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>
We have another constant timeout of 5s for channel watchdog.
Hence drop default channel timeout (used for SCHED errors)
to 3s so that they both don't conflict with each other
Bug 200133289
Change-Id: Ieed675cad462119ff2f1a155a955c8a22cb6c6f8
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/810958
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-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>
While loading the context, erstwhile set CDE flag was being
overwritten by copying code of golden context, thus losing
the information. This was not letting the CDE info reach
to the ucode, and T1 was not configured to 128B mem access.
Bug 200096226
Change-Id: I5ceb234a62450ff7875aeba05ec616758cb319d9
Signed-off-by: sujeet baranwal <sbaranwal@nvidia.com>
Reviewed-on: http://git-master/r/811767
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>
bug 1688374
disabling pmu will break RAM suspend on chips implementing
split rails. pmu will be powered down along with rest of
the GPU anyway. pmu_destroy is not be used outside of
rail gating or gpu suspend
Change-Id: I9e89859b7c701f731276ae1d1063d9ccd88d4334
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/805940
(cherry picked from commit 8ded353878ff7df73e55b702041008ddc3cbf069)
Reviewed-on: http://git-master/r/808248
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Add CPU dcache flush after populating scatterBuffer so that the GPU
will see the buffer contents.
Bug 1679453
Change-Id: I564394ed1fcff4d08d753e753bd3243b460d76df
Signed-off-by: Jussi Rasanen <jrasanen@nvidia.com>
Reviewed-on: http://git-master/r/805197
(cherry picked from commit d6a5513745aa77c84ac5408a62f72f24839ef439)
Reviewed-on: http://git-master/r/808246
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
The server now exposes a new GMMU map interface that
can accept a scatter-gather list. This is needed to support
SMMU-bypass configurations.
Bug 1677153
JIRA VFND-689
Change-Id: I7b5af145db57dcebe2c9125ec90c689798d7e69e
Signed-off-by: Aingara Paramakuru <aparamakuru@nvidia.com>
Reviewed-on: http://git-master/r/792558
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-by: Vladislav Buzov <vbuzov@nvidia.com>
It is possible that user space requests more unmaps on a buffer
than it requested maps
In this case, we end up dropping one extra refcount which could
lead to releasing buffer early
Fix this by checking and returning if buffer's user_mapped
refcount is already zero
Bug 200130521
Change-Id: Ic8ef2dbfe0476b16d852ad899b1ed0404b5bb7de
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/788904
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>
Add support for CDE scatter buffers. When the bus addresses for
surfaces are not contiguous as seen by the GPU (e.g., when SMMU is
bypassed), CDE swizzling needs additional per-page information. This
information is populated in a scatter buffer when required.
Bug 1604102
Change-Id: I3384e2cfb5d5f628ed0f21375bdac8e36b77ae4f
Signed-off-by: Jussi Rasanen <jrasanen@nvidia.com>
Reviewed-on: http://git-master/r/789436
Reviewed-on: http://git-master/r/791243
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>
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>
Currently, while releasing the debug session we enable powergate
only if a channel is bound to session
If a session has no channel bound to it, and has powergate
disabled, then we do not enable powergate when that session
is closed
Fix this by calling dbg_set_powergate(POWERGATE_ENABLE) always
while releasing the session
Refcounting and sanity checks in dbg_set_powergate() will take
care of situation if powergate was not disabled by the session
in first place
Bug 1679372
Change-Id: I4e027393c611d3e8ab4f20e195f31871086da736
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/796999
Tested-by: Sandarbh Jain <sanjain@nvidia.com>
Reviewed-by: Sandarbh Jain <sanjain@nvidia.com>
Reviewed-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>
As per current sequence in gk20a_channel_abort(),
we first balance the syncpoint values associated with
failing channel, and then abort it
Reverse this sequence so that we first disable the channel
and then only balance the syncpoints
Bug 200133289
Change-Id: I5a748afce437e728a5ff6c8a030a75d0f627c622
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/797071
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-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>
Separate the kernel and userspace regions in the GPU virtual address
space. Do this by reserving the last part of the GPU VA aperture for
the kernel, and extend GPU VA aperture accordingly for regular address
spaces. This prevents the kernel polluting the userspace-visible GPU
VA regions, and thus, makes the success of fixed-address mapping more
predictable.
Bug 200077571
Change-Id: I63f0e73d4c815a4a9fa4a9ce568709974690ef0f
Signed-off-by: Sami Kiminki <skiminki@nvidia.com>
Reviewed-on: http://git-master/r/747191
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
consider buffer size as well when calculating the required alignment
for a buffer else we would be mapping a VA range greater than requested
thus allowing access to entire large page even when not needed creating
a security hole.
Bug 1492689
Change-Id: Ic404708d238621ea64c26cafd05bc30ba8e02e12
Signed-off-by: Sri Krishna chowdary <schowdary@nvidia.com>
Reviewed-on: http://git-master/r/793229
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: Sachin Nikam <snikam@nvidia.com>
Cyclestats snapshot feature is expected for new devices.
The detection code was isolated in separate function and run-time
check added to validate/allow ioctl calls on the current GPU.
Bug 1674079
Change-Id: Icc2f1e5cc50d39b395d31d5292c314f99d67f3eb
Signed-off-by: Leonid Moiseichuk <lmoiseichuk@nvidia.com>
Reviewed-on: http://git-master/r/781697
(cherry picked from commit bdd23136b182c933841f91dd2829061e278a46d4)
Reviewed-on: http://git-master/r/793630
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
