summaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/ttm (follow)
Commit message (Collapse)AuthorAgeFilesLines
* drm/ttm: fix stupid parameter inversion in the pipeline codeChristian König2016-07-071-1/+1
| | | | | | | | We want to keep the newest fence, not the oldest one. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: wait for eviction in ttm_bo_force_list_cleanChristian König2016-07-071-0/+18
| | | | | | | | Now that we can pipeline evictions we need to wait for them to finish when we cleanup a memory domain. Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: add the infrastructure for pipelined evictionsChristian König2016-07-072-5/+136
| | | | | | | | | Free up the memory immediately, remember the last eviction for each domain and make new allocations depend on the last eviction to be completed. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: simplify ttm_bo_waitChristian König2016-07-071-33/+4
| | | | | | | | As far as I can see no need for a custom implementation any more. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: remove TTM_BO_PRIV_FLAG_MOVINGChristian König2016-07-073-10/+17
| | | | | | | | | | | Instead of using the flag just remember the fence of the last move operation. This avoids waiting for command submissions pipelined after the move, but before accessing the BO with the CPU again. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: remove no_gpu_wait param from ttm_bo_move_accel_cleanupChristian König2016-07-071-1/+0
| | | | | | | | | It isn't used and not waiting for the GPU after scheduling a move is actually quite dangerous. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: wait for BO idle after the move in ttm_bo_swapoutChristian König2016-07-071-6/+9
| | | | | | | | Final part to avoid pre move waits. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: drop waiting for idle in ttm_bo_evict.Christian König2016-07-071-10/+1
| | | | | | | | That is unnecessary now. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: drop wait for idle in ttm_bo_move_bufferChristian König2016-07-071-14/+0
| | | | | | | | That is unnecessary now. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: wait for BO idle in ttm_bo_move_memcpyChristian König2016-07-072-2/+8
| | | | | | | | When we want to pipeline accelerated moves we need to wait in the fallback path. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: remove NULL checks when calling ttm_tt_destroyChristian König2016-07-073-11/+7
| | | | | | | | The function is a no-op with a NULL pointer. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: cleanup ttm_tt_(unbind|destroy)Christian König2016-07-073-17/+5
| | | | | | | | ttm_tt_destroy should be the only one unbinding the object. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* Merge tag 'v4.6-rc7' into drm-nextDave Airlie2016-05-091-13/+4
|\ | | | | | | | | Merge this back as we've built up a fair few conflicts, and I have some newer trees to pull in.
| * drm/ttm: fix kref count mess in ttm_bo_move_to_lru_tailFlora Cui2016-04-271-13/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes the following scenario: 1. Page table bo allocated in vram and linked to man->lru. tbo->list_kref.refcount=2 2. Page table bo is swapped out and removed from man->lru. tbo->list_kref.refcount=1 3. Command submission from userspace. Page table bo is moved to vram. ttm_bo_move_to_lru_tail() link it to man->lru and don't increase the kref count. Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Flora Cui <Flora.Cui@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
* | drm/ttm: implement LRU add callbacks v2Christian König2016-05-051-9/+20
| | | | | | | | | | | | | | | | | | | | | | This allows fine grained control for the driver where to add a BO into the LRU. v2: fix typo in comment Reviewed-by: Sinclair Yeh <syeh@vmware.com> 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>
* | drm/ttm: add optional LRU removal callback v2Christian König2016-05-051-5/+7
| | | | | | | | | | | | | | | | | | | | | | Useful for driver specific LRU handling. v2: fix typo in comment Reviewed-by: Sinclair Yeh <syeh@vmware.com> 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>
* | drm/ttm: remove unused validation sequenceChristian König2016-05-051-1/+0
| | | | | | | | | | | | | | | | | | Not used any more. Reviewed-by: Sinclair Yeh <syeh@vmware.com> 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>
* | drm/ttm: remove lazy parameter from ttm_bo_waitChristian König2016-05-053-12/+12
| | | | | | | | | | | | | | | | | | Not used any more. Reviewed-by: Sinclair Yeh <syeh@vmware.com> 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>
* | drm/ttm: remove use_ticket parameter from ttm_bo_reserveChristian König2016-05-053-12/+10
