| Commit message (Collapse) | Author | Age |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
export below APIs for TSGs :
gk20a_enable_tsg() - enable only TSG
gk20a_disable_tsg() - disable only TSG
gk20a_enable_channel_tsg() -
if channel is part of TSG, enable TSG
otherwise enable channel
gk20a_disable_channel_tsg() -
if channel is part of TSG, disable TSG
otherwise disable channel
Bug 200156699
Change-Id: Icdaca35235c3f323687f839fe32c6c5fe964b230
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/927131
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Interleave all high priority channels between all other channels.
This reduces the latency for high priority work when there
are a lot of lower priority work present, imposing an upper
bound on the latency. Change the default high priority timeslice
from 5.2ms to 3.0 in the process, to prevent long running high priority
apps from hogging the GPU too much.
Introduce a new debugfs node to enable/disable high priority
channel interleaving. It is currently enabled by default.
Adds new runlist length max register, used for allocating
suitable sized runlist.
Limit the number of interleaved channels to 32.
This change reduces the maximum time a lower priority job
is running (one timeslice) before we check that high priority
jobs are running.
Tested with gles2_context_priority (still passes)
Basic sanity testing is done with graphics_submit
(one app is high priority)
Also more functional testing using lots of parallel runs with:
NVRM_GPU_CHANNEL_PRIORITY=3 ./gles2_expensive_draw
–drawsperframe 20000 –triangles 50 –runtime 30 –finish
plus multiple:
NVRM_GPU_CHANNEL_PRIORITY=2 ./gles2_expensive_draw
–drawsperframe 20000 –triangles 50 –runtime 30 -finish
Previous to this change, the relative performance between
high priority work and normal priority work comes down
to timeslice value. This means that when there are many
low priority channels, the high priority work will still
drop quite a lot. But with this change, the high priority
work will roughly get about half the entire GPU time, meaning
that after the initial lower performance, it is less likely
to get lower in performance due to more apps running on the system.
This change makes a large step towards real priority levels.
It is not perfect and there are no guarantees on anything,
but it is a step forwards without any additional CPU overhead
or other complications. It will also serve as a baseline to
judge other algorithms against.
Support for priorities with TSG is future work.
Support for interleave mid + high priority channels,
instead of just high, is also future work.
Bug 1419900
Change-Id: I0f7d0ce83b6598fe86000577d72e14d312fdad98
Signed-off-by: Peter Pipkorn <ppipkorn@nvidia.com>
Reviewed-on: http://git-master/r/805961
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
It'll detect dead semaphore acquire. The worst case is when
ACQUIRE_SWITCH is disabled, semaphore acquire will poll and
consume full gpu timeslicees.
The timeout value is set to half of channel WDT.
Bug 1636800
Change-Id: Ida6ccc534006a191513edf47e7b82d4b5b758684
Signed-off-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-on: http://git-master/r/928827
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vladislav Buzov <vbuzov@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Current sequence in gk20a_disable_channel() is
- disable channel in gk20a_channel_abort()
- adjust pending fence in gk20a_channel_abort()
- preempt channel
But this leads to scenarios where syncpoint has
min > max value
Hence to fix this, make sequence in gk20a_disable_channel()
- disable channel in gk20a_channel_abort()
- preempt channel in gk20a_channel_abort()
- adjust pending fence in gk20a_channel_abort()
If gk20a_channel_abort() is called from other API where
preemption is not needed, then use channel_preempt
flag and do not preempt channel in those cases
Bug 1683059
Change-Id: I4d46d4294cf8597ae5f05f79dfe1b95c4187f2e3
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/921290
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
When closing channel, disable and preempt it immediately instead of
waiting for it to finish all work.
Bug 1683059
Change-Id: Ia5f5fc6a072dc3ddb1e9bf63534814ff0a60b5b4
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/836746
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Currently, we create sync_fence (from nvhost_sync_create_fence())
for every submit
But not all submits request for a sync_fence.
Also, nvhost_sync_create_fence() API takes about 1/3rd of the total
submit path.
