summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
AgeCommit message (Collapse)Author
2017-12-06drm/amdgpu: align GTT start to 4GB v2Christian König
For VCE to work properly the start of the GTT space must be aligned to a 4GB boundary. v2: add comment why we do this 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>
2017-12-06drm/amdgpu: remove VRAM size reduction v2Christian König
Remove some outdated comments and all code which tries to reduce the VRAM size mapped into the MC. This is superfluous and misleading since we never actually program the size. v2: handle gmc_v6_0.c 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>
2017-12-06drm/amdgpu/gmc9: make some ECC messages debug onlyAlex Deucher
To avoid spamming the logs on non-ECC boards. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu: always make gart.table_addr 64bitChristian König
Fixing warning/compile errors on 32bit kernels. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu: require a root bus window above 4GB for BAR resizeChristian König
Don't even try to resize the BAR when there is no window above 4GB. Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu:cancel timer of virtual DCE(v2)Monk Liu
virtual DCE Timer structure is already released after its sw_fini(), so we need to cancel the its Timer in hw_fini() otherwise the Timer canceling is missed. v2: use for loop and num_crtc to replace original code Signed-off-by: Monk Liu <Monk.Liu@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu:fix virtual dce bugMonk Liu
this fix the issue that access memory after freed after driver unloaded. Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu:show error message if fail on event4Monk Liu
Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu:cleanup firmware.fw_buf alloc/freeMonk Liu
use bo_create/free_kernel instead of manually doing it 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>
2017-12-06drm/amdgpu:free CSA in unified placeMonk Liu
instead of doing it in each GFX ip's sw_fini 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>
2017-12-06drm/amdgpu:cleanup unused stack varMonk Liu
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>
2017-12-06drm/amdgpu:fix NULL pointer access during drv removeMonk Liu
NULL pointer is because original logic will step into set_pde_pte() even after the gart.ptr is freed due to there are twice gart_unbind() on all gart area. also, there are other minor fixes: 1,since gart_init only create dummy page, the corresponding gart_fini shouldn't do more like unbinding all GART, this is unnecessary because in driver fini stage all GART unbinding had already been done during each IP's SW_FINI (GMC's SW_FINI is the last one called), so remove the step for the GART unbinding in gart_fini(). 2,gart_fini() is already invoked during each GMC IP's gart_fini routine,e.g. gmc_vx_0_gart_fini(), so no need to manually call it during ttm_fini(). 3,amdgpu_gem_force_release() should be put ahead of amdgpu_vm_manager_fini() 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>
2017-12-06drm/amdgpu:cleanup GMC & gart garbage functionMonk Liu
for gart_ram_alloc/free, they are never used in driver thus ripe them out totally. for gart_vram_pin/unpin, they are not needed becuase we can use bo_creat_kernel/free to replace the original manual way in the gart_vram_alloc/free, thus gart_vram_pin/unpin can also be riped out. 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>
2017-12-06drm/amdgpu:cleanup stolen vga memory finishMonk Liu
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>
2017-12-06amdgpu: Don't use DRM_ERROR when failing to allocate a BOMichel Dänzer
This can be triggered by userspace, e.g. trying to allocate too large a BO, so it shouldn't log anything by default. Callers need to handle failure anyway. Reviewed-by: Alex Deucher <alexander.deucher@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>
2017-12-06drm/amd/amdgpu: not allow gtt size exceed 75%*system memory sizeRoger He
keep consistency with threshold of swapout Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Roger He <Hongbo.He@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu: Add ability to determine and report if board supports ECC.David Panariti
Make initialization code check the ECC related registers, which are initialized by the VBIOS, to see if ECC is present and initialized and DRM_INFO() the result. Signed-off-by: David Panariti <David.Panariti@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu/gfx6: use cached values for raster config in clear stateAlex Deucher
Use the cached values rather than hardcoding it. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu/gfx7: use cached values for raster config in clear stateAlex Deucher
Use the cached values rather than hardcoding it. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu/gfx8: use cached values for raster config in clear stateAlex Deucher
