aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
AgeCommit message (Collapse)AuthorFilesLines
2015-11-18drm/amdgpu: cleanup scheduler command submissionChristian König1-39/+24
Unify the two code path again, cause they do pretty much the same thing. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <davdi1.zhou@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
2015-11-16drm/amdgpu: fix handling order in scheduler CSChristian König1-5/+5
We need to clear parser.ibs and num_ibs before amd_sched_fence_create, otherwise the IB could be freed twice if fence creates fails. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2015-11-16drm/amdgpu: fix incorrect mutex usage v3Christian König1-19/+24
Before this patch the scheduler fence was created when we push the job into the queue, so we could only get the fence after pushing it. The mutex now was necessary to prevent the thread pushing the jobs to the hardware from running faster than the thread pushing the jobs into the queue. Otherwise the thread pushing jobs into the queue would have accessed possible freed up memory when it tries to get a reference to the fence. So what you get in the end is thread A: mutex_lock(&job->lock); ... Kick of thread B. ... mutex_unlock(&job->lock); And thread B: mutex_lock(&job->lock); .... mutex_unlock(&job->lock); kfree(job); I'm actually not sure if I'm still up to date on this, but this usage pattern used to be not allowed with mutexes. See here as well https://lwn.net/Articles/575460/. v2: remove unrelated changes, fix missing owner v3: rebased, add more commit message Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-11-16drm/amdgpu: add command submission workflow tracepointChunming Zhou1-1/+1
OGL needs these tracepoints to investigate performance issue. Change-Id: I5e58187d061253f7d665dfce8e4e163ba91d3e2b Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
2015-11-16drm/amdgpu: cleanup amdgpu_cs_parser handlingChristian König1-55/+33
No need any more to allocate that structure dynamically, just put it on the stack. This is a start to cleanup some of the scheduler fallouts. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-11-16drm/amdgpu: fix leaking the IBs on errorChristian König1-13/+12
Fixing a memory leak when the scheduler is enabled. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-11-05Merge branch 'drm-next-4.4' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie1-2/+4
into drm-next - Updated register headers for GFX 8.1 for Stoney - Add some new CZ revisions - minor pageflip optimizations - Fencing clean up - Warning fix - More fence cleanup - oops fix - Fiji fixes * 'drm-next-4.4' of git://people.freedesktop.org/~agd5f/linux: (29 commits) drm/amdgpu: group together common fence implementation drm/amdgpu: remove AMDGPU_FENCE_OWNER_MOVE drm/amdgpu: remove now unused fence functions drm/amdgpu: fix fence fallback check drm/amdgpu: fix stoping the scheduler timeout drm/amdgpu: cleanup on error in amdgpu_cs_ioctl() drm/amdgpu: update Fiji's Golden setting drm/amdgpu: update Fiji's rev id drm/amdgpu: extract common code in vi_common_early_init drm/amd/scheduler: don't oops on failure to load drm/amdgpu: don't oops on failure to load (v2) drm/amdgpu: don't VT switch on suspend drm/amdgpu: Make amdgpu_mn functions inline drm/amdgpu: remove amdgpu_fence_ref/unref drm/amdgpu: use common fence for sync drm/amdgpu: use the new fence_is_later drm/amdgpu: use common fences for VMID management v2 drm/amdgpu: move ring_from_fence to common code drm/amdgpu: switch to common fence_wait_any_timeout v2 drm/amdgpu: remove unneeded fence functions ...
2015-11-04drm/amdgpu: cleanup on error in amdgpu_cs_ioctl()Dan Carpenter1-2/+4
We recently changed the locking in this function and now there is a missing unlock on error. Also there are some other resources that we should probably release as well... Fixes: f48b2659f521 ('drm/amdgpu: fix the broken vm->mutex V2') Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2015-10-30Merge branch 'drm-next-4.4' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie1-11/+7
into drm-next More amdgpu and radeon stuff for drm-next. Stoney support is the big change. The rest is just bug fixes and code cleanups. The Stoney stuff is pretty low impact with respect to existing chips. * 'drm-next-4.4' of git://people.freedesktop.org/~agd5f/linux: drm/amdgpu: change VM size default to 64GB drm/amdgpu: add Stoney pci ids drm/amdgpu: update the core VI support for Stoney drm/amdgpu: add VCE support for Stoney (v2) drm/amdgpu: add UVD support for Stoney drm/amdgpu: add GFX support for Stoney (v2) drm/amdgpu: add SDMA support for Stoney (v2) drm/amdgpu: add DCE support for Stoney drm/amdgpu: Update SMC/DPM for Stoney drm/amdgpu: add GMC support for Stoney drm/amdgpu: add Stoney chip family drm/amdgpu: fix the broken vm->mutex V2 drm/amdgpu: remove the unnecessary parameter adev for amdgpu_fence_wait_any() drm/amdgpu: remove the exclusive lock drm/amdgpu: remove old lockup detection infrastructure drm: fix trivial typos drm/amdgpu/dce: simplify suspend/resume drm/amdgpu/gfx8: set TC_WB_ACTION_EN in RELEASE_MEM packet drm/radeon: Use rdev->gem.mutex to protect hyperz/cmask owners
2015-10-21drm/amdgpu: fix the broken vm->mutex V2Chunming Zhou1-3/+5
