aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
AgeCommit message (Collapse)AuthorFilesLines
2018-02-28drm/amdgpu: cond_exec only for schedule with a jobMonk Liu1-1/+1
issue: under SR-IOV sometimes the iB test will fail on gfx ring fix: with cond_exec inserted in RB the gfx engine would skip part packets if RLCV issue PREEMPT on gfx engine if gfx engine is prior to COND_EXEC packet, this is okay for regular command from UMD, but for the ib test since the whole dma format doesn't support PREEMPT so must remove the COND_EXEC from it. Signed-off-by: Monk Liu <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-28drm/amdgpu: only flush hotplug work without DCMonk Liu1-2/+4
since hotplug_work is initialized under the case of no dc support Signed-off-by: Monk Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-28drm/amdgpu: skip ECC for SRIOV in gmc late_initMonk Liu1-1/+1
Signed-off-by: Monk Liu <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-28drm/amdgpu: fix&cleanups for wb_clearMonk Liu2-3/+4
fix: should do right shift on wb before clearing cleanups: 1,should memset all wb buffer 2,set max wb number to 128 (total 4KB) is big enough Signed-off-by: Monk Liu <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/amd/amdgpu: Correct VRAM width for APUs with GMC9Tom St Denis1-1/+4
DDR4 has a 64-bit width not 128-bits. It was reporting twice the width. Tested with my Ryzen 2400G. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: drop persistent_swap_storage from ttm_bo_init and coChristian König1-2/+2
Never used as parameter, the only driver actually using this is nouveau and there it is initialized after the BO is initialized. Signed-off-by: Christian König <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: drop ttm->dummy_read_pageChristian König1-3/+2
Only used by the AGP backend and there it can be easily accessed using ttm->bdev->glob. Signed-off-by: Christian König <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/amd: remove inclusion of non-existing scheduler directoryCorentin Labbe1-1/+0
The scheduler directory was removed via commit 1b1f42d8fde4 ("drm: move amd_gpu_scheduler into common location") Remove it from include path. Reviewed-by: Christian König <[email protected]> Signed-off-by: Corentin Labbe <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/amdgpu: Remove duplicate setting of ->need_swiotlbThierry Reding1-1/+0
There's no need to set this before the number of DMA bits has been properly determined. Signed-off-by: Thierry Reding <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/amdgpu: Change default value of module parameter amdgpu_pp_feature_maskRex Zhu1-1/+1
Currently all pp features are enabled by default except OVERDRIVE Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/amdgpu: Add query vram width in CGS query system infoRex Zhu1-0/+3
powerplay need vram width to set default mclk optimization settings(uphyst/downhyst/activity threshold) Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/amdgpu: use the TTM dummy page instead of allocating oneChristian König13-41/+30
We have a global dummy page in TTM, use that one instead of allocating a new one. Signed-off-by: Christian König <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: use bit flag to replace allow_reserved_eviction in ttm_operation_ctxRoger He2-4/+4
for saving memory and more bit flag can be used in future Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-20drm/amdgpu: use drm_gem_private_object_initChristian König1-5/+1
We use our own backing store and don't need the shmem file. Signed-off-by: Christian König <[email protected]> Acked-by: Daniel Vetter <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-20drm/amdgpu: mitigate workaround for i915Christian König1-11/+20
To be able to use DRI_PRIME with amdgpu and i915 we add all our fences only as exclusive ones. Disable that behavior when sharing between amdgpu itself cause it hinders concurrent execution. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-20drm/amdgpu: implement amdgpu_gem_map_(attach/detach)Christian König3-22/+34
Instead of the pin/unpin callback implement the attach/detach ones. Functional identical, but allows us access to the attachment. Signed-off-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu/cgs: add refresh rate checking to non-DC display codeAlex Deucher1-0/+5
Clamp the vblank period to 0 if the refresh rate is larger than 120 hz for non-DC. This allows us to remove the refresh rate checks from powerplay for mclk switching. Reviewed-by: Eric Huang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu_gem: fix error handling path in amdgpu_gem_va_update_vmGustavo A. R. Silva1-3/+4
Currently, if amdgpu_vm_bo_update() fails, the returned error is being ignored. Fix this by properly checking _r_ after calling amdgpu_vm_bo_update. Also, remove redundant code just before label _error_. Addresses-Coverity-ID: 1464280 ("Unused value") Fixes: 0abc6878fc2d ("drm/amdgpu: update VM PDs after the PTs") Signed-off-by: Gustavo A. R. Silva <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: update the PASID mapping only on demandChristian König3-9/+32
Updating the PASID is rather heavyweight and shouldn't be done all the time. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: separate PASID mapping from VM flush v2Christian König22-76/+79
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 <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Fix potential uninitialized use of 'idle' in amdgpu_ids.cHarry Wentland1-1/+2
v2: Use NULL and reverse christmas tree ordering Signed-off-by: Harry Wentland <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Unify the dm resume calls into oneMikita Lipski1-9/+0
amdgpu_dm_display_resume is now called from dm_resume to unify DAL resume call into a single function call There is no more need to separately call 2 resume functions for DM. Initially they were separated to resume display state after cursor is pinned. But because there is no longer any corruption with the cursor - the calls can be merged into one function hook. Signed-off-by: Mikita Lipski <[email protected]> Reviewed-by: Harry Wentland <[email protected]> Reviewed-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Add a missing lock for drm_mm_takedownMikita Lipski1-1/+1