Use the cached values rather than hardcoding it. Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu/virt: remove redundant variable pf2vf_verColin Ian King
Variable pf2vf_ver is assigned but never read, it is redundant and hence can be removed. Cleans up clang warning: drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c:310:3: warning: Value stored to 'pf2vf_ver' is never read Reivewed-by: Horace Chen <horace.chen@amd.com> Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amd/amdgpu: fix UVD mc offsetsPiotr Redlewski
When UVD bo is created, its size is based on the information from firmware header (ucode_size_bytes). The same value should be be used when programming UVD mc controller offsets, otherwise it can happen that (mmUVD_VCPU_CACHE_OFFSET2 + mmUVD_VCPU_CACHE_SIZE2) will point AMDGPU_GPU_PAGE_SIZE bytes after the UVD bo end. Second issue is that when programming the mmUVD_VCPU_CACHE_SIZE0 register, AMDGPU_UVD_FIRMWARE_OFFSET should be taken into account. If it isn't, (mmUVD_VCPU_CACHE_OFFSET2 + mmUVD_VCPU_CACHE_SIZE2) will always point AMDGPU_UVD_FIRMWARE_OFFSET bytes after the UVD bo end. v2: move firmware size calculation into macro definition v3: align firmware size to the gpu page size Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Piotr Redlewski <predlewski@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu: Implement BO size validation V2Andrey Grodzovsky
Validates BO size against each requested domain's total memory. v2: Make GTT size check a MUST to allow fall back to GTT. Rmove redundant NULL check. 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>
2017-12-06drm/amdgpu: cleanup vm_size handlingChristian König
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>
2017-12-06drm/amdgpu: remove nonsense const u32 cast on ARRAY_SIZE resultChristian König
Not sure what that should originally been good for, but it doesn't seem to make any sense 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>
2017-12-06drm/amdgpu: use dep_sync for CS dependency/syncobjChunming Zhou
Otherwise, they could be optimized by scheduled fence. 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>
2017-12-06drm/amdgpu/gfx8: Fix compute ring failure after resettingXiangliang.Yu
Do ring clear before ring test, otherwise compute ring test will fail after gpu resetting. Still can't find the root cause, just workaround it. Signed-off-by: Xiangliang.Yu <Xiangliang.Yu@amd.com> Acked-by: Monk Liu <Monk.Liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-06drm/amdgpu: revise retry init to fully cleanup driverPixel Ding
Retry at drm_dev_register instead of amdgpu_device_init. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Pixel Ding <Pixel.Ding@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu:read VRAMLOST from gimMonk Liu
Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu: bypass FB resizing for SRIOV VFpding
It introduces 900ms latency in exclusive mode which causes failure of driver loading. Host can resize the BAR before guest staring, so the resizing is not necessary here. Signed-off-by: Pixel Ding <Pixel.Ding@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu: release exclusive mode after hw_initpding
Signed-off-by: pding <Pixel.Ding@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdkfd: initialise kfd inside amdgpu_device_initpding
Also finalize kfd inside amdgpu_device_fini. kfd device_init needs SRIOV exclusive accessing. Try to gather exclusive accessing to reduce time consuming. Signed-off-by: pding <Pixel.Ding@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu: don't use ttm_bo_move_ttm in amdgpu_ttm_bind v2Christian König
Just allocate the GART space and fill it. This prevents forcing the BO to be idle. v2: don't unbind/bind at all, just fill the allocated GART space Signed-off-by: Christian König <christian.koenig@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu: rename amdgpu_ttm_bind to amdgpu_ttm_alloc_gartChristian König
We actually don't bind here, but rather allocate GART space if necessary. 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>
2017-12-04drm/amdgpu: switch to use new SOC15 reg read/write macros for soc15 ihHawking Zhang
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu: resize VRAM BAR for CPU access v6Christian König
Try to resize BAR0 to let CPU access all of VRAM. v2: rebased, style cleanups, disable mem decode before resize, handle gmc_v9 as well, round size up to power of two. v3: handle gmc_v6 as well, release and reassign all BARs in the driver. v4: rename new function to amdgpu_device_resize_fb_bar, reenable mem decoding only if all resources are assigned. v5: reorder resource release, return -ENODEV instead of BUG_ON(). v6: squash in rebase fix 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>
2017-12-04drm/amdgpu: refine SR-IOV firmware VRAM reservation to protect dataHorace Chen
