Add cleanup to the gk20a_probe() function since it will often fail
due to probe deferal. These "failures" cause this function to be
called multiple times and potentially allocate many resources over
and over again, leaking the old allocations.
Bug 200369627
Change-Id: Ic0bba0ae6542485135d9cb7393086e4460cd271d
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1640628
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
-MMU_CTRL_USE_PDB_BIG_PAGE_SIZE is set to TRUE and hence
RAMIN_BIG_PAGE_SIZE should be set to 64KB i.e. val 1.
By default this is set to 128KB i.e. val 0.
-This change will also fix an issue where perfbuffer_enable and
nvgpu_init_hwpm function pass 0 as big page size while initializing
inst_block and due to which ramin_big_page_size does not get updated
to 64KB and remains set to unsupported 128KB value.
-Volta supports 64KB for big pages. Selecting 128KB for
big pages results in an UNBOUND_INSTANCE fault.
Bug 200327596
Change-Id: Ie304e4e5ff7bedaead27e9380d64c59013dd64ca
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1639540
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Following fb iso register is not valid for gv11b but
hw headers has it. So, removing it manually from
gating register list:
0x00100D1C
Following sm blcg register not hooked up correctly
in gv11b. So, removing it manually from gating register
list:
0x00419c84
Once hw headers are updated, gating register tool will
automatically remove them from kernel code.
Bug 2042775
Change-Id: I4839b857656220566e53b66d3aead676893aaa59
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1636787
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add HAL for dumping ctxsw statistics. The statistics are dependent on
the architecture, and the function that calls this operation needs to
be moved to gk20a.
Bug 1842197
Change-Id: I285c74b8ddc8c7854c85b3fef4cbfc582098919e
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1632681
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Upon receiving MMU_FAULT error, MMU will forward MMU_NACK to SM
If MMU_NACK is masked out, SM will simply release the semaphores
And if semaphores are released before MMU fault is handled, user space
could see that operation as successful incorrectly
Fix this by handling SM reported MMU_NACK exception
Enable MMU_NACK reporting in gv11b_gr_set_hww_esr_report_mask
In MMU_NACK handling path, we just set the error notifier and clear
the interrupt so that the User Space sees the error as soon as
semaphores are released by SM
And MMU_FAULT handling path will take care of triggering RC recovery
anyways
Also add necessary h/w accessors for mmu_nack
Bug 2040594
Jira NVGPU-473
Change-Id: Ic925c2d3f3069016c57d177713066c29ab39dc3d
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1631708
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
runlist event interrupt is not needed to be enabled as
s/w polls for preemption completion for preempts issued
in RUNLIST_PREEMPT. Even though it is not enabled, intr
will get set in fifo_intr_0 status register whenever
RUNLIST_PRREMPT is successfully completed. Since intr
is disabled, fifo intr will not be triggered but it will
be handled during handling of other fifo interrupts
whenever fifo intr is triggered.
Bug 2039371
Change-Id: I0817c2b6e9f3f14958ca7c738392bc67875be5d5
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1630283
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
On gv11b we can have multiple SMs per TPC. Add sm_per_tpc in
vgpu constants to properly dimension the virtual SM to TPC/GPC
mapping in virtualization case.
Use TEGRA_VGPU_CMD_GET_SMS_MAPPING to query current mapping.
Bug 2039676
Change-Id: I817be18f9a28cfb9bd8af207d7d6341a2ec3994b
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1631203
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Used chip specific attrib_cb_gfxp_default_size and
attrib_cb_gfxp_size buffer sizes during committing
global callback buffer when gfx preemption is requested.
These sizes are different for gv11b from gp10b.
For gp10b used smaller buffer sizes than specified
value in hw manuals as per sw requirement.
Also used gv11b specific preemption related functions:
gr_gv11b_set_ctxsw_preemption_mode
gr_gv11b_update_ctxsw_preemption_mode
This is required because preemption related buffer
sizes are different for gv11b from gp10b. More optimization
will be done as part of NVGPU-484.
Another issue fixed is: gpu va for preemption buffers
still needs to be 8 bit aligned, even though 49 bits
available now. This done because of legacy implementation
of fecs ucode.
Bug 1976694
Change-Id: I2dc923340d34d0dc5fe45419200d0cf4f53cdb23
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1635027
GVS: Gerrit_Virtual_Submit
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In case we need to re-initialize GR after floorsweeping TPC,
gp10b_ltc_init_comptags() will try to allocate comptag memory again
Skip this during re-initialization since it is unnecessary to
re-allocate all those buffers
Comptag buffer size is 33MB and reallocating causes huge memory leak
anyways
Bug 2031635
Change-Id: I935f96eb133283d6f935589c0e581e0997e980e2
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1634737
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This reverts commit caf168e33e.
Might be causing an intermittency in quill-c03 graphics submit. Super
weird since the only change that seems like it could affect it is the
header file update but that seems rather safe.
