aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/ttm
AgeCommit message (Collapse)AuthorFilesLines
2018-05-15drm/ttm: remove priority hard code when initializing ttm boJunwei Zhang1-1/+0
Then priority could be set before initialization. By default, it requires to kzalloc ttm bo. In fact, we always do so. Signed-off-by: Junwei Zhang <[email protected]> Reviewed-by: David Zhou <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/ttm: Use GFP_TRANSHUGE_LIGHT for allocating huge pagesMichel Dänzer2-4/+10
GFP_TRANSHUGE tries very hard to allocate huge pages, which can result in long delays with high memory pressure. I have observed firefox freezing for up to around a minute due to this while restic was taking a full system backup. Since we don't really need huge pages, use GFP_TRANSHUGE_LIGHT | __GFP_NORETRY instead, in order to fail quickly when there are no huge pages available. Set __GFP_KSWAPD_RECLAIM as well, in order for huge pages to be freed up in the background if necessary. With these changes, I'm no longer seeing freezes during a restic backup. Cc: [email protected] Reviewed-by: Christian König <[email protected]> Signed-off-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-05-15drm/ttm: keep a reference to transfer pipelined BOsChristian König1-20/+30
Make sure the transfered BO is never destroy before the transfer BO. Signed-off-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-03-22drm/ttm: Export the ttm_k[un]map_atomic_prot API.Thomas Hellstrom1-5/+26
It will be used by vmwgfx cpu blit. Reviewed-by: Christian König <[email protected]> Reviewed-by: Brian Paul <[email protected]> Signed-off-by: Thomas Hellstrom <[email protected]>
2018-03-22drm/ttm: Clean up kmap_atomic_prot selection codeThomas Hellstrom1-33/+31
Use helpers to perform the kmap_atomic_prot() functionality to a) Avoid in-function ifdefs that violate the kernel coding policy, b) Facilitate exporting the functionality. This commit should not change any functionality. Reviewed-by: Christian König <[email protected]> Signed-off-by: Thomas Hellstrom <[email protected]>
2018-03-14drm/ttm: move initializing ttm->sg into ttm_tt_init_fieldsChristian König1-3/+1
Better to set this with all other fields as well. Signed-off-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-03-14drm/ttm: add bo as parameter to the ttm_tt_create callbackChristian König2-18/+17
Instead of calculating the size in bytes just to recalculate the number of pages from it pass the BO directly to the function. Signed-off-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-03-14drm/ttm: add ttm_bo_pipeline_guttingChristian König2-3/+36
Allows us to gut a BO of it's backing store when the driver says that it isn't needed any more. Signed-off-by: Christian König <[email protected]> Acked-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-03-14drm/ttm: add ttm_sg_tt_initChristian König1-9/+45
This allows drivers to only allocate dma addresses, but not a page array. Signed-off-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-03-14drm/ttm: move ttm_tt defines into ttm_tt.hChristian König1-6/+0
Let's stop mangling everything in a single header and create one header per object instead. Signed-off-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Acked-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: cleanup ttm_tt_createChristian König1-16/+13
Cleanup ttm_tt_create a bit. Signed-off-by: Christian König <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: move ttm_tt_create into ttm_tt.c v2Christian König2-48/+48
Rename ttm_bo_add_ttm to ttm_tt_create and move it into ttm_tt.c. v2: separate the cleanup. Signed-off-by: Christian König <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: check if free mem space is under the lower limitRoger He3-0/+99
the free mem space and the lower limit both include two parts: system memory and swap space. For the OOM triggered by TTM, that is the case as below: first swap space is full of swapped out pages and soon system memory also is filled up with ttm pages. and then any memory allocation request will run into OOM. to cover two cases: a. if no swap disk at all or free swap space is under swap mem limit but available system mem is bigger than sys mem limit, allow TTM allocation; b. if the available system mem is less than sys mem limit but free swap space is bigger than swap mem limit, allow TTM allocation. v2: merge two memory limit(swap and system) into one v3: keep original behavior except ttm_opt_ctx->flags with TTM_OPT_FLAG_FORCE_ALLOC v4: always set force_alloc as tx->flags & TTM_OPT_FLAG_FORCE_ALLOC v5: add an attribute for lower_mem_limit v6: set lower_mem_limit as 0 to keep original behavior Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: drop persistent_swap_storage from ttm_bo_init and coChristian König1-7/+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 König3-14/+8
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/ttm: drop ttm->globChristian König3-10/+9
The pointer is available as ttm->bdev->glob as well. 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 bo->globChristian König3-15/+16
The pointer is available as bo->bdev->glob as well. Signed-off-by: Christian König <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: add default implementations for ttm_tt_(un)populateChristian König1-2/+8
Use ttm_pool_populate/ttm_pool_unpopulate if the driver doesn't provide a function. Signed-off-by: Christian König <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: set TTM_OPT_FLAG_FORCE_ALLOC in ttm_bo_force_list_cleanRoger He1-1/+5