| | | | | | | | | | | | | | | | | | Not used any more. Reviewed-by: Sinclair Yeh <syeh@vmware.com> 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>
* | drm/ttm: don't wait for BO on initial allocationChristian König2016-05-051-6/+12
| | | | | | | | | | | | | | | | | | | | When we use an extern reservation object that otherwise waits for every fence registered with it. Reviewed-by: Sinclair Yeh <syeh@vmware.com> 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>
* | drm/ttm: Fix TTM BO accountingFelix Kuehling2016-05-051-3/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | TTM BO accounting is out of sync with how memory is really allocated in ttm[_dma]_tt_alloc_page_directory. This resulted in excessive estimated overhead with many small allocations. ttm_dma_tt_alloc_page_directory makes a single allocation for three arrays: pages, DMA and CPU addresses. It uses drm_calloc_large, which uses kmalloc internally for allocations smaller than PAGE_SIZE. ttm_round_pot should be a good approximation of its memory usage both above and below PAGE_SIZE. Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Monk Liu <monk.liu@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* | Merge tag 'v4.6-rc3' into drm-nextDave Airlie2016-04-221-2/+2
|\| | | | | | | | | | | Backmerge 4.6-rc3 for i915. Linux 4.6-rc3
| * mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macrosKirill A. Shutemov2016-04-041-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | drm/ttm: Remove TTM_HAS_AGPDaniel Vetter2016-03-304-12/+10
|/ | | | | | | | | | | | | | | | | | | | | It tries to do fancy things with excluding agp support if ttm is built-in, but agp isn't. Instead just express this depency like drm does and use CONFIG_AGP everywhere. Also use the neat Makefile magic to make the entire ttm_agp_backend file optional. v2: Use IS_ENABLED(CONFIG_AGP) as suggested by Ville v3: Review from Emil. v4: Actually get it right as spotted by 0-day. Cc: Emil Velikov <emil.l.velikov@gmail.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/1459337046-25882-1-git-send-email-daniel.vetter@ffwll.ch
* Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linuxLinus Torvalds2016-01-171-2/+29
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull drm updates from Dave Airlie: "This is the main drm pull request for 4.5. I don't think I've missed anything too major, I'm mostly back at work now but I'll probably get some sleep in 5 years time. Summary: New drivers: - etnaviv: GPU driver for the 3D core on the Vivante core used in numerous ARM boards. Highlights: Core: - Atomic suspend/resume helpers - Move the headers to using userspace friendlier types. - Documentation updates - Lots of struct_mutex removal. - Bunch of DP MST fixes from AMD. Panel: - More DSI helpers - Support for some new basic panels i915: - Basic Kabylake support - DP link training and detect code refactoring - fbc/psr fixes - FIFO underrun fixes - SDE interrupt handling fixes - dma-buf/fence support in pageflip path. - GPU side for MST audio support radeon/amdgpu: - Drop UMS support - GPUVM/Scheduler optimisations - Initial Powerplay support for Tonga/Fiji/CZ/ST - ACP audio prerequisites nouveau: - GK20a instmem improvements - PCIE link speed change support msm: - DSI support for msm8960/apq8064 tegra: - Host1X support for Tegra210 SoC vc4: - 3D acceleration support armada: - Get rid of struct mutex tda998x: - Atomic modesetting support - TMDS clock limitations omapdrm: - Atomic modesetting support - improved TILER performance rockchip: - RK3036 VOP support - Atomic modesetting support - Synopsys DW MIPI DSI support exynos: - Runtime PM support - of_graph binding for DP panels - Cleanup of IPP code - Configurable plane support - Kernel panic fixes at release time" * 'drm-next' of git://people.freedesktop.org/~airlied/linux: (711 commits) drm/fb_cma_helper: Remove implicit call to disable_unused_functions drm/amdgpu: add missing irq.h include drm/vmwgfx: Fix a width / pitch mismatch on framebuffer updates drm/vmwgfx: Fix an incorrect lock check drm: nouveau: fix nouveau_debugfs_init prototype drm/nouveau/pci: fix check in nvkm_pcie_set_link drm/amdgpu: validate duplicates first drm/amdgpu: move VM page tables to the LRU end on CS v2 drm/ttm: add ttm_bo_move_to_lru_tail function v2 drm/ttm: fix adding foreign BOs to the swap LRU drm/ttm: fix adding foreign BOs to the LRU during init v2 drm/radeon: use kobj_to_dev() drm/amdgpu: use kobj_to_dev() drm/amdgpu/cz: force vce clocks when sclks are forced drm/amdgpu/cz: force uvd clocks when sclks are forced drm/amdgpu/cz: add code to enable forcing VCE clocks drm/amdgpu/cz: add code to enable forcing UVD clocks drm/amdgpu: fix lost sync_to if scheduler is enabled. drm/amd/powerplay: fix static checker warning for return meaningless value. drm/sysfs: use kobj_to_dev() ...
