bug 1648908
This commit adds support for FECS ctxsw tracing. Code is compiled
conditionnaly under CONFIG_GK20_CTXSW_TRACE.
This feature requires an updated FECS ucode that writes one record to a ring
buffer on each context switch. On RM/Kernel side, the GPU driver reads records
from the master ring buffer and generates trace entries into a user-facing
VM ring buffer. For each record in the master ring buffer, RM/Kernel has
to retrieve the vmid+pid of the user process that submitted related work.
Features currently implemented:
- master ring buffer allocation
- debugfs to dump master ring buffer
- FECS record per context switch (with both current and new contexts)
- dedicated device for ctxsw tracing (access to VM ring buffer)
- SOF generation (and access to PTIMER)
- VM ring buffer allocation, and reconfiguration
- enable/disable tracing at user level
- event-based trace filtering
- context_ptr to vmid+pid mapping
- read system call for ctxsw dev
- mmap system call for ctxsw dev (direct access to VM ring buffer)
- poll system call for ctxsw dev
- save/restore register on ELPG/CG6
- separate user ring from FECS ring handling
Features requiring ucode changes:
- enable/disable tracing at FECS level
- actual busy time on engine (bug 1642354)
- master ring buffer threshold interrupt (P1)
- API for GPU to CPU timestamp conversion (P1)
- vmid/pid/uid based filtering (P1)
Change-Id: I8e39c648221ee0fa09d5df8524b03dca83fe24f3
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1022737
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Previously, only "high" priority bare channels were interleaved
between all other bare channels and TSGs. This patch decouples
priority from interleaving and introduces 3 levels for interleaving
a bare channel or TSG: high, medium, and low. The levels define
the number of times a channel or TSG will appear on a runlist (see
nvgpu.h for details).
By default, all bare channels and TSGs are set to interleave level
low. Userspace can then request the interleave level to be increased
via the CHANNEL_SET_RUNLIST_INTERLEAVE ioctl (TSG-specific ioctl will
be added later).
As timeslice settings will soon be coming from userspace, the default
timeslice for "high" priority channels has been restored.
JIRA VFND-1302
Bug 1729664
Change-Id: I178bc1cecda23f5002fec6d791e6dcaedfa05c0c
Signed-off-by: Aingara Paramakuru <aparamakuru@nvidia.com>
Reviewed-on: http://git-master/r/1014962
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Support preprocessing of SM exceptions if API
pointer pre_process_sm_exception() is defined
Also, expose some common APIs
Bug 200156699
Change-Id: I1303642c1c4403c520b62efb6fd83e95eaeb519b
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/925883
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>
Instead of depending on clock frame-work, use platform data
for ptimer source rate. Removed ptimerscaling10x platform
data, and use ptimer source frequency to calculate
ptimerscaling factor.
Reviewed-on: http://git-master/r/819030
(cherry picked from commit dd291334d54dab80cab7eb1656dffc48a59610b4)
Change-Id: I7638ce9875a6e440bbfc2ba2da0d0b094b2700ff
Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/827300
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>
When we induce a fake MMU fault, we do not have pointer to a channel.
Use the tsg pointer instead. Also remove the error print in case we
do not have ch pointer.
Change-Id: I14fd75d2b743244915bf32fe39de76097ef5c42f
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/819034
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>
To handle any of the pbdma interrupt, we currently write zero
to pbdma_method0 and then clear the interrupt
But this is insufficient since we cannot use same intr clear
method for all the interrupts
Hence, add intr specific routines to handle those interrupts
NV_PPBDMA_INTR_0_PBENTRY:
- fix the pb_header to have a null opcode
- fix the pbdma_method to have a valid nop
NV_PPBDMA_INTR_0_METHOD:
- fix the pbdma_method to have a valid nop
NV_PPBDMA_INTR_0_DEVICE:
- fix the pb_header to have a null opcode
- go through all pbdma_method0/1/2/3
-- if they contain host s/w methods, replace those
methods with a valid NOP
Bug 200134238
Change-Id: I10c284a6cdc1441f9d437cea65aae00d3c33a8c8
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/814561
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@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>
bug 1603226
host based timeouts use ptimer for detecting
timeouts. on gk20a and gm20b ptimer runs 2.6x
slower. scale the fifo_eng_timeout to account
for this
Change-Id: Ie44718382953e36436ea47d6e89b9a225d5c2070
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/799983
(cherry picked from commit d1d837fd09ff0f035feff1757c67488404c23cc6)
Reviewed-on: http://git-master/r/808250
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
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>
bug 1625901
1) disable ELPG before doing GR reset when runlist update times out
2) add mutex for GR reset to avoid multiple threads resetting GR
3) protect GR reset with FECS mutex so that no one else submits methods
Change-Id: I02993fd1eabe6875ab1c58a40a06e6c79fcdeeae
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/793643
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
