The context switch timeout works by triggering a hardware timeout at 10
Hz. When handling these, we check whether a channel has actually timed
out. Currently the timeout limit can be shorter than the 10 Hz interval
which always causes us to recover a channel but would also cause
detection of progress if there was any in the interval.
Handling both situations at the same time would reuse the channel
pointer local to the function after a loop has finished and would cause
memory corruption. Fix this by making the two branches mutually
exclusive, and move the recover case to happen first because that's how
our tests assume things to work.
Jira NVGPU-967
Bug 2502074
Change-Id: I26aa0fa7fd80ab42a9a1a93a6cca2cd29c9d3f3f
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1932449
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
(cherry picked from commit 8ac9a53d816a3d012a6948a9a96ac6db699c662di
in dev-kernel)
Reviewed-on: https://git-master.nvidia.com/r/1997597
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Bibek Basu <bbasu@nvidia.com>
Tested-by: Bibek Basu <bbasu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- In vGPU code path, function vgpu_channel_abort_cleanup() does not
obtain channel reference before using the channel structure
(channel_gk20a)
- vgpu_channel_abort_cleanup() is called by vgpu_intr_thread() which
runs commands obtained from interrupt queue from RM server.
- If there is a scenario where gk20a_channel_release() function runs
before guest receives notification from RM server to abort channel
cleanup, channel gets freed before vgpu_channel_abort_cleanup() runs.
- However, because vgpu_channel_abort_cleanup() does not take explicit
reference to the channel, it ends up accessing structures
(such as ch->g) which are set to NULL and thus we end up in a crash.
- This patch explicitly takes reference of channel before
vgpu_channel_abort_cleanup() is called.
- If gk20a_channel_release() runs before vgpu_channel_abort_cleanup()
and ends up freeing channel, we dont get reference to freed
channel in vgpu_channel_abort_cleanup() and thus we return from
function rather than continuing with freed channel as was the case
previously.
Bug 200453473
JIRA EVLR-3411
Change-Id: I311043b2231336616b28246531cf8a0dc151b0cd
Signed-off-by: Deepak Bhosale <dbhosale@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1932028
(cherry picked from commit b91228e506)
Reviewed-on: https://git-master.nvidia.com/r/1970807
Reviewed-by: Aparna Das <aparnad@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Tested-by: Karl Ding <kding@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Nirav Patel <nipatel@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This change adds RDMA supports for tegra iGPU.
1. Cuda Process allocates the memory and passes
the VA and size to the custom kernel driver.
2. The custom kernel driver maps the user allocated
buf and does the DMA to/from it.
3. Only supports iGPU + cudaHostAlloc sysmem
4. Works only for a given process.
5. Address should be sysmem page aligned and size should
be multiple of sysmem page size.
6. The custom kernel driver must register a free_callback when get_page()
function is called.
Bug 200438879
Signed-off-by: Preetham Chandru R <pchandru@nvidia.com>
Change-Id: I43ec45734eb46d30341d0701550206c16e051106
Reviewed-on: https://git-master.nvidia.com/r/1953780
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Bibek Basu <bbasu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Instead of using num_inflight_jobs to determine whether to pre-alloc
resources for a channel use the c->deterministic flag and the
number of inflight jobs field. Non-determinsitic channels do not
require pre-alloced resources and deterministic channels with 0
in flight jobs (i.e no kernel job tracking, AKA fast path sumits)
also do not require pre-alloced resources.
Bug 2327792
Change-Id: I7e8eb0478c22e005ca2c46c555415afa0ded0be1
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1850123
(cherry picked from commit 05ec7b80eb)
Reviewed-on: https://git-master.nvidia.com/r/1949219
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: James Norton <jnorton@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add a reboot handler to make sure that nvgpu does not try to busy
the GPU if the system is going down. If the system is going down
then any number of subsystems nvgpu depends on may already have
been deinitialized.
Bug 200333709
Bug 200454316
Change-Id: I2ceaf7ca4fb88643310874b5b26937ef44c6e3dd
Signed-off-by: Kary Jin <karyj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1927018
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vinayak Pane <vpane@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
When turning off CONFIG_DEBUG_FS, there are build errors:
drivers/gpu/nvgpu/os/linux/os_ops_gp106.o: In function `nvgpu_fecs_trace_init_debugfs':
os_ops_gp106.c:(.text+0x8): multiple definition of `nvgpu_fecs_trace_init_debugfs'
drivers/gpu/nvgpu/os/linux/os_ops_gp10b.o:os_ops_gp10b.c:(.text+0x0): first defined here
drivers/gpu/nvgpu/os/linux/os_ops_gv100.o: In function `gp106_therm_init_debugfs':
os_ops_gv100.c:(.text+0x0): multiple definition of `gp106_therm_init_debugfs'
drivers/gpu/nvgpu/os/linux/os_ops_gp106.o:os_ops_gp106.c:(.text+0x0): first defined here
drivers/gpu/nvgpu/os/linux/os_ops_tu104.o: In function `gv100_clk_init_debugfs':
os_ops_tu104.c:(.text+0x0): multiple definition of `gv100_clk_init_debugfs'
drivers/gpu/nvgpu/os/linux/os_ops_gv100.o:os_ops_gv100.c:(.text+0x10): first defined here
This is because those functions aren't marked as static.