| * drm/ttm: add ttm_bo_move_to_lru_tail function v2Christian König2016-01-131-0/+21
| | | | | | | | | | | | | | | | | | | | | | This allows the drivers to move a BO to the end of the LRU without removing and adding it again. v2: Make it more robust, handle pinned and swapable BOs as well. Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/ttm: fix adding foreign BOs to the swap LRUChristian König2016-01-131-1/+1
| | | | | | | | | | | | | | | | It doesn't make any sense to try to swap out imported BOs. Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
| * drm/ttm: fix adding foreign BOs to the LRU during init v2Christian König2016-01-131-1/+7
| | | | | | | | | | | | | | | | | | | | | | | | If we import a BO with an external reservation object we don't reserve/unreserve it. So we never add it to the LRU causing a possible denial of service. v2: fix typo in commit message Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* | mm, dax, gpu: convert vm_insert_mixed to pfn_tDan Williams2016-01-161-1/+3
|/ | | | | | | | | | | | | | | Convert the raw unsigned long 'pfn' argument to pfn_t for the purpose of evaluating the PFN_MAP and PFN_DEV flags. When both are set it triggers _PAGE_DEVMAP to be set in the resulting pte. There are no functional changes to the gpu drivers as a result of this conversion. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave@sr71.net> Cc: David Airlie <airlied@linux.ie> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* drm/ttm: Fixed a read/write lock imbalanceThomas Hellstrom2015-11-261-1/+1
| | | | | | | | | | | | In ttm_write_lock(), the uninterruptible path should call __ttm_write_lock() not __ttm_read_lock(). This fixes a vmwgfx hang on F23 start up. syeh: Extracted this from one of Thomas' internal patches. Cc: <stable@vger.kernel.org> Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
* drm/ttm: Fix memory space allocation v2Thomas Hellstrom2015-09-151-12/+16
| | | | | | | | | | | | | | | | | | In the event that TTM doesn't find a compatible memory type for the driver's first placement choice (placement without eviction), TTM returns -EINVAL without trying the driver's second choice. This causes problems on vmwgfx when VRAM is disabled before first modeset and during VT switches when fbdev is not enabled. Fix this by also trying the driver's second choice before returning -EINVAL. v2: Also check that man->use_type is true for the driver's second choice. Fixes a bug where disallowed memory types could be used. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Brian Paul <brianp@vmware.com> Reviewed-by: Sinclair Yeh <syeh@vmware.com>
* Merge tag 'v4.2-rc7' into drm-nextDave Airlie2015-08-171-1/+2
|\ | | | | | | | | | | Linux 4.2-rc7 Backmerge master for i915 fixes
| * drm/ttm: recognize ARM64 arch in ioprot handlerAlexandre Courbot2015-07-241-1/+2
| | | | | | | | | | | | | | | | Return proper pgprot for ARM64. This is required for objects like Nouveau fences to be mapped with expected coherency. Signed-off-by: Alexandre Courbot <acourbot@nvidia.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* | drivers: gpu: Drop unlikely before IS_ERR(_OR_NULL)Viresh Kumar2015-08-061-2/+2
|/ | | | | | | | | IS_ERR(_OR_NULL) already contain an 'unlikely' compiler flag and there is no need to do that again from its callers. Drop it. Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Reviewed-by: Sinclair Yeh <syeh@vmware.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
* drm/ttm: improve uncached page deallocation.Jérôme Glisse2015-07-171-6/+6
| | | | | | | | | | | | | | Calls to set_memory_wb() incure heavy TLB flush and IPI cost. To minimize those wait until pool grow beyond batch size before draining the pool. Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Mario Kleiner <mario.kleiner.de@gmail.com> Reviewed-and-Tested-by: Michel Dänzer <michel@daenzer.net> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* drm/ttm: fix uncached page deallocation to properly fill page pool v3.Jérôme Glisse2015-07-171-1/+0