Hence to optimize, we can allocate sync_fence
only when user explicitly asks for it using
(NVGPU_SUBMIT_GPFIFO_FLAGS_FENCE_GET &&
NVGPU_SUBMIT_GPFIFO_FLAGS_SYNC_FENCE)
Also, in CDE path from gk20a_prepare_compressible_read(),
we reuse existing fence stored in "state" and that can
result into not returning sync_fence_fd when user asked
for it
Hence, force allocation of sync_fence when job submission
comes from CDE path
Bug 200141116
Change-Id: Ia921701bf0e2432d6b8a5e8b7d91160e7f52db1e
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/812845
(cherry picked from commit 5fd47015eeed00352cc8473eff969a66c94fee98)
Reviewed-on: http://git-master/r/837662
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add IOCTL NVGPU_IOCTL_CHANNEL_WDT to disable/enable
watchdog per-channel
Also, if watchdog is disabled, we currently schedule
the worker with MAX timeout.
Instead of this, do not schedule any worker if
watchdog is disabled
Bug 1683059
Bug 1700277
Change-Id: I7f6bec84adeedb74e014ed6d1471317b854df84c
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/837962
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
We currently allocate private command buffers (wait_cmd
and incr_cmd) before submitting the job but we never
free them explicitly.
When private command queue of the channel is full, we
then try to recycle/remove free command buffers.
But this recycling happens during submit path, and
hence that particular submit path takes much longer
Rework this as below :
- add reference of command buffers to job structure
- when job completes, free the command buffers
explicitly
- remove the code to recycle buffers since it should
not be needed now
Note that command buffers need to be freed in order of
their allocation. Ensure this with error print before
freeing the command buffer entry
Bug 200141116
Bug 1698667
Change-Id: Id4b69429d7ad966307e0d122a71ad55076684307
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/827638
(cherry picked from commit c6cefd69b71c9b70d6df5343b13dfcfb3fa99598)
Reviewed-on: http://git-master/r/835802
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In GPU job submit path gk20a_ioctl_channel_submit_gpfifo(),
we currently allocate a temporary gpfifo, copy user space
gpfifo content into this temporary buffer, and then copy
temp buffer content into channel's gpfifo.
Allocation/copy/free of temporary buffer adds additional
overhead
Rewrite this sequence such that gk20a_submit_channel_gpfifo()
can receive either a pre-filled gpfifo or pointer to
user provided args.
And then we can direclty copy the user provided gpfifo
into the channel's gpfifo
Also, if command buffer tracing is enabled, we still need
to copy user provided gpfifo into temporaty buffer for reading
But that should not cause overhead in real world use case
Bug 200141116
Change-Id: I7166c9271da2694059da9853ab8839e98457b941
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/823386
(cherry picked from commit 3e0702db006c262dd8737a567b8e06f7ff005e2c)
Reviewed-on: http://git-master/r/835799
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add new IOCTL NVGPU_IOCTL_TSG_SET_PRIORITY to allow
setting timeslice for entire TSG
Return error from channel specific IOCTL_CHANNEL_SET_PRIORITY
if the channel is part of TSG
Separate out API gk20a_channel_get_timescale_from_timeslice()
to get timeslice_timeout and scale from timeslice period
Use this API to get timeslice_timeout and scale for TSG and
store it in tsg_gk20a structure
Then trigger runlist update so that new timeslice values
will be re-written to runlist for TSG
Bug 200146615
Change-Id: I555467d034f81b372b31372f0835d72b1c159508
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/824206
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Get rid of the duplicate gpfifo struct to emphasize the fact that
nvgpu_gpfifo is the only memory layout for gpfifo entries that works.
This is the same layout that HW uses.
Also, add a local pointer to the gpfifo memory in
gk20a_submit_channel_gpfifo to get rid of repeated typecasts.
Bug 1592391
Bug 1550886
Change-Id: I5432859ef8e7c1aab5907e44098994d7bb807f50
Signed-off-by: Janne Hellsten <jhellsten@nvidia.com>
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/677341
(cherry picked from commit 724c8c6228af81dd440e825bddf545dd6b2b8bd7)
Reviewed-on: http://git-master/r/822548
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Arto Merilainen <amerilainen@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
| |
Protect creation and deletion of sync by an own mutex. This prevents
deadlock in channel abort when abort is called from submit path.