Because ttm_bo_force_list_clean() is only called on two occasions: 1. By ttm_bo_evict_mm() during suspend. 2. By ttm_bo_clean_mm() when the driver unloads. On both cases we absolutely don't want any memory allocation failure. Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-26drm/ttm: add bit flag TTM_OPT_FLAG_FORCE_ALLOCRoger He1-1/+3
set TTM_OPT_FLAG_FORCE_ALLOC when we are servicing for page fault routine. for ttm_mem_global_reserve if in page fault routine, allow the gtt pages reservation always. because page fault routing already grabbed system memory and the allowance of this exception is harmless. Otherwise, it will trigger OOM killer. will be used later. v2: set the FORCE_ALLOC always v3: minor refine Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[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 He1-1/+2
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]>
2018-02-26drm/ttm: set page mapping during allocationChristian König2-2/+17
To aid debugging set the page mapping during allocation instead of during VM faults. Signed-off-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: add ttm_tt_populate wrapperChristian König3-9/+15
Stop calling the driver callback directly. Signed-off-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Simplify ttm_dma_page_put()Tom St Denis1-3/+1
Remove redundant store of return code. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Fix coding style in ttm_dma_pool_alloc_new_pages()Tom St Denis1-2/+1
Add missing {} braces. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Fix coding style in ttm_tt_swapout()Tom St Denis1-1/+2
Add missing {} braces. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Simplify ttm_eu_reserve_buffers()Tom St Denis1-6/+8
Hoist the comparison of the ret to -EDEADLK above the two code paths to simplify the function. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Remove unncessary retval from ttm_bo_vm_fault()Tom St Denis1-15/+13
The dual ret/retval was more complex than need be. Now we drop the retval variable and assign the appropriate VM codes to ret instead. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Fix coding style in ttm_bo_move_memcpy()Tom St Denis1-1/+2
Add missing {} braces. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Simplify ttm_dma_find_pool() (v2)Tom St Denis1-9/+6
Flip the logic of the comparison and remove the redudant variable for the pool address. (v2): Remove {} bracing. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Fix coding style in ttm_pool_store()Tom St Denis1-3/+4
Correct missing {} style. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Change ttm_tt page allocations to return errorsTom St Denis1-6/+10
Explicitly return errors in ttm_tt_alloc_page_directory() and ttm_dma_tt_alloc_page_directory() instead of relying on further logic to detect errors. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Add a default BO destructor to simplify code (v2)Tom St Denis1-5/+8
(v2): Remove stray ; noticed by Felix Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Fix coding style in ttm_bo.cTom St Denis1-5/+2
Correct indentation and {} brace style. Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: add the missed global memory count updateRoger He1-16/+25
when ttm_mem_global_alloc_page fails, we should call ttm_mem_global_free_page to update memory count for the ttm pages which already run ttm_mem_global_alloc_page successfully Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-02-19drm/ttm: Allow page allocations w/o triggering OOM..Andrey Grodzovsky4-2/+23
This to allow drivers to choose to avoid OOM invocation and handle page allocation failures instead. v2: Remove extra new lines. Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-29drm/ttm: Fix 'buf' pointer update in ttm_bo_vm_access_kmap() (v2)Tom St Denis1-1/+2
The buf pointer was not being incremented inside the loop meaning the same block of data would be read or written repeatedly. (v2) Change 'buf' pointer to uint8_t* type Cc: [email protected] Fixes: 09ac4fcb3f25 ("drm/ttm: Implement vm_operations_struct.access v2") Signed-off-by: Tom St Denis <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-29drm/ttm: fix missing parameter change for ttm_bo_cleanup_refsRoger He1-1/+1
Missed in the patche: dc94777 drm/ttm: enable swapout for reserved BOs during allocation. don't unreserve the BO if it is not reserved by itself. Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-25Merge branch 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie3-50/+63
into drm-next A few more fixes for 4.16, nothing major. A few more fixes for 4.16. This is on top of the pull request from last week. Most notable change here is a fix to the link order for the now separate from amdgpu GPU scheduler to fix crashes when the modules are build into the kernel rather than as modules. * 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux: drm: fix gpu scheduler link order drm/amd/display: Demote error print to debug print when ATOM impl missing drm/amdgpu: Avoid leaking PM domain on driver unbind (v2) drm/amd/amdgpu: Add Polaris version check drm/amdgpu: Reenable manual GPU reset from sysfs drm/amdgpu: disable MMHUB power gating on raven drm/ttm: Don't unreserve swapped BOs that were previously reserved drm/ttm: Don't add swapped BOs to swap-LRU list drm/amdgpu: only check for ECC on Vega10 drm/amd/powerplay: Fix smu_table_entry.handle type drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count drm/radeon: fill in rb backend map on evergreen/ni. drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2) drm/ttm: only free pages rather than update global memory count together drm/amdgpu: fix CPU based VM updates drm/amdgpu: fix typo in amdgpu_vce_validate_bo drm/amdgpu: fix amdgpu_vm_pasid_fault_credit drm/ttm: check the return value of register_shrinker drm/radeon: fix sparse warning: Should it be static?
