summaryrefslogtreecommitdiff
path: root/include/drm/ttm
AgeCommit message (Collapse)AuthorFilesLines
2016-07-29drm/ttm: partial revert "cleanup ttm_tt_(unbind|destroy)" v3Christian König1-0/+9
We still need to unbind explicitly during a move. This partial reverts commit ff20caa0bcbfef9f7686f8d1868a3b990921afd6. v2: remove unnecessary check and unused variable v3: fix typo in commit message Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-07-26Backmerge tag 'v4.7' into drm-nextDave Airlie1-0/+14
Linux 4.7 As requested by Daniel Vetter as the conflicts were getting messy.
2016-07-07drm/ttm: add the infrastructure for pipelined evictionsChristian König1-0/+24
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>
2016-07-07drm/ttm: remove TTM_BO_PRIV_FLAG_MOVINGChristian König2-5/+2
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>
2016-07-07drm/ttm: remove no_gpu_wait param from ttm_bo_move_accel_cleanupChristian König1-3/+1
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>
2016-07-07drm/ttm: wait for BO idle in ttm_bo_move_memcpyChristian König1-1/+3
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>
2016-07-07drm/ttm: cleanup ttm_tt_(unbind|destroy)Christian König1-9/+0
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>
2016-07-01drm/ttm: Make ttm_bo_mem_compat availableSinclair Yeh1-0/+14
There are cases where it is desired to see if a proposed placement is compatible with a buffer object before calling ttm_bo_validate(). Signed-off-by: Sinclair Yeh <syeh@vmware.com> Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com> Cc: <stable@vger.kernel.org> --- This is the first of a 3-patch series to fix a black screen issue observed on Ubuntu 16.04 server.
2016-05-05drm/ttm: implement LRU add callbacks v2Christian König1-0/+9
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>
2016-05-05drm/ttm: add optional LRU removal callback v2Christian König1-0/+6
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>
2016-05-05drm/ttm: remove unused validation sequenceChristian König1-2/+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>
2016-05-05drm/ttm: remove lazy parameter from ttm_bo_waitChristian König1-1/+1
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>
2016-05-05drm/ttm: remove use_ticket parameter from ttm_bo_reserveChristian König1-9/+5
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>
2016-04-22Merge tag 'v4.6-rc3' into drm-nextDave Airlie1-1/+1
Backmerge 4.6-rc3 for i915. Linux 4.6-rc3
2016-04-05drm/ttm: use phys_addr_t for ttm_bus_placementAlex Deucher1-1/+1
Fixes ttm on platforms like PPC460 where the CPU is in 32-bit mode, but the physical addresses are >32 bits. Extracted from a patch by Hans Verkuil. Tested-by: Julian Margetson <runaway@candw.ms> Acked-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Christian König <christian.koenig@amd.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Julian Margetson <runaway@candw.ms> Cc: Hans Verkuil <hans.verkuil@cisco.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2016-03-30drm/ttm: Remove TTM_HAS_AGPDaniel Vetter1-2/+1
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
2016-01-13drm/ttm: add ttm_bo_move_to_lru_tail function v2Christian König1-0/+10
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>
2015-12-15drm/ttm: fix documentation of ttm_bo_reserveNicolai Hähnle1-2/+2
Previously, the comment was inconsistent. EDEADLK is what the ww_mutex mechanism really returns. Signed-off-by: Nicolai Hähnle <Nicolai.Haehnle@amd.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2015-03-05drm/ttm: device address space != CPU address spaceAlex Deucher2-2/+2
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>
2014-12-04drm/ttm: optionally move duplicates to a separate listChristian König1-1/+8
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>
2014-09-30drm/ttm: add reservation_object as argument to ttm_bo_initMaarten Lankhorst1-0/+2
This allows importing reservation objects from dma-bufs. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
2014-09-11drm/ttm: allow fence to be added as sharedChristian König1-0/+2
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>
2014-09-02drm/ttm: flip the switch, and convert to dma_fenceMaarten Lankhorst3-33/+5
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
2014-09-01drm/ttm: kill off some members to ttm_validate_bufferMaarten Lankhorst1-3/+0
This reorders the list to keep track of what buffers are reserved, so previous members are always unreserved. This gets rid of some bookkeeping that's no longer needed, while simplifying the code some. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
2014-09-01drm/ttm: add interruptible parameter to ttm_eu_reserve_buffersMaarten Lankhorst1-4/+5
It seems some drivers really want this as a parameter, like vmwgfx. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
2014-09-01drm/ttm: kill fence_lockMaarten Lankhorst2-7/+1
No users are left, kill it off! :D Conversion to the reservation api is next on the list, after that the functionality can be restored with rcu. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
2014-08-27drm/ttm: move fpfn and lpfn into each placement v2Christian König2-24/+19
This allows us to more fine grained specify where to place the buffer object. v2: rebased on drm-next, add bochs changes as well Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2014-08-09drm/ttm: expose CPU address of DMA-allocated pagesAlexandre Courbot1-0/+2
