kernel/linux.git/drivers/gpu/drm/ttm, branch v4.16.17

drm/ttm: Use GFP_TRANSHUGE_LIGHT for allocating huge pages

2018-05-16T08:12:31+00:00

commit da291320baec914f0bb4e65a9dccb86bd6c728f2 upstream. 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: stable@vger.kernel.org Reviewed-by: Christian König Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher Signed-off-by: Greg Kroah-Hartman

drm/ttm: Fix 'buf' pointer update in ttm_bo_vm_access_kmap() (v2)

2018-01-30T04:09:31+00:00

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: stable@vger.kernel.org Fixes: 09ac4fcb3f25 ("drm/ttm: Implement vm_operations_struct.access v2") Signed-off-by: Tom St Denis Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/ttm: fix missing parameter change for ttm_bo_cleanup_refs

2018-01-30T03:53:12+00:00

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 Reviewed-by: Christian König Signed-off-by: Alex Deucher

Merge branch 'drm-next-4.16' of git://people.freedesktop.org/~agd5f/linux into drm-next

2018-01-25T01:40:54+00:00

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?

drm/ttm: Don't unreserve swapped BOs that were previously reserved

2018-01-18T21:14:32+00:00

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 Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/ttm: Don't add swapped BOs to swap-LRU list

2018-01-18T21:14:03+00:00

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 Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org

drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count

2018-01-18T21:07:26+00:00

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 Reviewed-by: Christian König Signed-off-by: Alex Deucher

BackMerge tag 'v4.15-rc8' into drm-next

2018-01-17T23:32:15+00:00

Linux 4.15-rc8 Daniel requested this for so the intel CI won't fall over on drm-next so often.

drm/ttm: only free pages rather than update global memory count together

2018-01-16T20:35:27+00:00

if ttm_get_pages or ttm_mem_global_alloc_page fail, should not update global memory count. Signed-off-by: Roger He Reviewed-by: Christian König Tested-by: Andrey Grodzovsky Acked-by: Andrey Grodzovsky Signed-off-by: Alex Deucher

drm/ttm: check the return value of register_shrinker

2018-01-16T20:35:26+00:00

This fixes the build warning: "ignoring return value of 'register_shrinker', declared with attribute warn_unused_result [-Wunused-result]" Signed-off-by: Roger He Reviewed-by: Christian König Signed-off-by: Alex Deucher