The previous solution will create a zero buffer on the system domain and then move the zeroes to the VRAM. This will break the original data on the VRAM. Refine the code to create bo on VRAM domain directly and then remove and re-create mem node to the exact position before bo_pin. This can avoid breaking the data and will not cause eviction. Signed-off-by: Horace Chen <horace.chen@amd.com> Reviewed-by: monk liu <monk.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu: retry init if exclusive mode request is failedpding
This is caused of that hypervisor fails to handle request, one known issue is MMIO unblocking timeout. In theory we can retry init here. Signed-off-by: pding <Pixel.Ding@amd.com> Reviewed-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu: return error when sriov access requests get timeoutpding
Reported-by: Sun Gary <Gary.Sun@amd.com> Signed-off-by: pding <Pixel.Ding@amd.com> Reviewed-by: Xiangliang Yu <Xiangliang.Yu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04amdgpu: Remove AMDGPU_{HPD,CRTC_IRQ,PAGEFLIP_IRQ}_LASTMichel Dänzer
Not used anymore. Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04amdgpu/dce: Use actual number of CRTCs and HPDs in set_irq_funcsMichel Dänzer
Hardcoding the maximum numbers could result in spurious error messages from the IRQ state callbacks, e.g. on Polaris 11/12: [drm:dce_v11_0_set_pageflip_irq_state [amdgpu]] *ERROR* invalid pageflip crtc 5 [drm:amdgpu_irq_disable_all [amdgpu]] *ERROR* error disabling interrupt (-22) Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu: move GART recovery into GTT manager v2Christian König
The GTT manager handles the GART address space anyway, so it is completely pointless to keep the same information around twice. v2: rebased 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>
2017-12-04drm/amdgpu: nuke amdgpu_ttm_is_bound() v2Christian König
Rename amdgpu_gtt_mgr_is_allocated() to amdgpu_gtt_mgr_has_gart_addr() and use that instead. v2: rename the function 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>
2017-12-04drm/amdgpu:fix random missing of FLR NOTIFYMonk Liu
Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu/sriov:fix memory leak in psp_load_fwMonk Liu
for SR-IOV when doing gpu reset this routine shouldn't do resource allocating otherwise memory leak Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-12-04drm/amdgpu:cleanup ucode_init_boMonk Liu
1,no sriov check since gpu recover is unified 2,need CPU_ACCESS_REQUIRED flag for VRAM if SRIOV because otherwise after following PIN the first allocated VRAM bo is wasted due to some TTM mgr reason. 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>
2017-12-04drm/amdgpu:cleanup in_sriov_reset and lock_resetMonk Liu
since now gpu reset is unified with gpu_recover for both bare-metal and SR-IOV: 1)rename in_sriov_reset to in_gpu_reset 2)move lock_reset from adev->virt to adev 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>
2017-12-04drm/amdgpu:implement new GPU recover(v3)Monk Liu
1,new imple names amdgpu_gpu_recover which gives more hint on what it does compared with gpu_reset 2,gpu_recover unify bare-metal and SR-IOV, only the asic reset part is implemented differently 3,gpu_recover will increase hang job karma and mark its entity/context as guilty if exceeds limit V2: 4,in scheduler main routine the job from guilty context will be immedialy fake signaled after it poped from queue and its fence be set with "-ECANCELED" error 5,in scheduler recovery routine all jobs from the guilty entity would be dropped 6,in run_job() routine the real IB submission would be skipped if @skip parameter equales true or there was VRAM lost occured. V3: 7,replace deprecated gpu reset, use new gpu recover 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>
2017-12-04amd/scheduler:imple job skip feature(v3)Monk Liu
jobs are skipped under two cases 1)when the entity behind this job marked guilty, the job poped from this entity's queue will be dropped in sched_main loop. 2)in job_recovery(), skip the scheduling job if its karma detected above limit, and also skipped as well for other jobs sharing the same fence context. this approach is becuase job_recovery() cannot access job->entity due to entity may already dead. v2: some logic fix v3: when entity detected guilty, don't drop the job in the poping stage, instead set its fence error as -ECANCELED in run_job(), skip the scheduling either:1) fence->error < 0 or 2) there was a VRAM LOST occurred on this job. this way we can unify the job skipping logic. with this feature we can introduce new gpu recover feature. 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>
2017-12-04drm/amdgpu: fix indentation in amdgpu_display.hChristian König
That was somehow completely of. 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>
generated by cgit v1.2.3 (git 2.39.1) at 2025-08-05 08:37:21 +0000