aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
AgeCommit message (Collapse)AuthorFilesLines
2015-06-03drm/amdgpu: add hdp flush for gfx8 compute ringmonk.liu1-0/+1
We had forgotten to register the callback. Signed-off-by: monk.liu <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: jammy zhou <[email protected]>
2015-06-03drm/amdgpu: fix no hdp flush for compute ringmonk.liu1-1/+3
No pfp on compute. Signed-off-by: monk.liu <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: add HEVC/H.265 UVD supportChristian König1-0/+8
Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: stop loading firmware with pm.mutex lockedChristian König1-4/+4
Loading firmware is a rather complicated process, in the end we add a dependency between the pm mutex and the mm semaphore which results in a harmless but annoying error message. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: remove mclk_lockChristian König5-43/+4
Not needed any more. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: fix description of vm_size module parameter (v2)Alex Deucher2-4/+4
default is 8GB, not 4GB. v2: fix fallback setting when the user provides an invalid input Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: remove all sh mem register modification in vm flushmonk.liu5-160/+0
Leave that at the values set during init. No need to update them repeatedly. Signed-off-by: monk.liu <[email protected]> Signed-off-by: David Zhang <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: rename GEM_OP_SET_INITIAL_DOMAIN -> GEM_OP_SET_PLACEMENTMarek Olšák1-1/+1
Signed-off-by: Marek Olšák <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: fence should be added to shared slotmonk.liu1-2/+2
Signed-off-by: monk.liu <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: jammy zhou <[email protected]>
2015-06-03drm/amdgpu: sync fence of clear_invalids (v2)monk.liu3-4/+6
bo_va may un-initialized, fix it. Signed-off-by: monk.liu <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: max_pde_used usage should be under protectmonk.liu1-1/+5
Need to take the lock when accessing this. Signed-off-by: monk.liu <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: fix bug of vm_bo_map (v2)monk.liu1-0/+4
call reservation_object_reserve_shared before amdgpu_bo_fence Signed-off-by: monk.liu <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: implement the allocation range (v3)Chunming Zhou8-64/+136
Pass a ttm_placement pointer to amdgpu_bo_create_restricted add min_offset to amdgpu_bo_pin_restricted. This makes it easier to allocate memory with address restrictions. With this patch we can also enable 2-ended allocation again. v2: fix rebase conflicts v3: memset placements before using Reviewed-by: Jammy Zhou <[email protected]> Signed-off-by: Chunming Zhou <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: rename amdgpu_ip_funcs to amd_ip_funcs (v2)yanyang154-707/+986
The structure is renamed and moved to amd_shared.h to make the component independent. This makes it easier to add new components in the future. v2: fix include path Reviewed-by: Jammy Zhou <[email protected]> Signed-off-by: yanyang1 <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: drop AMDGPU_FENCE_SIGNALED_SEQChristian König2-15/+0
It's causing issues with VMID handling and comparing the fence value two times actually doesn't make handling faster. Port of radeon commit "d6d5c5b8364bcc4d52cddc68bcb0a330d2af20f3". Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Monk Liu <[email protected]>
2015-06-03drm/amdgpu: port fault_reserve_notify changes from radeonChristian König1-20/+35
Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: enable uvd dpm and powergatingSonny Jiang3-3/+91
Enable UVD dpm (dynamic power management) and powergating. UVD dpm dynamically scales the UVD clocks on demand. Powergating turns off the power to the block when it's not in use. Signed-off-by: Sonny Jiang <[email protected]> Acked-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: implement VCE two instances supportLeo Liu1-54/+87
VCE 3.0 has two indentical instances in the engine, they share the same registers name in differrent memory block distinguished by the grbm_gfx_index, we set to master instance after init, it will dispatch task to slave instance. These two instances will share the same firmware, but have their own stacks and heaps. v2: add mutex for using grbm_gfx_index Signed-off-by: Leo Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: recalculate VCE firmware BO sizeLeo Liu5-15/+20
Firmware required BO size changes in terms of ASIC family Signed-off-by: Leo Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: remove unused TRACE_SYSTEM_STRING defineAlex Deucher1-1/+0
Port of 77cb2fea1e5fc4b083dd967f231bbf6edd96150e to amdgpu. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: rework tiling flagsMarek Olšák5-286/+36
Signed-off-by: Marek Olšák <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: don't set unused tiling flagsMarek Olšák1-13/+1