fix the vm->mutex and ww_mutex confilcts. vm->mutex is always token first, then ww_mutex. V2: remove unneccessary checking for pt bo. Change-Id: Iea56e183752c02831126d06d2f5b7a474a6e4743 Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
2015-10-21drm/amdgpu: remove the exclusive lockChristian König1-8/+2
Finally getting rid of it. Signed-off-by: Christian König <christian.koenig@amd.com>
2015-10-16Merge commit '06d1ee32a4d25356a710b49d5e95dbdd68bdf505' of ↵Dave Airlie1-4/+5
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into drm-next Backmerge the drm-fixes pull from Linus's tree into drm-next. This is to fix some conflicts and make future pulls cleaner
2015-10-14drm/amdgpu: add option to clear VM page tables after every submitChristian König1-1/+16
This makes it much easier to find when userspace misses to send some buffers. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-10-14drm/amdgpu: rework sdma structuresAlex Deucher1-3/+4
Rework the sdma structures in the driver to consolidate all of the sdma info into a single structure and allow for asics that may have different numbers of sdma instances. Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-10-07drm/amdgpu: fix 32-bit compiler warningArnd Bergmann1-3/+3
The new amdgpu driver passes a user space pointer in a 64-bit structure member, which is the correct way to do it, but it attempts to directly cast it to a __user pointer in the kernel, which causes a warning in three places: drm/amd/amdgpu/amdgpu_cs.c: In function 'amdgpu_cs_parser_init': drm/amd/amdgpu/amdgpu_cs.c:180:21: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] chunk_array_user = (uint64_t __user *)(cs->in.chunks); This changes all three to add an intermediate cast to 'unsigned long' as other drivers do. This avoids the warning and works correctly on both 32-bit and 64-bit architectures. Fixes: e60b344f6c0eff ("drm/amdgpu: optimize amdgpu_parser_init") Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-09-29drm/amdgpu: signedness bug in amdgpu_cs_parser_init()Dan Carpenter1-1/+2
The "i" variable should be signed or it leads to a crash in the error handling code. Fixes: 1d263474c441 ('drm/amdgpu: unwind properly in amdgpu_cs_parser_init()') Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-09-23drm/amdgpu: unwind properly in amdgpu_cs_parser_init()Dan Carpenter1-34/+51
The amdgpu_cs_parser_init() function doesn't clean up after itself but instead the caller uses a free everything function amdgpu_cs_parser_fini() on failure. This style of error handling is often buggy. In this example, we call "drm_free_large(parser->chunks[i].kdata);" when it is an unintialized pointer or when "parser->chunks" is NULL. I fixed this bug by adding unwind code so that it frees everything that it allocates. I also mode some other very minor changes: 1) Renamed "r" to "ret". 2) Moved the chunk_array allocation to the start of the function. 3) Removed some initializers which are no longer needed. Reviewed-by: Christian König <christian.koenig@amd.com> Reported-by: Ilja Van Sprundel <ivansprundel@ioactive.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2015-09-23drm/amdgpu: more scheduler cleanups v2Christian König1-1/+1
Embed the scheduler into the ring structure instead of allocating it. Use the ring name directly instead of the id. v2: rebased, whitespace cleanup Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by: Chunming Zhou<david1.zhou@amd.com>
2015-09-23drm/amdgpu: rename fence->scheduler to sched v2Christian König1-1/+1
Just to be consistent with the other members. v2: rename the ring member as well. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com> (v1) Reviewed-by: Chunming Zhou<david1.zhou@amd.com>
2015-09-23drm/amdgpu: refine the scheduler job type conversionJunwei Zhang1-1/+1
Use container_of rather than casting. Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: David Zhou <david1.zhou@amd.com> Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
2015-09-23drm/amdgpu: refine the job naming for amdgpu_job and amdgpu_sched_jobJunwei Zhang1-7/+7
Use consistent naming across functions. Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: David Zhou <david1.zhou@amd.com> Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
2015-09-23drm/amdgpu: validate duplicates in the CS as wellChristian König1-14/+20
This allows for multiple BOs to have the same reservation object. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-09-03drm/amdgpu: fix buffer placement under memory pressureChristian König1-1/+1
Some buffers (UVD/VM page tables) must be placed in VRAM, but the byte restriction for moving buffers didn't took this into account. Port of radeon commit 4b09556660bfe1b43d72ca858524c6baf2c6cb1d. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com>
2015-08-25drm/amdgpu: add owner for sched fenceChunming Zhou1-1/+1
Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-25drm/amdgpu: fix and cleanup amd_sched_entity_push_jobChristian König1-1/+1
Calling schedule() is probably the worse things we can do. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2015-08-25drm/amdgpu: remove the context from amdgpu_jobChristian König1-3/+1
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2015-08-25drm/amdgpu: fix user fences when scheduler is enabledChristian König1-0/+2