Bug 200147887
Change-Id: I5d6308b773c1d1a6a89d4590e2e74c74d691f79d
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/821127
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In gk20a_fifo_handle_sched_error(), we currently cancel
the timeout on all the channels
But this could cause us to miss one of stuck channel
hence, instead of cancelling, restart the timeout of channel
on which it is already active
Bug 200133289
Change-Id: I40e7e0e5394911fc110ab6fde39592b885dfaf7d
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/816133
Reviewed-by: Ishan Mittal <imittal@nvidia.com>
Tested-by: Ishan Mittal <imittal@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A SCHED error might cause multiple channels' watchdogs to trigger
simultaneously
Hence, to avoid this conflict cancel watchdog timeout on all
channels before recovering from SCHED errors
Also, define API gk20a_channel_timeout_stop_all_channels()
to cancel wdt timeout on all channels
Bug 200133289
Change-Id: I8324c397891f0a711327b77d0677cd6718af6d01
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/810959
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Channel watchdog timeout is set to a costant value of 5s
as of now
Make this timeout platform specific and set it to 5s for gm20b
and 7s for gk20a
Bug 200133289
Change-Id: I6e7f0fed93a8d5b197ae46807131311196c6636f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/810956
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In case of CDE channel, T1 (Tex) unit needs to be promoted to 128B
aligned, otherwise causes a HW deadlock. Gpu driver makes changes in
FECS header which FECS uses to configure the T1 promotions to aligned
128B accesses.
Bug 200096226
Change-Id: I8a8deaf6fb91f4bbceacd491db7eb6f7bca5001b
Signed-off-by: sujeet baranwal <sbaranwal@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: sujeet baranwal <sbaranwal@nvidia.com>
Reviewed-on: http://git-master/r/804625
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Implement per-channel watchdog/timer as per below rules :
- start the timer while submitting first job on channel or if
no timer is already running
- cancel the timer when job completes
- re-start the timer if there is any incomplete job left
in the channel's queue
- trigger appropriate recovery method as part of timeout
handling mechanism
Handle the timeout as per below :
- get timed out channel, and job data
- disable activity on all engines
- check if fence is really pending
- get information on failing engine
- if no engine is failing, just abort the channel
- if engine is failing, trigger the recovery
Also, add flag "ch_wdt_enabled" to enable/disable channel
watchdog mechanism. Watchdog can also be disabled using
global flag "timeouts_enabled"
Set the watchdog time to be 5s using macro
NVGPU_CHANNEL_WATCHDOG_DEFAULT_TIMEOUT_MS
Bug 200133289
Change-Id: I401cf14dd34a210bc429f31bd5216a361edf1237
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/797072
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
| |
This reverts commit 882975f7f1b4e050be79b0a047a2daa8b53a9187.
Change-Id: I4940fc9f7a837840be1ea8e42d58d603235d88d5
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/804616
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In case of CDE channel, T1 (Tex) unit needs to be promoted to 128B
aligned, otherwise causes a HW deadlock. Gpu driver makes changes in
FECS header which FECS uses to configure the T1 promotions to aligned
128B accesses.
Bug 200096226
Change-Id: Ic006b2c7035bbeabe1081aeed968a6c6d11f9995
Signed-off-by: sujeet baranwal <sbaranwal@nvidia.com>
Reviewed-on: http://git-master/r/802327
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add reference counting for channels, and wait for reference count to
get to 0 in gk20a_channel_free() before actually freeing the channel.
Also, change free channel tracking a bit by employing a list of free
channels, which simplifies the procedure of finding available channels
with reference counting.
Each use of a channel must have a reference taken before use or held
by the caller. Taking a reference of a wild channel pointer may fail, if
the channel is either not opened or in a process of being closed. Also,
add safeguards for protecting accidental use of closed channels,
specifically, by setting ch->g = NULL in channel free. This will make it
obvious if freed channel is attempted to be used.
The last user of a channel might be the deferred interrupt handler,
so wait for deferred interrupts to be processed twice in the channel
free procedure: once for providing last notifications to the channel
and once to make sure there are no stale pointers left after referencing
to the channel has been denied.
Finally, fix some races in channel and TSG force reset IOCTL path,
by pausing the channel scheduler in gk20a_fifo_recover_ch() and
gk20a_fifo_recover_tsg(), while the affected engines have been identified,
the appropriate MMU faults triggered, and the MMU faults handled. In this
case, make sure that the MMU fault does not attempt to query the hardware
about the failing channel or TSG ids. This should make channel recovery
more safe also in the regular (i.e., not in the interrupt handler) context.
