summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/nouveau/nouveau_fence.c
AgeCommit message (Collapse)AuthorFilesLines
2012-10-03drm/nouveau: port all engines to new engine module formatBen Skeggs1-16/+7
This is a HUGE commit, but it's not nearly as bad as it looks - any problems can be isolated to a particular chipset and engine combination. It was simply too difficult to port each one at a time, the compat layers are *already* ridiculous. Most of the changes here are simply to the glue, the process for each of the engine modules was to start with a standard skeleton and copy+paste the old code into the appropriate places, fixing up variable names etc as needed. v2: Marcin Slusarz <marcin.slusarz@gmail.com> - fix find/replace bug in license header v3: Ben Skeggs <bskeggs@redhat.com> - bump indirect pushbuf size to 8KiB, 4KiB barely enough for userspace and left no space for kernel's requirements during GEM pushbuf submission. - fix duplicate assignments noticed by clang v4: Marcin Slusarz <marcin.slusarz@gmail.com> - add sparse annotations to nv04_fifo_pause/nv04_fifo_start - use ioread32_native/iowrite32_native for fifo control registers v5: Ben Skeggs <bskeggs@redhat.com> - rebase on v3.6-rc4, modified to keep copy engine fix intact - nv10/fence: unmap fence bo before destroying - fixed fermi regression when using nvidia gr fuc - fixed typo in supported dma_mask checking Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-10-03drm/nouveau/pageflip: kick flip handling out of engsw and into fenceBen Skeggs1-0/+1
This is all very much a policy thing, and hence will not belong in SW after the rework. engsw now only handles receiving the event to say "can flip now" and makes a callback to perform the actual work. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-10-03drm/nouveau/fence: un-port from nouveau_exec_engine interfacesBen Skeggs1-6/+9
Still the same code, but not an "engine" anymore. The fence code is more of a policy decision rather than exposing mechanisms, so it's not appropriate to port it to the new engine subsystem. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-10-03drm/nouveau: restructure source tree, split core from drm implementationBen Skeggs1-1/+1
Future work will be headed in the way of separating the policy supplied by the nouveau drm module from the mechanisms provided by the driver core. There will be a couple of major classes (subdev, engine) of driver modules that have clearly defined tasks, and the further directory structure change is to reflect this. No code changes here whatsoever, aside from fixing up a couple of include file pathnames. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-05-24drm/nouveau/fence: fix a race where fence->channel can disappearBen Skeggs1-5/+9
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-05-24drm/nouveau/fence: convert to exec engine, and improve channel syncBen Skeggs1-412/+62
Now have a somewhat simpler semaphore sync implementation for nv17:nv84, and a switched to using semaphores as fences on nv84+ and making use of the hardware's >= acquire operation. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-05-24drm/nouveau/fence: minor api changes for an upcoming reworkBen Skeggs1-130/+85
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-05-24drm/nouveau/fence: make ttm interfaces wrap ours, not the other way aroundBen Skeggs1-23/+13
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-05-24drm/nouveau: create real execution engine for software object classBen Skeggs1-5/+1
Just a cleanup more or less, and to remove the need for special handling of software objects. This removes a heap of documentation on dma/graph object formats. The info is very out of date with our current understanding, and is far better documented in rnndb in envytools git. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-05-24drm/nouveau: base fence timeout on time of emissionMarcin Slusarz1-1/+4
Wait loop can be interrupted by signal, so if signals are raised periodically (e.g. SIGALRM) this loop may never finish. Use emission time as a base for fence timeout. Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-05-24drm/nouveau: use the same packet header macros as userspaceBen Skeggs1-13/+13
Cosmetic cleanup only. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-05-23nouveau: add PRIME supportDave Airlie1-1/+1
This adds prime->fd and fd->prime support to nouveau, it passes the SG object to TTM, and then populates the GART entries using it. v2: add stubbed kmap + use new function to fill out pages array for faulting + add reimport test. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-03-22drm/nouveau: move fence sequence check to start of loopBen Skeggs1-6/+5
I want to be able to use REF_CNT from other places in the kernel without pushing a fence object onto the list of emitted fences. The current code makes an assumption that every time the acked sequence is bumped that there's at least one fence on the list that'll be signalled. This will no longer be true in the near future. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-03-22drm/nouveau: remove subchannel names from places where it doesn't matterBen Skeggs1-12/+12