Inside amdgpu_gtt_mgr_fini add a missing lock to maintain locking balance Signed-off-by: Mikita Lipski <[email protected]> Reviewed-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: cleanup VCN IB generationChristian König1-69/+18
Start to use amdgpu_bo_create_reserved v2. v2: Fix missing pointer init to NULL. Remove extra new lines. Signed-off-by: Christian König <[email protected]> Signed-off-by: Andrey Grodzovsky <[email protected]> Tested-and-Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: fix and cleanup UVD IB generationChristian König1-68/+38
We didn't synced the BO after validating it. Also sart to use amdgpu_bo_create_reserved to simplify things. Signed-off-by: Christian König <[email protected]> Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: remove extra TT unpopulated checkChristian König1-3/+0
The subsystem should check that, not the driver. Signed-off-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Add place holder for soc15 asic init on emulationShaoyun Liu4-15/+40
Add common smu_soc_asic_init function to emulate the sillicon post sequence Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Double the timeout count on emulation modeShaoyun Liu1-0/+2
Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Avoid get vram info from atom bios on emulation modeShaoyun Liu1-1/+2
Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Fix none-powerplay issue when load driver on emulation modeShaoyun Liu2-0/+11
On emulation mode , driver will be loaded with powerplay disabled Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Basic emulation supportShaoyun Liu3-3/+28
Add amdgpu_emu_mode module parameter to control the emulation mode Avoid vbios operation on emulation since there is no vbios post duirng emulation, use the common hw_init to simulate the post Signed-off-by: Shaoyun Liu <[email protected]> Acked-By: Alex Deucher <[email protected]> Acked-By: Christian Konig <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: add new device to use atpx quirkKai-Heng Feng1-0/+1
The affected system (0x0813) is pretty similar to another one (0x0812), it also needs to use ATPX power control. Signed-off-by: Kai-Heng Feng <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2018-02-19drm/amdgpu: Get/set dgpu power cap via hwmon APIRex Zhu1-0/+75
v2: change power unit to microWatt Adust power limit through power1_cap Get min/max power limit through power1_cap_min/power1_cap_max Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Enable ip block bit mask print out info by defaultShaoyun Liu1-1/+1
Signed-off-by: Shaoyun Liu <[email protected]> Reviewed-by: Christian Konig <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: add mmhub powergating set by smuEric Huang1-0/+3
PSP will disable legacy mmhub PG setting that is programming registers, and drive will use SMC message to set it up. Signed-off-by: Eric Huang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: add an interface of amdgpu_dpm_set_mmhub_powergating_by_smuEric Huang1-0/+4
Signed-off-by: Eric Huang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: sync the VM PD/PT before clearing itChristian König1-0/+5
Otherwise we might overwrite stuff which is still in use. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: clear the shadow fence as wellChristian König1-0/+5
It also needs to be initialized. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: release the VM shadow in the error path as wellChristian König1-0/+2
Without it we run into a memory leak. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: remove unused display_vblank_wait interfaceAlex Deucher7-259/+0
No longer used since we changed the MC programming sequence. Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu/dce: fix mask in dce_v*_0_is_in_vblankAlex Deucher3-3/+3
Using the wrong mask. Reviewed-by: Michel Dänzer <[email protected]> Noticed-by: Hans de Ruiter <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: cache the fence to wait for a VMIDChristian König3-2/+9
Beneficial when a lot of processes are waiting for VMIDs. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: restructure amdgpu_vmid_grabChristian König1-47/+42
Now that we have the different cases for grabbing a VMID in separate functions, restructure the top level function to only have one place where VMIDs are assigned to jobs. Signed-off-by: Christian König <[email protected]> Acked-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: move reusing VMIDs into separate functionChristian König1-49/+81
Let's try this once more. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: cleanup and simplify amdgpu_vmid_grab_reservedChristian König1-23/+35
Drop the "_locked" from the name, cleanup and simplify the logic a bit. Add missing comments. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: stop checking GPU reset counter during VMID grabChristian König1-5/+1
We do this later on when we flush the VMID anyway. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: make VMID owner none atomic v2Christian König2-6/+8
The variable is protected by the VMID mutex anyway. v2: grab the mutex while resetting the VMID as well Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: split finding idle VMID into separate functionChristian König1-47/+69
No functional change, but makes it easier to maintain the code. Signed-off-by: Christian König <[email protected]> Reviewed-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: make VMID assignment more fair v2Christian König1-5/+7
Similar to finding an idle one before reuse. This guarantees fairness between processes. Otherwise process with a reserved VMID have an unfair advantage while scheduling jobs. v2: improve commit message Signed-off-by: Christian König <[email protected]> Acked-by: Chunming Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/amdgpu: Fix always_valid bos multiple LRU insertions.Bas Nieuwenhuizen2-3/+5
If these bos are evicted and are in the validated list things blow up, so do not put them in there. Notably, that tries to add the bo to the LRU twice, which results in a BUG_ON in ttm_bo.c. While for the bo_list an alternative would be to not allow always valid bos in there, that does not work for the user fence. v2: Fixed whitespace issue pointed out by checkpatch.pl Signed-off-by: Bas Nieuwenhuizen <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
Powered by cgit, Gruvboxed by Blaster4385.