Bug 1530226
Bug 1597493
Bug 1625901
Bug 200076344
Bug 200071810
Change-Id: Ib274876908e18219c64ea41e50ca443df81d957b
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Signed-off-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-on: http://git-master/r/448463
(cherry picked from commit 3f03aeae64ef2af4829e06f5f63062e8ebd21353)
Reviewed-on: http://git-master/r/755147
Reviewed-by: Automatic_Commit_Validation_User
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
That is a kernel supporting code for cyclestats mode E.
Cyclestats mode E implemented following Windows-design in user-space
and required the following operations to be implemented:
- attach a client for shared hardware buffer of device
- detach client from shared hardware buffer
- flush means copy of available data from hardware buffer to private
client buffers according to perfmon IDs assigned for clients
- perfmon IDs management for user-space clients
- a NVGPU_GPU_FLAGS_SUPPORT_CYCLE_STATS_SNAPSHOT capability added
Bug 1573150
Change-Id: I9e09f0fbb2be5a95c47e6d80a2e23fa839b46f9a
Signed-off-by: Leonid Moiseichuk <lmoiseichuk@nvidia.com>
Reviewed-on: http://git-master/r/740653
(cherry picked from commit 79fe89fd4cea39d8ab9dbef0558cd806ddfda87f)
Reviewed-on: http://git-master/r/753274
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Pass flags parameter to channel_setup_ramfc for
indicating nvgpu_alloc_gpfifo_args characteristics.
Bug 1645628
Change-Id: Ia40b37c5c7b208d459aa84f1b022036dd5e1b599
Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/744526
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
| |
Introduce mem_desc, which holds all information needed for a buffer.
Implement helper functions for allocation and freeing that use this
data type.
Change-Id: I82c88595d058d4fb8c5c5fbf19d13269e48e422f
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/712699
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add a big mutex for protecting the channel during ioctls, in case the
userspace uses the same channel from several threads at once. The lock
is taken during all operations except CHANNEL_WAIT, which could deadlock.
Bug 1603482
Change-Id: Ibed962eadc9f00645abd54413dde9aaee00377ab
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/678871
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add the ioctl to open a new gpu channel to also the control node for
improved process startup performance, in addition to the current open
ioctl in the channel node. The new channel fd creation is refactored to
a separate function which is called from both ctrl and channel ioctls.
Bug 1604952
Change-Id: I3357ceec694c0e6d7a85807183884324cb725d3a
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/679516
Reviewed-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
| |
Signed-off-by: Dan Willemsen <dwillemsen@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
Make mem_desc a generic container for buffers. Add functions for
allocating and mapping buffers to an address space which store their
data in mem_desc.
Change-Id: I031643442c6fd41f5e7222fe9b7bfcaf9b784db5
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/660908
GVS: Gerrit_Virtual_Submit
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Protect callback races from spurious gk20a channel updates by testing if
the channel update callback still exists when in the scheduled work
(instead of only when scheduling the work to the queue), and by
canceling the work when the channel is freed. Protect access to the
callback and its data by accessing them together inside
spinlock-protected regions.
Bug 200051384
Change-Id: Ib4e1571c35f662195e1dec1e362df32ddc099eb3
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/592026
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Kernel support for allowing a GPU debugger to suspend and resume
SMs. Invocation of "suspend" on a given channel will suspend all
SMs if the channel is resident, else remove the channel form the
runlist. Similarly, "resume" will either resume all SMs if the
channel was resident, or re-enable the channel in the runlist.
Change-Id: I3b4ae21dc1b91c1059c828ec6db8125f8a0ce194
Signed-off-by: sujeet baranwal <sbaranwal@nvidia.com>
Signed-off-by: Mayank Kaushik <mkaushik@nvidia.com>
Reviewed-on: http://git-master/r/552115
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add support for a callback function with user data pointer to be
scheduled from the end of gk20a_channel_update. The function and its
private data are supplied when opening a new channel.
Change-Id: Ib6b408855ea60d46a6a114a69c01904703019572
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/552014
Reviewed-by: Arto Merilainen <amerilainen@nvidia.com>
Tested-by: Arto Merilainen <amerilainen@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Move nvgpu ioctls from the many user space interface headers to a new
single nvgpu.h header under include/uapi. No new code or replaced names
are introduced; this change only moves the definitions and changes
include directives accordingly.