Signed-off-by: Marek Olšák <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Acked-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: actually use the VM map parametersChristian König1-2/+3
Signed-off-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: validate amdgpu_vm_bo_map parametersChristian König1-0/+7
Signed-off-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: enforce AMDGPU_GEM_CREATE_NO_CPU_ACCESSChristian König2-1/+5
Deny user and kernel mapping if we said we never want to do so. Signed-off-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: fix VM_CONTEXT*_PAGE_TABLE_END_ADDR handlingChristian König2-4/+4
Signed-off-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: retry dcpd fetchAlex Deucher1-9/+11
Retry the dpcd fetch several times. Some eDP panels fail several times before the fetch is successful. bug: https://bugs.freedesktop.org/show_bug.cgi?id=73530 Ported from radeon. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: simplify DPCD debug outputAlex Deucher1-5/+4
Use %*ph rather than walking the array. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: make some DP parameters constAlex Deucher1-7/+7
Ported from similar radeon patch. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: take the mode_config mutex when handling hpdsAlex Deucher1-0/+2
Since we may modify display state. Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: add and implement the GPU reset status queryMarek Olšák3-16/+27
Signed-off-by: Marek Olšák <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: add some new tonga pci idsAlex Deucher1-0/+2
Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: add new bonaire pci idAlex Deucher1-0/+1
Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2015-06-03drm/amdgpu: rewording some left radeonsJammy Zhou2-3/+3
Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: switch to amdgpu folder for firmware files v2Jammy Zhou8-47/+47
v2: keep using radeon folder for CIK Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: do necessary NULL checkJammy Zhou1-2/+5
Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: expose the max virtual addressJammy Zhou1-0/+1
Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: fix context switchChristian König5-21/+26
Properly protect the state and also handle submission failures. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Monk Liu <[email protected]>
2015-06-03drm/amdgpu: fix dereference before checkChristian König1-2/+4
Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Monk Liu <[email protected]>
2015-06-03drm/amdgpu: cleanup HDP flush handlingChristian König7-54/+18
Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Monk Liu <[email protected]>
2015-06-03drm/amdgpu: always emit GDS switchChristian König1-1/+1
Otherwise a process can access the GDS data of another process. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Monk Liu <[email protected]>
2015-06-03drm/amdgpu: add CE preamble flag v3Jammy Zhou2-0/+14
The CE preamble IB can be dropped for the same context v2: use the flags directly v3: remove 'CE' for potential preamble usage by other rings Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: add flags for amdgpu_ib structureJammy Zhou5-10/+7
Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: check context id for context switching (v2)Jammy Zhou2-1/+4
check the filp is not robust, and sometimes different contexts may have same filp value. v2: check both filp and ctx_id Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: add ctx_id to the WAIT_CS IOCTL (v4)Jammy Zhou3-0/+38
It is required to support fence per context. v2: add amdgpu_ctx_get/put v3: improve get/put v4: squash hlock fix Signed-off-by: Jammy Zhou <[email protected]> Reviewed-by: Christian König <[email protected]>
2015-06-03drm/amdgpu: allow unaligned memory access (v2)Jack Xiao5-4/+22
Set up the CP and SDMA for proper unaligned memory access. Required for OpenCL 2.x v2: udpate commit message Signed-off-by: Jack Xiao <[email protected]> Reviewed-by: Monk Liu <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: make the CTX ioctl thread-safeMarek Olšák3-12/+12
The existing locks were protecting the list, but not the elements. v2: rename hlock to lock Signed-off-by: Marek Olšák <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: remove unsafe context releasingMarek Olšák1-10/+2
If ctx was released between put and get, then "get" would crash. Signed-off-by: Marek Olšák <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]>
2015-06-03drm/amdgpu: fix userptr lockupChristian König1-0/+3
Signed-off-by: Christian König <[email protected]> Reviewed-by: Jammy Zhou <[email protected]> Reviewed-by: Monk Liu <[email protected]>
2015-06-03drm/amdgpu: fix userptr BO unpin bug (v2)monk.liu1-5/+3
sg could point to array of contigiouse page*, only free page could lead to memory leak. v2: use iterator Signed-off-by: monk.liu <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.