2018-01-18drm/ttm: Don't unreserve swapped BOs that were previously reservedFelix Kuehling1-2/+2
If ttm_bo_swapout doesn't own the lock, don't release it. Someone else probably depends on it still being locked. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-18drm/ttm: Don't add swapped BOs to swap-LRU listFelix Kuehling1-1/+2
A BO that's already swapped would be added back to the swap-LRU list for example if its validation failed under high memory pressure. This could later lead to swapping it out again and leaking previous swap storage. This commit adds a condition to prevent that from happening. v2: Check page_flags instead of swap_storage Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2018-01-18drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global countRoger He1-26/+29
add this for correctly updating global mem count in ttm_mem_zone. before that when ttm_mem_global_alloc_page fails, we would update all dma_page's global mem count in ttm_dma->pages_list. but actually here we should not update for the last dma_page. v2: only the update of last dma_page is not right v3: use lower bits of dma_page vaddr Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-18BackMerge tag 'v4.15-rc8' into drm-nextDave Airlie1-0/+2
Linux 4.15-rc8 Daniel requested this for so the intel CI won't fall over on drm-next so often.
2018-01-16drm/ttm: only free pages rather than update global memory count togetherRoger He1-2/+4
if ttm_get_pages or ttm_mem_global_alloc_page fail, should not update global memory count. Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[email protected]> Tested-by: Andrey Grodzovsky <[email protected]> Acked-by: Andrey Grodzovsky <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-16drm/ttm: check the return value of register_shrinkerRoger He2-19/+26
This fixes the build warning: "ignoring return value of 'register_shrinker', declared with attribute warn_unused_result [-Wunused-result]" Signed-off-by: Roger He <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-10drm/ttm: specify DMA_ATTR_NO_WARN for huge page poolsChristian König1-2/+6
Suppress warning messages when allocating huge pages fails since we can always fall back to normal pages. Signed-off-by: Christian König <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-10drm/ttm: remove ttm_bo_default_io_mem_pfnTan Xiaojun1-9/+2
No one will use this function except ttm_bo_io_mem_pfn() now, so move the calculation of ttm_bo_default_io_mem_pfn() into ttm_bo_io_mem_pfn() and do some cleanup. Signed-off-by: Tan Xiaojun <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2018-01-02drm/ttm: check the return value of kzallocXiongwei Song1-0/+2
In the function ttm_page_alloc_init, kzalloc call is made for variable _manager, we need to check its return value, it may return NULL. Signed-off-by: Xiongwei Song <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-12-28drm/ttm: enable swapout for reserved BOs during allocationRoger He2-8/+19
if the bo shares same reservation object then not lock it again at swapout time to make it possible to swap out. v2: refine the commmit message Reviewed-by: Thomas Hellström <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Chuming Zhou <[email protected]> Signed-off-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-12-28drm/ttm: add new function to check if bo is allowable to evict or swapoutRoger He1-10/+30
extract a function as ttm_bo_evict_swapout_allowable since eviction and swapout can share same logic. v2: modify commit message and add description in the code Reviewed-by: Thomas Hellström <[email protected]> Reviewed-by: Christian König <[email protected]> Reviewed-by: Chuming Zhou <[email protected]> Signed-off-by: Roger He <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.