Pages allocated using the DMA API have a coherent memory mapping. Make this mapping visible to drivers so they can decide to use it instead of creating their own redundant one. Signed-off-by: Alexandre Courbot <acourbot@nvidia.com> Acked-by: David Airlie <airlied@linux.ie> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2014-07-08drm/ttm: fix handling of TTM_PL_FLAG_TOPDOWN v2Christian König1-0/+2
bo->mem.placement is not initialized when ttm_bo_man_get_node is called, so the flag had no effect at all. v2: change nouveau and vmwgfx as well Signed-off-by: Christian König <christian.koenig@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie <airlied@redhat.com>
2014-07-08drm/ttm: remove declaration of ttm_tt_cache_flushAlexandre Courbot1-12/+0
ttm_tt_cache_flush's implementation was removed in 2009 by commit c9c97b8c, but its declaration has been hiding in ttm_bo_driver.h since then. It has been surviving in the dark for too long now ; give it the mercy blow. Reviewed-by: Thierry Reding <treding@nvidia.com> Reviewed-by: David Herrmann <dh.herrmann@gmail.com> Signed-off-by: Alexandre Courbot <acourbot@nvidia.com> Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
2014-05-26drm/ttm: fix kerneldoc of ttm_bo_createAlexandre Courbot1-3/+2
The kerneldoc header of ttm_bo_create() was referring to another (nonexisting) function and had a few obsolete or incorrect arguments. Signed-off-by: Alexandre Courbot <acourbot@nvidia.com> Reviewed-by: David Herrmann <dh.herrmann@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2014-04-05Merge tag 'ttm-next-2014-04-04' of ↵Dave Airlie1-18/+29
git://people.freedesktop.org/~thomash/linux into drm-next Pull request of 2014-04-04 Currently only a single patch fixing up mixed use of the ttm_bo_reserve and ww_mutex APIs * tag 'ttm-next-2014-04-04' of git://people.freedesktop.org/~thomash/linux: drm/ttm: Hide the implementation details of reservation
2014-04-04drm/ttm: Hide the implementation details of reservationThomas Hellstrom1-18/+29
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Brian Paul <brianp@vmware.com>
2014-04-04drm: Add support for two-ended allocation, v3Lauri Kasanen1-0/+3
Clients like i915 need to segregate cache domains within the GTT which can lead to small amounts of fragmentation. By allocating the uncached buffers from the bottom and the cacheable buffers from the top, we can reduce the amount of wasted space and also optimize allocation of the mappable portion of the GTT to only those buffers that require CPU access through the GTT. For other drivers, allocating small bos from one end and large ones from the other helps improve the quality of fragmentation. Based on drm_mm work by Chris Wilson. v3: Changed to use a TTM placement flag v2: Updated kerneldoc Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Ben Widawsky <ben@bwidawsk.net> Cc: Christian König <deathsimple@vodafone.de> Signed-off-by: Lauri Kasanen <cand@gmx.com> Signed-off-by: David Airlie <airlied@redhat.com>
2014-03-28drm/ttm: Add a ttm_ref_object_exists functionThomas Hellstrom1-0/+4
A function to be used to check whether a caller has put a ref object (opened) a struct ttm_base_object Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Brian Paul <brianp@vmware.com>
2014-03-16drm: init TTM dev_mapping in ttm_bo_device_init()David Herrmann1-0/+2
With dev->anon_inode we have a global address_space ready for operation right from the beginning. Therefore, there is no need to do a delayed setup with TTM. Instead, set dev_mapping during initialization in ttm_bo_device_init() and remove any "if (dev_mapping)" conditions. Cc: Dave Airlie <airlied@redhat.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com> Cc: Alex Deucher <alexdeucher@gmail.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
2014-02-18drm/ttm: declare 'struct device' in ttm_page_alloc.hAlexandre Courbot1-0/+2
Declare 'struct device' explicitly in ttm_page_alloc.h as this file does not include any file declaring it. This removes the following warning: warning: 'struct device' declared inside parameter list Signed-off-by: Alexandre Courbot <acourbot@nvidia.com> Reviewed-by: Thierry Reding <treding@nvidia.com>
2014-01-14Merge tag 'vmwgfx-next-2014-01-13' of ↵Dave Airlie1-2/+16
git://people.freedesktop.org/~thomash/linux into drm-next Anyway, nothing big here, Three more code cleanup patches from Rashika Kheria, and one TTM/vmwgfx patch from me that tightens security around TTM objects enough for them to opened using prime objects from render nodes: Previously any client could access a shared buffer using the "name", also without actually opening it. Now a reference is required, and for render nodes such a reference is intended to only be obtainable using a prime fd. vmwgfx-next 2014-01-13 pull request * tag 'vmwgfx-next-2014-01-13' of git://people.freedesktop.org/~thomash/linux: drivers: gpu: Mark functions as static in vmwgfx_fence.c drivers: gpu: Mark functions as static in vmwgfx_buffer.c drivers: gpu: Mark functions as static in vmwgfx_kms.c drm/ttm: ttm object security fixes for render nodes
2014-01-08drm/ttm: ttm object security fixes for render nodesThomas Hellstrom1-2/+16