These are FIFO methods, it doesn't matter what subchannel is being used. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-11-10drm/nouveau: initialize chan->fence.lock before useMarcin Slusarz1-2/+0
Fence lock needs to be initialized before any call to nouveau_channel_put because it calls nouveau_channel_idle->nouveau_fence_update which uses fence lock. BUG: spinlock bad magic on CPU#0, test/24134 lock: ffff88019f90dba8, .magic: 00000000, .owner: <none>/-1, .owner_cpu: 0 Pid: 24134, comm: test Not tainted 3.0.0-nv+ #800 Call Trace: spin_bug+0x9c/0xa3 do_raw_spin_lock+0x29/0x13c _raw_spin_lock+0x1e/0x22 nouveau_fence_update+0x2d/0xf1 nouveau_channel_idle+0x22/0xa0 nouveau_channel_put_unlocked+0x84/0x1bd nouveau_channel_put+0x20/0x24 nouveau_channel_alloc+0x4ec/0x585 nouveau_ioctl_fifo_alloc+0x50/0x130 drm_ioctl+0x289/0x361 do_vfs_ioctl+0x4dd/0x52c sys_ioctl+0x42/0x65 system_call_fastpath+0x16/0x1b It's easily triggerable from userspace. Additionally remove double initialization of chan->fence.pending. Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com> Cc: stable@kernel.org Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20drm/nouveau: workaround semaphore hw bug causing unnecessary interruptsBen Skeggs1-1/+1
The HW will only accept the DMA_FROM_MEMORY class for DMA_SEMAPHORE without asking the driver to intervene. It appears that semaphores will work correctly even without DMA_IN_MEMORY, so lets avoid the large amount of interrupts generated by x-chan sync. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-09drm/nouveau: fix oops on pre-semaphore hardwareBen Skeggs1-1/+2
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-23drm/nouveau: remove 'chan' argument from nouveau_bo_newBen Skeggs1-1/+1
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-23drm/nv84-nvc0: explicitly map semaphore buffer into channel vmBen Skeggs1-16/+13
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-06-18drm/nouveau: fix assumption that semaphore dmaobj is valid in x-chan syncBen Skeggs1-34/+25
The DDX modifies DMA_SEMAPHORE on nv50 in order to implement sync-to-vblank, things will go very wrong for cross-channel sync after this. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-03-14drm/nouveau: fix __nouveau_fence_wait performanceMarcin Slusarz1-3/+12
Commit 21e86c1c8a844bf978f8fc431a59c9f5a578812d ("drm/nouveau: remove cpu_writers lock") turned on lazy waits. Unfortunately __nouveau_fence_wait was not optimized for this case and on HZ=100 kernel wasted up to 10 ms per call. Depending on application, it led to 10-30% FPS regression. Fix it. Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com> Signed-off-by: Francisco Jerez <currojerez@riseup.net>
2011-02-24drm/nouveau: remove no_vm/mappable flags from nouveau_boBen Skeggs1-1/+1
'mappable' isn't really used at all, nor is it necessary anymore as the bo code is capable of moving buffers to mappable vram as required. 'no_vm' isn't necessary anymore either, any places that don't want to be mapped into a GPU address space should allocate the VRAM directly instead. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-24drm/nv50: drop explicit yields in favour of smaller PFIFO timesliceBen Skeggs1-46/+6
This gives a small, but noticeable performance gain at lower performance levels, and unchanged at the higher ones. With this commit, we're now using the same timeslice size as the NVIDIA binary driver currently does, and dropping an unknown bit that NVIDIA no longer appear to set. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-24drm/nv84: use vm offsets for semaphoresBen Skeggs1-5/+17
We may well be making more use of semaphores in the future, having the entire VM available makes requiring DMA objects for each and every semaphore block unnecessary. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-24drm/nv50: 0x50 needs semaphore yields tooBen Skeggs1-4/+17
Evil, evil chipset. Worst of both worlds. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-24drm/nvc0: implement semaphores for inter-channel syncBen Skeggs1-12/+40
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-02-24drm/nv84: switch to new-style semaphoresBen Skeggs1-39/+80
These are the same semaphores nvc0 will use, and they potentially allow us to do much cooler things than our current inter-channel sync impl. Lets switch to them where possible now for some testing. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-30drm/nvc0: reserve only subc 0 for kernel useBen Skeggs1-1/+1
Current 3D driver expects this behaviour. While this could be changed, there's no compelling reason to reserve more than one subchannel for the DRM. If we ever need to use an object other then M2MF, we can just re-bind subchannel 0 as required. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-21drm/nvc0: implement fencingBen Skeggs1-8/+20
