdgpu_vm_grab_id and amdgpu_vm_flush directly. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: must update page table after gpu resetChunming Zhou1-0/+1
Record the gpu reset count in vmid to identify if gpu reset happened. Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: must update page table after gpu resetChunming Zhou1-0/+3
Record the gpu reset count in vmid to identify if gpu reset happened. Reviewed-by: Christian König <[email protected]> Signed-off-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: validate VM PTs only on evictionChristian König1-1/+12
We don't need to validate them again if the eviction counter didn't changed. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: disable compute pipeline sync workaround when using fixed fwAlex Deucher1-1/+27
No need to stall the pipe when we are using firmware with the fix. Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: save the PD addr before scheduling the jobChristian König1-4/+2
When we pipeline evictions the page directory could already be moving somewhere else when grab_id is called. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: sync to buffer moves before VM updatesChristian König1-4/+19
Otherwise we could update the VM page tables while the move is only scheduled. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: Initialize the variables in a straight-forward wayAlex Xie1-6/+28
Initialize the variable in a straight-forward way instead of hiding the initialization inside the loop. This can also reduce one function call. Signed-off-by: Alex Xie <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: Add comment to describe the purpose of one difficult if statementAlex Xie1-4/+7
Use == instead of != in the if statement to make code easier understood Signed-off-by: Alex Xie <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: Change some variable names to make code easier understoodAlex Xie1-16/+16
Add comment to describe some variables otherwise. Signed-off-by: Alex Xie <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: remove now unnecessary checksChristian König1-20/+11
vm_flush() now comes directly after vm_grab_id(). Acked-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Acked-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: use a fence array for VMID managementChristian König1-58/+97
Just wait for any fence to become available, instead of waiting for the last entry of the LRU. Acked-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Acked-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: reuse VMIDs assigned to a VM only if there is also a free oneChristian König1-54/+59
This fixes a fairness problem with the GPU scheduler. VM having lot of jobs could previously starve VM with less jobs. Acked-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Acked-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: prefer VMIDs idle on the current ringChristian König1-15/+9
Prefer to use a VMIDs which are idle on the ring we want to submit to. This also removes bubbling idle VMIDs up on the LRU, which is actually not beneficial. Acked-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Acked-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-07-07drm/amdgpu: add optional ring to amdgpu_sync_is_idleChristian König1-2/+2
Check if the sync object is idle depending on the ring a submission works with. Acked-by: Alex Deucher <[email protected]> Signed-off-by: Christian König <[email protected]> Acked-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-05-11drm/amdgpu: Encapsulate some VM table update parameters (v2)Harish Kasiviswanathan1-49/+62
Bundle some VM table parameters into amdgpu_vm_update_params structure, so that number of function parameters can be reduced. Only structural change, no logic change. v2: agd: squash in fix from Harish Signed-off-by: Harish Kasiviswanathan <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-05-11drm/amdgpu: remove define for reserved client IDChristian König1-1/+1
Just set it to zero instead. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2016-05-11drm/amdgpu: remove owner cleanup v2Christian König1-13/+0
The client ID is now unique, so no need to resert the owner fields any more. v2: remove unused variables as well Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> (v1) Signed-off-by: Alex Deucher <[email protected]>
2016-05-11drm/amdgpu: make the VMID owner always 64bitChristian König1-2/+2
Otherwise we could (in theory) run into problems on 32bit systems. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.