Bug 1434573
Change-Id: I4d02415148e437a4e3edad221e08785fac377e91
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/542651
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
To help remove the nvhost dependency from nvgpu, rename ioctl defines
and structures used by nvgpu such that nvhost is replaced by nvgpu.
Duplicate some structures as needed.
Update header guards and such accordingly.
Change-Id: Ifc3a867713072bae70256502735583ab38381877
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/542620
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add poll interface and control ioctls for waiting for GPU job completion
via semaphores.
Poll on a gk20a channel file waits for events from pending semaphore
interrupts (stalling) of that channel. New ioctls enable and disable the
events, and clear a single interrupt event so that next poll doesn't
wake up for it again.
Bug 1528781
Change-Id: I5c6238966b5d0900c8ab263c6a7f8f2611901f33
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/497750
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The nvgpu driver now supports using the Tegra graphics virtualization
interfaces to support gk20a in a virtualized environment.
Bug 1509608
Change-Id: I6ede15ee7bf0b0ad8a13e8eb5f557c3516ead676
Signed-off-by: Aingara Paramakuru <aparamakuru@nvidia.com>
Reviewed-on: http://git-master/r/440122
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When moving compression state tracking and compbit management ops to
kernel, we need to attach a fence to dma-buf metadata, along with the
compbit state.
To make in-kernel fence management easier, introduce a new gk20a_fence
abstraction. A gk20a_fence may be backed by a semaphore or a syncpoint
(id, value) pair. If the kernel is configured with CONFIG_SYNC, it will
also contain a sync_fence. The gk20a_fence can easily be converted back
to a syncpoint (id, value) parir or sync FD when we need to return it to
user space.
Change gk20a_submit_channel_gpfifo to return a gk20a_fence instead of
nvhost_fence. This is to facilitate work submission initiated from
kernel.
Bug 1509620
Change-Id: I6154764a279dba83f5e91ba9e0cb5e227ca08e1b
Signed-off-by: Lauri Peltonen <lpeltonen@nvidia.com>
Reviewed-on: http://git-master/r/439846
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This patch modifies channel interfaces to allow allocating the
channel for kernel use. This is needed if we want to run a shader
from kernel space.
Bug 1409151
Change-Id: I3544186bb1541120f85e01a19de106ef011c1b11
Signed-off-by: Arto Merilainen <amerilainen@nvidia.com>
Reviewed-on: http://git-master/r/440261
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Lauri Peltonen <lpeltonen@nvidia.com>
GVS: Gerrit_Virtual_Submit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Channel and gpfifo allocations are entirely separated from each
other, however, the code here assumes that active channel means
that the channel also has a gpfifo.
This reverts commit a24602f094380539788696d1b1567a4f4d914b17 which
added gpfifo dump. Changing debug dumping to be safe requires
refactoring the channel release code to use proper locking.
Bug 1530226
Change-Id: I2fb02542a17dd56a0a9ce732b327e34b85ade8b9
Signed-off-by: Arto Merilainen <amerilainen@nvidia.com>
Reviewed-on: http://git-master/r/434038
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: Shridhar Rasal <srasal@nvidia.com>
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
All channels in a TSG need to share same engine context
i.e. pointer in RAMFC of all channels in a TSG must point
to same NV_RAMIN_GR_WFI_TARGET
To get this, add a pointer to gr_ctx inside TSG struct so
that TSG can maintain its own unique gr_ctx
Also, change the type of gr_ctx in a channel to pointer
variable so that if channel is part of TSG it can point
to TSG's gr_ctx otherwise it will point to its own gr_ctx
In gk20a_alloc_obj_ctx(), allocate gr_ctx as below :
1) If channel is not part of any TSG
- allocate its own gr_ctx buffer if it is already not allocated
2) If channel is part of TSG
- Check if TSG has already allocated gr_ctx (as part of TSG)
- If yes, channel's gr_ctx will point to that of TSG's
- If not, then it means channels is first to be bounded to
this TSG
- And in this case we will allocate new gr_ctx on TSG first
and then make channel's gr_ctx to point to this gr_ctx
Also, gr_ctx will be released as below ;
1) If channels is not part of TSG, then it will be released
when channels is closed
2) Otherwise, it will be released when TSG itself is closed
Bug 1470692
Change-Id: Id347217d5b462e0e972cd3d79d17795b37034a50
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/417065
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add support to create/destroy TSGs using node "/dev/nvhost-tsg-gpu"
Provide below IOCTLs to bind/unbind channels to/from TSGs :
NVGPU_TSG_IOCTL_BIND_CHANNEL
NVGPU_TSG_IOCTL_UNBIND_CHANNEL
Bug 1470692
Change-Id: Iaf9f16a522379eb943906624548f8d28fc6d4486
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/416610
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When outputting debug dump, print the contents of current push buffer
segment.