Bug 2044830
Change-Id: I14809d4945744193b9c2d7729ae8a516eb3e0b21
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1634349
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Timo Alho <talho@nvidia.com>
Tested-by: Timo Alho <talho@nvidia.com>
- F/W version update for gv11b PMU ucode of
CL https://git-master.nvidia.com/r/#/c/1628288/
Current CL has PMU F/W version for ucode bin of
P4 CL# 23378914
P4 CL# & its changes.
- 23378914
- Don't post "PMU_PG_EVENT_IDLE_SNAP" event in
method pgConvertPgInterrupts_GP10X()
- 23355380
- Remove debug code included by mistake in P4
change list #23354716
- 23354716
- Made change to point CONVERT_PG_INTERRUPTS of
gv11b to _GP10x - pgConvertPgInterrupts_GP10X()
- Removed PMU halt upon FIFO preempt timeout in
_fifoPreemptRunlist_GP10X()
Bug 2039371
Bug 200377983
Change-Id: I8ce7cb926203b329308944235a06933768ed2a5f
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1628380
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: David Martinez Nieto <dmartineznie@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
GVS: Gerrit_Virtual_Submit
Tested-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Used chip specific attrib_cb_gfxp_default_size and
attrib_cb_gfxp_size buffer sizes during committing
global callback buffer when gfx preemption is requested.
These sizes are different for gv11b from gp10b.
Also used gv11b specific preemption related functions:
gr_gv11b_set_ctxsw_preemption_mode
gr_gv11b_update_ctxsw_preemption_mode
This is required because preemption related buffer
sizes are different for gv11b from gp10b. More optimization
will be done as part of NVGPU-484.
Another issue fixed is: gpu va for preemption buffers
still needs to be 8 bit aligned, even though 49 bits
available now. This done because of legacy implementation
of fecs ucode.
Bug 1976694
Change-Id: I284e29e0815d205c150998b07d0757b5089d3267
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1630520
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
Tested-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
During bringup and before nvlink is up GV100 on the DDPX platform operates
with a very, very slow sysmem link. In order to get sysmem test to pass
it is neccesary to significantly increase most timeouts by an order the
magnitude.
Bug 2040544
Change-Id: I26858afde4ae80c70f86b47cfff674b6b00b5bf8
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1627417
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
With a recent rework we moved gk20a_get() call to nvgpu_ioctl_tsg_open(),
but corresponding gk20a_put() call remained in gk20a_tsg_release()
So if a TSG is opened and released from within kernel with APIs
gk20a_tsg_open()/gk20a_tsg_release() we mistakenly drop extra refcount
through gk20a_put()
Fix this by moving gk20a_put() call to nvgpu_ioctl_tsg_release() which
balances gk20a_get() call in nvgpu_ioctl_tsg_open()
Bug 200374011
Change-Id: Id0cec0426e6231309dc530ab5c934dacaba9f8da
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1630969
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In gk20a_ce_create_context(), if gk20a_tsg_open() or gk20a_open_new_channel()
fails, we bail out from the function without setting the error code
This could mislead the caller and report incorrect success
Fix this by setting error code explicitly in failure cases
Bug 200374011
Change-Id: Idf6cba4a57740107bada698295745352f7b5d5ac
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1631506
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In gk20a_ce_delete_gpu_context(), we unbind the channel from TSG and
close the channel. But we do not drop the TSG refcount leaking
the TSG reference
Fix this by explicitly dropping TSG refcount
Also, do not explicitly unbind the channel from TSG
gk20a_channel_close() will internally unbind the channel from TSG
Bug 200374011
Change-Id: Ie4aa32f1d0bff4231f41aa2b33743cdc63e967c7
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1629972
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In gk20a_cde_load(), if TSG allocation fails we bail out the function without
setting the error code and caller of this functions assumes CDE load is
successful
Fix this by setting explicit error code if TSG allocation fails
Bug 200374011
Change-Id: I6e7bcb325fb0062605fa2f696da4abdeb34e241a
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1627117
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In gk20a_cde_remove_ctx(), we unbind the channel from TSG and
close the channel. But we do not drop the TSG refcount leaking
the TSG reference
After allocating sufficient contexts, we see TSG creation fails as below
nvgpu: 17000000.gp10b: gk20a_cde_load:1286 [ERR] cde: could not create TSG
Fix this by explicitly dropping TSG refcount
Also, do not explicitly unbind the channel from TSG
gk20a_channel_close() will internally unbind the channel from TSG
Bug 200374011
Change-Id: If6d75b20d5e03d710c0597d7a320d1157206a2a5
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1627116
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add a field in vm_gk20a to identify guest managed VM, with the
corresponding checks to ensure that there's no kernel section for
guest managed VMs.
Also make the __nvgpu_vm_init function available globally, so that
the vm can be allocated elsewhere, requisite fields set, and passed
to the function to initialize the vm.
Change-Id: Iad841d1b8ff9c894fe9d350dc43d74247e9c5512
Signed-off-by: Sourab Gupta <sourabg@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1617171
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