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2015-08-25drm/amdgpu: remove v_seq handling from the scheduler v2Christian König1-4/+2
Simply not used any more. Only keep 32bit atomic for fence sequence numbering. v2: trivial rebase Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v1) Reviewed-by: Jammy Zhou <Jammy.Zhou@amd.com> (v1) Reviewed-by: Chunming Zhou <david1.zhou@amd.com> (v1)
2015-08-20drm/amdgpu: fix CS error handling v2Christian König1-41/+26
Stop double freeing the the BO list by pulling the content of amdgpu_cs_parser_prepare_job() into the IOCTL function again. v2: better commit message Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> (v1) Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-08-20drm/amdgpu: fix zeroing all IB fields manually v2Christian König1-1/+1
The problem now is that we don't necessarily call amdgpu_ib_get() in some error paths and so work with uninitialized data. Better require that the memory is already zeroed. v2: better commit message Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> (v1) Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-08-20drm/amdgpu: don't need to use bo_list_clone any moreChunming Zhou1-21/+4
Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-20drm/amdgpu: some clean up for cs_ioctlChunming Zhou1-28/+1
Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-20drm/amdgpu: prepare job should be common code pathChunming Zhou1-6/+4
Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-20drm/amdgpu: abstract amdgpu_job for schedulerChunming Zhou1-46/+55
Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-17drm/amdgpu: wait on page directory changes. v2Bas Nieuwenhuizen1-0/+4
Pagetables can be moved and therefore the page directory update can be necessary for the current cs even if none of the the bo's are moved. In that scenario there is no fence between the sdma0 and gfx ring, so we add one. v2 (chk): rebased Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-08-17drm/amdgpu: move prepare work out of scheduler to cs_ioctlChunming Zhou1-13/+8
Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-17drm/amdgpu: drop bo_list_clone when no schedulermonk.liu1-9/+13
bo_list_clone() will take a lot of time when bo_list hold too much elements, like above 7000 Signed-off-by: Monk.Liu <monk.liu@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Jammy Zhou <jammy.zhou@amd.com>
2015-08-17drm/amdgpu: add reference for **fenceChunming Zhou1-0/+1
fix fence is released when pass to **fence sometimes. add reference for it. Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-17drm/amd: add scheduler fence implementation (v2)Chunming Zhou1-6/+15
scheduler fence is based on kernel fence framework. v2: squash in Christian's build fix Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-17drm/amdgpu: merge amd_sched_entity and amd_context_entity v2Christian König1-2/+2
Avoiding a couple of casts. v2: rename c_entity to entity as well Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2015-08-17drm/amdgpu: fix coding style in a couple of placesChristian König1-4/+2
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2015-08-17Revert "drm/amdgpu: return new seq_no for amd_sched_push_job"Chunming Zhou1-2/+3
This reverts commit d1d33da8eb86b8ca41dd9ed95738030df5267b95. Reviewed-by: Christian K?nig <christian.koenig@amd.com> Conflicts: drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
2015-08-17drm/amdgpu: fix bo list handling in CSChristian König1-3/+2
We didn't initialized the mutex in the cloned bo list resulting in nice warnings from lockdep. Also fixes error handling in this function. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2015-08-17drm/amdgpu: reorder the code to avoid forward declerationsChristian König1-33/+28
Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
2015-08-17drm/amdgpu: return new seq_no for amd_sched_push_jobJammy Zhou1-3/+2
It is clean to update last_queued_v_seq in the scheduler module Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-08-17drm/amdgpu: some code refinement v2Jammy Zhou1-13/+13
Fix the code alignment, etc. v2: rebase the code Signed-off-by: Jammy Zhou <Jammy.Zhou@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-08-17drm/amdgpu: use kernel fence for last_pt_updateChunming Zhou1-1/+1
Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com> Reviewed-by: Jammy Zhou <jammy.zhou@amd.com>
2015-08-17drm/amdgpu: stop using addr to check for BO move v3Christian König1-1/+10
It is theoretically possible that a swapped out BO gets the same GTT address, but different backing pages while being swapped in. Instead just use another VA state to note updated areas. Ported from not upstream yet radeon commit with the same name. v2: fix some bugs in the original implementation found in the radeon code. v3: squash in VCE/UVD fix Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
2015-08-17drm/amdgpu: fix seq in ctx_add_fenceChunming Zhou1-3/+2
if enabling scheduler, then the queued seq is assigned when pushing job before emitting job. Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
2015-08-17drm/amdgpu: add check for callbackChunming Zhou1-1/+2
it is possible that the callback isn't defined sometimes. Signed-off-by: Chunming Zhou <david1.zhou@amd.com> Reviewed-by: Christian K?nig <christian.koenig@amd.com>
Powered by cgit, Gruvboxed by Blaster4385.