Just simple REF_CNT fencing for the moment. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nouveau: Avoid potential race between nouveau_fence_update() and context ↵Francisco Jerez1-8/+11
takedown. Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nouveau: fix use of drm_mm_node in semaphore objectBen Skeggs1-3/+2
At some point in the future, this bo won't necessarily be backed by a drm_mm_node, so use the start/size fields of the ttm_mem_reg instead. Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nouveau: implicitly insert non-DMA objects into RAMHTBen Skeggs1-6/+1
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-08drm/nouveau: Spin for a bit in nouveau_fence_wait() before yielding the CPU.Francisco Jerez1-1/+2
Sleeping doesn't pay off for very short delays in comparison with the minimum granularity of schedule_timeout(). Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: tidy up and extend dma object creation interfacesBen Skeggs1-2/+2
Reviewed-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: fix annoying nouveau_fence type issueMarcin Slusarz1-11/+11
nouveau_fence_* functions are not type safe, which could lead to bugs. Additionally every use of nouveau_fence_unref had to cast struct nouveau_fence to void **. Fix it by renaming old functions and creating static inline functions with new prototypes. We still need old functions, because we pass function pointers to ttm. As we are wrapping functions, drop unused "void *arg" parameter where possible. Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com> Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: use object class structs more extensivelyBen Skeggs1-1/+1
The structs themselves, as well as the non-sw object creation function are probably very misnamed now. That's a problem for later :) Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: Take fence spinlock in nouveau_fence_channel_fini().Francisco Jerez1-0/+4
Without it there's a potential race with nouveau_fence_update(). Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: Avoid race in the interchannel sync code.Francisco Jerez1-9/+15
It needs a "strong" channel reference because it actually writes to the channel pushbuf, otherwise the corresponding FIFO context could get kicked off in the middle of nouveau_fence_sync(). Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: Make fences take a weak channel reference.Francisco Jerez1-1/+2
Fences didn't increment the channel reference count, and the fenced channel could go away at any time. Fixes a potential race in nouveau_fence_update(). Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: Use lazy fence waits when doing software interchannel sync.Francisco Jerez1-2/+2
Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: fix thinko in channel locking in semaphore pathBen Skeggs1-3/+3
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-12-03drm/nouveau: add more fine-grained locking to channel list + structuresBen Skeggs1-0/+10
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-11-18drm/nouveau: Fix sleep while atomic in the semaphore code.Francisco Jerez1-1/+6
Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-10-05drm/nv50: Fix large 3D performance regression caused by the interchannel ↵Francisco Jerez1-7/+39
sync patches. Reported-by: Christoph Bumiller <e0425955@student.tuwien.ac.at> Signed-off-by: Francisco Jerez <currojerez@riseup.net> Tested-by: Maarten Maathuis <madman2003@gmail.com> Tested-by: Xavier Chantry <chantry.xavier@gmail.com> Tested-by: Ben Skeggs <bskeggs@redhat.com> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-10-05drm/nouveau: Use semaphores to handle inter-channel sync in hardware.Francisco Jerez1-1/+194
Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-10-05drm/nouveau: Provide a means to have arbitrary work run on fence completion.Francisco Jerez1-0/+30
Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-10-05drm/nouveau: Minor refactoring/cleanup of the fence code.Francisco Jerez1-17/+46
Mainly to make room for inter-channel sync. Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-09-03drm/nouveau: Take fence spinlock before reading the last sequence.Francisco Jerez1-2/+4
It fixes a race between the TTM delayed work queue and the GEM IOCTLs (fdo bug 29583) uncovered by the BKL removal. Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-08-02drm/nouveau: set TASK_(UN)INTERRUPTIBLE before schedule_timeout()Kulikov Vasiliy1-2/+2
set_current_state() is called only once before the first iteration. After return from schedule_timeout() current state is TASK_RUNNING. If we are going to wait again, set_current_state() must be called. Signed-off-by: Kulikov Vasiliy <segooon@gmail.com> Signed-off-by: Francisco Jerez <currojerez@riseup.net> Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2010-07-13drm/nouveau: reduce usage of fence spinlock to when absolutely necessaryBen Skeggs1-25/+6
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-25 12:50:38 +0300