In gk20a_fifo_handle_sched_error(), we currently have a sequence
to identify failing engine (stuck on context switch) and
corresponding failing channel with its type
Separate out this sequence in new API
gk20a_fifo_get_failing_engine_data() so that it can be
reused from else where too
Bug 200133289
Change-Id: I3cef395170cf8990c014c7505c798fd6f2e37921
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/797070
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
bug 200114561
1) when handling sched error, if CTXSW status reads switch
check FECS mailbox register to know whether next or current
channel caused error
2) Update recovery function to use ch id passed to it
3) Recovery function now passes mmu_engine_id to mmu fault
handler instead of fifo_engine_id
Change-Id: I3576cc4a90408b2f76b2c42cce19c27344531b1c
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/763538
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Sachin Nikam <snikam@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
Improve the error path and return values from function
gk20a_fifo_handle_sched_error()
- return true, when we trigger the recovery in this function
- otherwise, return false
No need to reset the scheduler error register in this function,
since we anyway clear the interrupt in fifo_error_isr()
Also, fix the typo
"reset initated" -> "reset initiated"
Bug 200089043
Change-Id: Ibfc2fd2133982a268699d08682bcd6f044a3196a
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/722711
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Add platform specific API pointer (*get_iova_addr)()
which can be used to get iova/physical address from
given scatterlist and flags
Use this API with g->ops.mm.get_iova_addr() instead
of calling API gk20a_mm_iova_addr() which makes it
platform specific
Bug 1605653
Change-Id: I798763db1501bd0b16e84daab68f6093a83caac2
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/713089
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
There were still a couple of places using sg_phys directly. Use new
gk20a_mem_phys() to make the code shorter.
Change-Id: I6eb9b14e0c14a27ec39bacd06ab24e31e99769ca
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/717502
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
Dump GR status registers in case of ctxsw timeout.
This is helpful in case where ctxsw timeout is encountered
during stress testing but we lose the bad state since we do
the recovery. So dump as much status as we can when timeouts
are seen
Bug 200062436
Change-Id: Ie7d320cefa7b272f2cc607cdb5c01ba1f43ba1f2
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/708465
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Make recovery a more straightforward process. When we detect a fault,
trigger MMU fault, and wait for it to trigger, and complete recovery.
Also reset engines before aborting channel to ensure no stray sync
point increments can happen.
Change-Id: Iac685db6534cb64fe62d9fb452391f43100f2999
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/709060
(cherry picked from commit 95c62ffd9ac30a0d2eb88d033dcc6e6ff25efd6f)
Reviewed-on: http://git-master/r/707443
Retrieve number of physical page bits based on chip.
Bug 1567274
Change-Id: I5a0f6a66be37f2cf720d66b5bdb2b704cd992234
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/601700
Query interrupt number and reset id from HW. Use the number
from HW when enabling and detecting interrupts.
Bug 200036089
Bug 1567274
Change-Id: If9cb4db79a19dcb193ba7ad9db7081f4fe1ab433
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/600988
Do not call PMU ELPG calls if ELPG should be disabled. Also skips
initialization of PMU ucode if PMU is disabled.
Bug 1567274
Change-Id: Ia9cd3b553c358142ee05a1b0e0832f9412f7cf17
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/593335
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Fix below sparse warnings :
warning: Using plain integer as NULL pointer
warning: symbol <variable/funcion> was not declared. Should it be static?
warning: Initializer entry defined twice
Also, remove dead functions
Bug 1573254
Change-Id: I29d71ecc01c841233cf6b26c9088ca8874773469
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/593363
Reviewed-by: Amit Sharma (SW-TEGRA) <amisharma@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
With CG enabled sometimes fifo could not be idled
during firmware load.
Bug 200042729
Change-Id: I43d7551c0c7c19314c52ac5f678afed8c6df6415
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/559077
Reviewed-by: Automatic_Commit_Validation_User
Convert GR and LTC HALs to use const structs, and initialize them
with macros.
Bug 1567274
Change-Id: Ia3f24a5eccb27578d9cba69755f636818d11275c
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/590371
When initializing fifo, we ignore several error conditions. Add
checks for them.
Change-Id: Id67f3ea51e3d4444b61a3be19553a5541b1d1e3a
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/553269
If engine status is in context switch in the fifo mmu fault handler,
dump falcon stats and gr stats for each engine.
Bug 1544766
Change-Id: Idfa9772b7e67072941144ac3bdd73e791fdc2b23
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/553205
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-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>
