summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2017-07-14drm/amdgpu: call atomfirmware get_clock_info for atomfirmware systemsAlex Deucher
Rather than the legacy atombios version. Acked-by: Chunming Zhou <david1.zhou@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: add get_clock_info for atomfirmwareAlex Deucher
The information has moved to different tables, notably smu_info for core refclk and umc_info for mem refclk. Acked-by: Chunming Zhou <david1.zhou@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Send no-retry XNACK for all fault typesJay Cornwall
A subset of VM fault types currently send retry XNACK to the client. This causes a storm of interrupts from the VM to the host. Until the storm is throttled by other means send no-retry XNACK for all fault types instead. No change in behavior to the client which will stall indefinitely with the current configuration in any case. Improves system stability under GC or MMHUB faults. Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: John Bridgman <John.Bridgman@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Correctly establish the suspend/resume hook for amdkfdYong Zhao
Signed-off-by: Yong Zhao <yong.zhao@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Make SDMA phase quantum configurableFelix Kuehling
Set a configurable SDMA phase quantum when enabling SDMA context switching. The default value significantly reduces SDMA latency in page table updates when user-mode SDMA queues have concurrent activity, compared to the initial HW setting. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Andres Rodriguez <andres.rodriguez@amd.com> Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com> Acked-by: Chunming Zhou <david1.zhou@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Enable SDMA context switching for CIKFelix Kuehling
Enable SDMA context switching on CIK (copied from sdma_v3_0.c). Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Enable SDMA_CNTL.ATC_L1_ENABLE for SDMA on CZshaoyunl
For GFX context, the ATC bit in SDMA*_GFX_VIRTUAL_ADDRESS can be cleared to perform in VM mode. For RLC context, to support ATC mode , ATC bit in SDMA*_RLC*_VIRTUAL_ADDRESS should be set. SDMA_CNTL.ATC_L1_ENABLE bit is global setting that enables the L1-L2 translation for ATC address. Signed-off-by: shaoyun liu <shaoyun.liu@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>
2017-07-14drm/amdgpu: Try evicting from CPU visible to invisible VRAM firstMichel Dänzer
This gives BOs which haven't been accessed by the CPU since they were moved to visible VRAM another chance to stay in VRAM when another BO needs to go to visible VRAM. This should allow BOs to stay in VRAM longer in some cases. v2: * Only do this for BOs which don't have the AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED flag set. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Don't force BOs into visible VRAM for page faultsJohn Brooks
There is no need for page faults to force BOs into visible VRAM if it's full, and the time it takes to do so is great enough to cause noticeable stuttering. Add GTT as a possible placement so that if visible VRAM is full, page faults move BOs to GTT instead of evicting other BOs from VRAM. Suggested-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: John Brooks <john@fastquake.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Set/clear CPU_ACCESS flag on page fault and move to VRAMJohn Brooks
When a BO is moved to VRAM, clear AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED. This allows it to potentially later move to invisible VRAM if the CPU does not access it again. Setting the CPU_ACCESS flag in amdgpu_bo_fault_reserve_notify() also means that we can remove the loop to restrict lpfn to the end of visible VRAM, because amdgpu_ttm_placement_init() will do it for us. v3 [Michel Dänzer] * Use AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED instead of a new flag (Christian König) * Clear flag in amdgpu_bo_move instead of amdgpu_move_ram_vram (Christian) * Explicitly mention amdgpu_bo_fault_reserve_notify in amdgpu_bo_move * Also clear flag in amdgpu_bo_create_restricted Suggested-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: John Brooks <john@fastquake.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Throttle visible VRAM moves separatelyJohn Brooks
The BO move throttling code is designed to allow VRAM to fill quickly if it is relatively empty. However, this does not take into account situations where the visible VRAM is smaller than total VRAM, and total VRAM may not be close to full but the visible VRAM segment is under pressure. In such situations, visible VRAM would experience unrestricted swapping and performance would drop. Add a separate counter specifically for moves involving visible VRAM, and check it before moving BOs there. v2: Only perform calculations for separate counter if visible VRAM is smaller than total VRAM. (Michel Dänzer) v3: [Michel Dänzer] * Use BO's location rather than the AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED flag to determine whether to account a move for visible VRAM in most cases. * Use a single if (adev->mc.visible_vram_size < adev->mc.real_vram_size) { block in amdgpu_cs_get_threshold_for_moves. Fixes: 95844d20ae02 (drm/amdgpu: throttle buffer migrations at CS using a fixed MBps limit (v2)) Signed-off-by: John Brooks <john@fastquake.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Add vis_vramlimit module parameterJohn Brooks
Allow specifying a limit on visible VRAM via a module parameter. This is helpful for testing performance under visible VRAM pressure. v2: Add cast to 64-bit (Christian König) Signed-off-by: John Brooks <john@fastquake.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: change gartsize default to 256MBChristian König
Limit the default GART size and save a lot of VRAM. 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>
2017-07-14drm/amdgpu: add new gttsize module parameter v2Christian König
This allows setting the gtt size independent of the gart size. v2: fix copy and paste typo 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>
2017-07-14drm/amdgpu: limit the GTT manager address spaceChristian König
We should only cover the GART size with the GTT manager. 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>
2017-07-14drm/amdgpu: consistent name all GART related partsChristian König