| | | | | | | | | | | | | | | | | | | | | | Current code never allowed the page pool to actualy fill in anyway. This fix it, so that we only start freeing page from the pool when we go over the pool size. Changed since v1: - Move the page batching optimization to its separate patch. Changed since v2: - Do not remove code part of the batching optimization with this patch. - Better commit message. Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Mario Kleiner <mario.kleiner.de@gmail.com> Reviewed-and-Tested-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* drm/ttm: dma: Don't crash on memory in the vmalloc rangeAlexandre Courbot2015-06-021-3/+6
| | | | | | | | | | | dma_alloc_coherent() can return memory in the vmalloc range. virt_to_page() cannot handle such addresses and crashes. This patch detects such cases and obtains the struct page * using vmalloc_to_page() instead. Signed-off-by: Alexandre Courbot <acourbot@nvidia.com> Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* dma-buf: cleanup dma_buf_export() to make it easily extensibleSumit Semwal2015-04-211-2/+7
| | | | | | | | | | | | | | | | | At present, dma_buf_export() takes a series of parameters, which makes it difficult to add any new parameters for exporters, if required. Make it simpler by moving all these parameters into a struct, and pass the struct * as parameter to dma_buf_export(). While at it, unite dma_buf_export_named() with dma_buf_export(), and change all callers accordingly. Reviewed-by: Maarten Lankhorst <maarten.lankhorst@canonical.com> Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org> Acked-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com> Acked-by: Dave Airlie <airlied@redhat.com> Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
* drm/ttm: device address space != CPU address spaceAlex Deucher2015-03-051-1/+1
| | | | | | | | | | | | | | | | | | | | | We need to store device offsets in 64 bit as the device address space may be larger than the CPU's. Fixes GPU init failures on radeons with 4GB or more of vram on 32 bit kernels. We put vram at the start of the GPU's address space so the gart aperture starts at 4 GB causing all GPU addresses in the gart aperture to get truncated. bug: https://bugs.freedesktop.org/show_bug.cgi?id=89072 [airlied: fix warning on nouveau build] Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: thellstrom@vmware.com Acked-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
* drm/ttm: optionally move duplicates to a separate listChristian König2014-12-041-1/+9
| | | | | | | | | | This patch adds an optional list_head parameter to ttm_eu_reserve_buffers. If specified duplicates in the execbuf list are no longer reported as errors, but moved to this list instead. Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: Avoid memory allocation from shrinker functions.Tetsuo Handa2014-11-202-21/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Andrew Morton wrote: > On Wed, 12 Nov 2014 13:08:55 +0900 Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> wrote: > > > Andrew Morton wrote: > > > Poor ttm guys - this is a bit of a trap we set for them. > > > > Commit a91576d7916f6cce ("drm/ttm: Pass GFP flags in order to avoid deadlock.") > > changed to use sc->gfp_mask rather than GFP_KERNEL. > > > > - pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), > > - GFP_KERNEL); > > + pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp); > > > > But this bug is caused by sc->gfp_mask containing some flags which are not > > in GFP_KERNEL, right? Then, I think > > > > - pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp); > > + pages_to_free = kmalloc(npages_to_free * sizeof(struct page *), gfp & GFP_KERNEL); > > > > would hide this bug. > > > > But I think we should use GFP_ATOMIC (or drop __GFP_WAIT flag) > > Well no - ttm_page_pool_free() should stop calling kmalloc altogether. > Just do > > struct page *pages_to_free[16]; > > and rework the code to free 16 pages at a time. Easy. Well, ttm code wants to process 512 pages at a time for performance. Memory footprint increased by 512 * sizeof(struct page *) buffer is only 4096 bytes. What about using static buffer like below? ---------- >From d3cb5393c9c8099d6b37e769f78c31af1541fe8c Mon Sep 17 00:00:00 2001 From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Date: Thu, 13 Nov 2014 22:21:54 +0900 Subject: [PATCH] drm/ttm: Avoid memory allocation from shrinker functions. Commit a91576d7916f6cce ("drm/ttm: Pass GFP flags in order to avoid deadlock.") caused BUG_ON() due to sc->gfp_mask containing flags which are not in GFP_KERNEL. https://bugzilla.kernel.org/show_bug.cgi?id=87891 Changing from sc->gfp_mask to (sc->gfp_mask & GFP_KERNEL) would avoid the BUG_ON(), but avoiding memory allocation from shrinker function is better and reliable fix. Shrinker function is already serialized by global lock, and clean up function is called after shrinker function is unregistered. Thus, we can use static buffer when called from shrinker function and clean up function. Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: stable <stable@kernel.org> [2.6.35+] Signed-off-by: Dave Airlie <airlied@redhat.com>
* drm/ttm: Use only DRM_MM_SEARCH_BELOW for TTM_PL_FLAG_TOPDOWNMichel Dänzer2014-11-121-1/+1
| | | | | | | | | | | | | | DRM_MM_SEARCH_BEST gets the smallest hole which can fit the BO. That seems against the idea of TTM_PL_FLAG_TOPDOWN: * The smallest hole may be in the overall bottom of the area * If the hole isn't much larger than the BO, it doesn't make much difference whether the BO is placed at the bottom or at the top of the hole Reviewed-by: Lauri Kasanen <cand@gmx.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: Add DRM_MM_SEARCH_BELOW for TTM_PL_FLAG_TOPDOWNMichel Dänzer2014-11-121-3/+5
| | | | | | | | | If the BO should be placed at the top of the area, we should start looking for holes from the top. Reviewed-by: Lauri Kasanen <cand@gmx.com> Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: Don't evict BOs outside of the requested placement rangeMichel Dänzer2014-10-171-3/+17
| | | | | | | | | | | | | | | | | | | | The radeon driver uses placement range restrictions for several reasons, in particular to make sure BOs in VRAM can be accessed by the CPU, e.g. during a page fault. Without this change, TTM could evict other BOs while trying to satisfy the requested placement, even if the evicted BOs were outside of the requested placement range. Doing so didn't free up any space in the requested placement range, so the (potentially high) eviction cost was incurred for no benefit. Nominating for stable because radeon driver changes in 3.17 made this much more noticeable than before. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=84662 Cc: stable@vger.kernel.org Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: Don't skip fpfn check if lpfn is 0 in ttm_bo_mem_compatMichel Dänzer2014-10-171-4/+4
| | | | | | 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>
* drm/ttm: add reservation_object as argument to ttm_bo_initMaarten Lankhorst2014-09-301-6/+18
| | | | | | This allows importing reservation objects from dma-bufs. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
* drm/ttm: Clean usage of ttm_io_prot() with TTM_PL_FLAG_CACHEDBenjamin Herrenschmidt2014-09-232-16/+9
| | | | | | | | | | | | | | Today, most callers of ttm_io_prot() check TTM_PL_FLAG_CACHED before calling it since on some archs it will unconditionally create non-cached mappings. But not all callers do which is incorrect as far as I can tell. Instead, move that check inside ttm_io_port() itself for all archs and make powerpc use the same implementation as ia64 and arm Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Dave Airlie <airlied@redhat.com>
* drm/ttm: make sure format string cannot leak inKees Cook2014-09-171-1/+2
| | | | | | | | | | While zone->name is currently hard coded, the call to kobject_init_and_add() should follow the more defensive argument list usage (as already done in other places in ttm_memory.c) where "%s" is used instead of directly passing in a variable as a format string. Signed-off-by: Kees Cook <keescook@chromium.org> Signed-off-by: Dave Airlie <airlied@redhat.com>
* drm/ttm: allow fence to be added as sharedChristian König2014-09-111-3/+15
| | | | | | | | This patch adds a new flag to the ttm_validate_buffer list to add the fence as shared to the reservation object. Signed-off-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
* drm/ttm: use rcu in core ttmMaarten Lankhorst2014-09-021-63/+13
| | | | Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-04 05:54:13 +0100