When a client looks up a ttm object, don't look it up through the device hash table, but rather from the file hash table. That makes sure that the client has indeed put a reference on the object, or in gem terms, has opened the object; either using prime or using the global "name". To avoid a performance loss, make sure the file hash table entries can be looked up from under an RCU lock, and as a consequence, replace the rwlock with a spinlock, since we never need to take it in read mode only anymore. Finally add a ttm object lookup function for the device hash table, that is intended to be used when we put a ref object on a base object or, in gem terms, when we open the object. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Brian Paul <brianp@vmware.com>
2014-01-08drm/ttm: Correctly set page mapping and -index membersThomas Hellstrom1-0/+9
Needed for some vm operations; most notably unmap_mapping_range() with even_cows = 0. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Brian Paul <brianp@vmware.com>
2013-11-21Merge branch 'ttm-fixes-3.13' of git://people.freedesktop.org/~thomash/linux ↵Dave Airlie1-1/+3
into drm-fixes The set_need_resched() removal fix and yet another fix in ttm_bo_move_memcpy(). * 'ttm-fixes-3.13' of git://people.freedesktop.org/~thomash/linux: drm/ttm: Remove set_need_resched from the ttm fault handler drm/ttm: Don't move non-existing data
2013-11-20drm/ttm: Remove set_need_resched from the ttm fault handlerThomas Hellstrom1-1/+3
Addresses "[BUG] completely bonkers use of set_need_resched + VM_FAULT_NOPAGE". In the first occurence it was used to try to be nice while releasing the mmap_sem and retrying the fault to work around a locking inversion. The second occurence was never used. There has been some discussion whether we should change the locking order to mmap_sem -> bo_reserve. This patch doesn't address that issue, and leaves that locking order undefined. The solution that we release the mmap_sem if tryreserve fails and wait for the buffer to become unreserved is something we want in any case, and follows how the core vm system waits for pages to be come unlocked while releasing the mmap_sem. The code also outlines what needs to be changed if we want to establish the locking order as mmap_sem -> bo::reserve. One slight issue that remains with this code is that the fault handler might be prone to starvation if another thread countinously reserves the buffer. IMO that usage pattern is highly unlikely. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
2013-11-18drm/ttm: Add a minimal prime implementation for ttm base objectsThomas Hellstrom1-2/+59
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
2013-11-18drm/ttm: Allow execbuf util reserves without ticketThomas Hellstrom1-1/+2
If no reservation ticket is given to the execbuf reservation utilities, try reservation with non-blocking semantics. This is intended for eviction paths that use the execbuf reservation utilities for convenience rather than for deadlock avoidance. Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
2013-11-06drm/ttm: Enable the dma page pool also for intel IOMMUsThomas Hellstrom1-1/+10
Used by the vmwgfx driver Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com> Reviewed-by: Jakob Bornecrantz <jakob@vmware.com> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-07-25drm/ttm: convert to unified vma offset managerDavid Herrmann2-17/+8
Use the new vma-manager infrastructure. This doesn't change any implementation details as the vma-offset-manager is nearly copied 1-to-1 from TTM. The vm_lock is moved into the offset manager so we can drop it from TTM. During lookup, we use the vma locking helpers to take a reference to the found object. In all other scenarios, locking stays the same as before. We always guarantee that drm_vma_offset_remove() is called only during destruction. Hence, helpers like drm_vma_node_offset_addr() are always safe as long as the node has a valid offset. This also drops the addr_space_offset member as it is a copy of vm_start in vma_node objects. Use the accessor functions instead. v4: - remove vm_lock - use drm_vma_offset_lock_lookup() to protect lookup (instead of vm_lock) Cc: Dave Airlie <airlied@redhat.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Maarten Lankhorst <maarten.lankhorst@canonical.com> Cc: Martin Peres <martin.peres@labri.fr> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Signed-off-by: David Herrmann <dh.herrmann@gmail.com> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Dave Airlie <airlied@gmail.com>
2013-06-28drm/ttm: get rid of ttm_bo_is_reservedMaarten Lankhorst1-14/+0
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2013-06-28drm/ttm: inline ttm_bo_reserve and related callsMaarten Lankhorst1-70/+105
Makes lockdep a lot more useful. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2013-06-28drm/ttm: convert to the reservation apiMaarten Lankhorst2-20/+6
Now that the code is compatible in semantics, flip the switch. Use ww_mutex instead of the homegrown implementation. ww_mutex uses -EDEADLK to signal that the caller has to back off, and -EALREADY to indicate this buffer is already held by the caller. ttm used -EAGAIN and -EDEADLK for those, respectively. So some changes were needed to handle this correctly. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2013-06-28drm/ttm: make ttm reservation calls behave like reservation callsMaarten Lankhorst3-13/+34
This commit converts the source of the val_seq counter to the ww_mutex api. The reservation objects are converted later, because there is still a lockdep splat in nouveau that has to resolved first. Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Dave Airlie <airlied@redhat.com>