Rename symbols from gtt_ to gart_ as appropriate. 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>
2017-07-14drm/amdgpu: remove gtt_base_align handlingChristian König
Not used any more. 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>
2017-07-14drm/amdgpu: move GART struct and function into amdgpu_gart.h v2Christian König
No functional change, just cleanup. v2: rebased, keep gart name. 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>
2017-07-14drm/amdgpu: check scratch registers to see if we need post (v2)Alex Deucher
Rather than checking the CONGIG_MEMSIZE register as that may not be reliable on some APUs. v2: The scratch register is only used on CIK+ Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu/soc15: init nbio registers for vega10Alex Deucher
Call nbio init registers on hw_init to set up any nbio registers that need initialization at hw init time. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: add nbio 6.1 register init functionAlex Deucher
Used for nbio registers that need to be initialized. Currently only used for a golden setting that got missed on some boards. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: added didt support for vega10Evan Quan
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: added grbm_idx_mutex lock/unlock to cgs v2Evan Quan
- v2: rename param 'en' as 'lock' Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: added support for new se_cac_idx APIs to cgsEvan Quan
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: added soc15 support for new se_cac_idx APIsEvan Quan
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: added new se_cac_idx r/w APIs v2Evan Quan
- v2: added missing spinlock init Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: added index gc cac read/write apis for vega10Evan Quan
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: use TTM values instead of MC values for the info queriesChristian König
Use the TTM values instead of the hardware config here. 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>
2017-07-14drm/amdgpu: remove maximum BO size limitation v2Christian König
We can finally remove this now. v2: remove now unused max_size variable 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>
2017-07-14drm/amdgpu: stop mapping BOs to GTTChristian König
No need to map BOs to GTT on eviction and intermediate transfers any more. 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>
2017-07-14drm/amdgpu: use the GTT windows for BO moves v2Christian König
This way we don't need to map the full BO at a time any more. v2: use fixed windows for src/dst 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>
2017-07-14drm/amdgpu: add amdgpu_gart_map function v2Christian König
This allows us to write the mapped PTEs into an IB instead of the table directly. v2: fix build with debugfs enabled, remove unused assignment 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>
2017-07-14drm/amdgpu: reserve the first 2x512 pages of GARTChristian König
We want to use them as remap address space. 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>
2017-07-14drm/amdgpu: make arrays pctl0_data and pctl1_data staticColin Ian King
The arrays pctl0_data and pctl1_data do not need to be in global scope, so them both static. Cleans up sparse warnings: symbol 'pctl0_data' was not declared. Should it be static? symbol 'pctl1_data' was not declared. Should it be static? Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu/gmc9: get vram width from atom for RavenAlex Deucher
Get it from the system info table. Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu/atomfirmware: implement vram_width for APUsAlex Deucher
Implement support using the new atomfirmware system info table. Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu/atom: fix atom_fw checkAlex Deucher
Not all vbios images seem to set the version appropriately. Switch the check based on asic type instead. Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Free resources of bo_list when idr_alloc failsAlex Xie
Signed-off-by: Alex Xie <AlexBin.Xie@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian König<christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: add avfs check for old asics on Vi.Rex Zhu
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: move VI common AVFS code to smu7_smumgr.cRex Zhu
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: refine avfs enable code on fiji.Rex Zhu
1. simplify avfs state switch. 2. delete save/restore VFT table functions as not support by fiji. 3. implement thermal_avfs_enable funciton. Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: fix avfs state update error on polaris.Rex Zhu
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amd/powerplay: fixed wrong data type declaration for ppfeaturemaskEvan Quan
Signed-off-by: Evan Quan <evan.quan@amd.com> Reviewed-by: Rex Zhu <Rex.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: set firmware loading type as direct by default for ravenHuang Rui
In previous case, driver can't enable psp via the kernel parameter for raven. We should open this path and set it as direct by default till psp firmware loading is workable. Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: make psp cmd buffer as a reserve memoryHuang Rui
Signed-off-by: Huang Rui <ray.huang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: fix missed asd bo free when hw_finiHuang Rui
Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: remove superfluous checkHuang Rui
Signed-off-by: Huang Rui <ray.huang@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: NO KIQ usage on nbio hdp flush routineShaoyun Liu
nbio hdp flush routine are called within atomic context. Avoid use KIQ when write to the HDP_MEM_COHERENCY_FLUSH_CNTL register since this register has its own VF copy Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu: Add WREG32_SOC15_NO_KIQ macro defineShaoyun Liu
Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-07-14drm/amdgpu:fix world switch hangMonk Liu
for SR-IOV, we must keep the pipeline-sync in the protection of COND_EXEC, otherwise the command consumed by CPG is not consistent when world switch triggerd, e.g.: world switch hit and the IB frame is skipped so the fence won't signal, thus CP will jump to the next DMAframe's pipeline-sync command, and it will make CP hang foever. after pipelin-sync moved into COND_EXEC the consistency can be guaranteed Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>