Also changes the debug dump to use pr_cont when applicable, and dumps
state before recovering in case channel was not loaded to an engine.
Bug 1498688
Change-Id: I5ca12f64bae8f12333d82350278c700645d5007e
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/422198
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When aborting jobs on channel error situations, we manually set
the channel syncpoint's min == max in gk20a_disable_channel_no_update.
Nvhost will notice this manual syncpoint increment, and will call back
to gk20a_channel_update, which will clean up the job.
With semaphore synchronization, we don't have anybody calling back to
gk20a_channel_update, so we need to call it ourselves. Release job
semaphores (the equivalent of set_min_eq_max) on
gk20a_disable_channel_no_update, and if any semaphores were released,
call gk20a_channel_update afterwards.
Because we are actually calling gk20a_channel_update in some situations,
gk20a_disable_channel_no_update is no longer an appropriate name for the
function. Rename it to gk20a_channel_abort.
Bug 1450122
Change-Id: I1267b099a5778041cbc8e91b7184844812145b93
Signed-off-by: Lauri Peltonen <lpeltonen@nvidia.com>
Reviewed-on: http://git-master/r/422161
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add semaphore implementation of the gk20a_channel_sync interface.
Each channel has one semaphore pool, which is mapped as read-write to
the channel vm. We allocate one or two semaphores from the pool for each
submit.
The first semaphore is only needed if we need to wait for an opaque sync
fd. In that case, we allocate the semaphore, and ask GPU to wait for
it's value to become 1 (semaphore acquire method). We also queue a
kernel work that waits on the fence fd, and subsequently releases the
semaphore (sets its value to 1) so that the command buffer can proceed.
The second semaphore is used on every submit, and is used for work
completion tracking. The GPU sets its value to 1 when the command buffer
has been processed.
The channel jobs need to hold references to both semaphores so that
their backing semaphore pool slots are not reused while the job is in
flight. Therefore gk20a_channel_fence will keep a reference to the
semaphore that it represents (channel fences are stored in the job
structure). This means that we must diligently close and dup the
gk20a_channel_fence objects to avoid leaking semaphores.
Bug 1450122
Bug 1445450
Change-Id: Ib61091a1b7632fa36efe0289011040ef7c4ae8f8
Signed-off-by: Lauri Peltonen <lpeltonen@nvidia.com>
Reviewed-on: http://git-master/r/374844
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- Export gk20a_wait_channel_idle() function from channel_gk20a.h
- also, return error -EBUSY from this function when channel is
found to be not idle
Bug 1487804
Change-Id: Ia7425e9b1332260ee9a53dca55ab07541f2755a9
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/412059
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add submit mutex lock to avoid race conditions between submitting
a job, removing a job and submitting WFI
With this lock make below operations atomic :
during submit_gpfifo() -
1. getting new syncpt
2. inserting syncpt increment
3. submitting gpfifo
4. setting job completion interrupt
during submit_wfi() -
1. getting new syncpt
2. inserting syncpt increment when idle
during channel_update() -
1. checking the submit job completion
2. freeing the job if it is completed
Bug 1305024
Change-Id: I0e3c0b8906d83fd59642344626ffdf24fad2aaab
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/397670
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
|
|
|
|
|
|
|
|
|
| |
Add abstraction for triggering fake MMU fault, and a gk20a
implementation. Also adds recovery to FE hardware warning
exception to make testing easier.
Bug 1495967
Change-Id: I6703cff37900a4c4592023423f9c0b31a8928db2
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
|
|
This patch moves the NVIDIA GPU driver to a new location.
Bug 1482562
Change-Id: I24293810b9d0f1504fd9be00135e21dad656ccb6
Signed-off-by: Arto Merilainen <amerilainen@nvidia.com>
Reviewed-on: http://git-master/r/383722
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
|