So this patch just simply fixes the bug.
Bug 2284925
Change-Id: I1da39345c653dfb50c509adb0c822b4657646c56
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1929355
(cherry picked from commit 0fd9c84f87)
Reviewed-on: https://git-master.nvidia.com/r/1933889
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vinayak Pane <vpane@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The PMM type-specific broadcast->unicast expansion calculation
was using incorrect values. This caused the invalid register
accesses to be generated.
This change HAL-ifies the values, so that the expansion will be
performed correctly.
Bug 200454109
Change-Id: I96c15de27b5e16e4db2e788fd98e6bf7d6e7d564
Signed-off-by: Matthew Braun <matthewb@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1921717
GVS: Gerrit_Virtual_Submit
Reviewed-by: Deepak Nibade <dnibade@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>
gops.fb.dump_vpr_wpr_info() accesses both VPR and WPR registers.
Split this into two different HALs gops.fb.dump_vpr_info() and
gops.fb.dump_wpr_info()
Also unset HALs accessing VPR registers on dGPUs
We don't support VPR on dGPUs
Remove fb_mmu_vpr_info_r() register and all its accessors from
dGPU headers
Bug 2173122
Change-Id: I5b2712f8c5389e422a84c375a7e836add48bfd1c
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1850947
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
We don't support big page size beginning Pascal, so set HAL
gops.fb.set_mmu_page_size() to NULL on all those platforms
Also remove these accessors from corresponding platforms
fb_mmu_ctrl_use_pdb_big_page_size_v()
fb_mmu_ctrl_use_pdb_big_page_size_true_f()
fb_mmu_ctrl_use_pdb_big_page_size_false_f()
Bug 2173122
Change-Id: I7353412860a7a6f8a993ca9184a0dc3ca9d749af
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1850946
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add support for the measure_freq clock op for igpu:
- add nvgpu_clk_measure_freq(), which in turn calls
the get_rate() clock op.
- Initialize the measure_freq clock op to nvgpu_clk_measure_freq()
for native linux and vgpu.
JIRA ESRM-398
Change-Id: I8a3b2ee79e29e3491a16f55281494f05cd841b07
Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1850585
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Nirav Patel <nipatel@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
PMU ucode is updated to use acrlib from t19xbringup
branch.
We are seeing build issues due to incompatibility
with acrlib from tegra_acr branch.
CTX_DMA aperture to be used for loading LS falcons
needed update in the local acrlib.
Bug 2400729.
Change-Id: Iad00a332acfac307c389bde504893a87abaf7460
Signed-off-by: Deepak <dgoyal@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1849182
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
-Created struct nvgpu_sec2 to hold members
related to SEC2-RTOS ucode support in header file
sec2.h
-Created nvgpu_sec2 variable under struct gk20a.
-Created NVGPU_SUPPORT_SEC2_RTOS enable flag
to enable SEC2 RTOS support.
-Defined method nvgpu_init_sec2_support() to
init SEC2 RTOS support by performing s/w setup like
mutex-init, sequence-init & add support
for remove_support.
-Defined method nvgpu_sec2_destroy() to deinit
SEC2 RTOS support.
-Added nvgpu_init_sec2_support()/nvgpu_sec2_destroy()
as part gk20a_finalize_poweron()/gk20a_prepare_poweroff()
sequence based on NVGPU_SUPPORT_SEC2_RTOS enable flag
-Assigned g->sec2->flcn to point to g->sec2_flcn to access
falcon.
-Made Makefile changes to include sec2.c to build
JIRA NVGPUT-80
Change-Id: Icdc8c25994e305427ad465a5a20e9ce533759a9e
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1791955
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
-Created command/message nv_flcn_cmd/msg_sec2
data struct to communicate between nvgpu<->sec2-rtos
in header file sec2_cmd_if.h
-Created acr command/message nv_sec2_acr_cmd/msg
to perform operation like bootstrap LSF flacon
in header file sec2_if_acr.h
-Created defines common SEC2 defines to use across
multiple operation related to SEC2-RTOS in header file
sec2_if_cmn.h
-Created data struct sec2_init_msg_sec2_init to receive
message from SEC2-RTOS to init queues, debug
data in header file sec2_if_sec2.h
JIRA NVGPUT-81
Change-Id: I4efbca20de7a2483d17de97841ada5336189e2b8
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1827806
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
All chips were currently using gm20b_gr_clear_sm_error_state
It was wrong for chips based on volta and later as the implementation didn't
consider non pes-aware vsms mapping
Add new HAL implementation for clear_sm_error_state for volta based and later
chips to fix this.
Bug 200448172
Change-Id: I65988c8cbb35d13089ac628e8333d9a3b58e0eb1
Signed-off-by: Anup Mahindre <amahindre@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1837188
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
1. Implement the following vgpu functions to support clk-arb:
- vgpu_clk_get_range() to return min and max freqs from
supported frequencies
- implement vgpu_clk_get_round_rate() which sets rounded
rate to input rate. Rounding is handled in RM Server
- modify vgpu_clk_get_freqs() to retrieve freq table in IVM
memory instead of copying the value in array as part of cmd
message.
2. Add support for clk-arb related HALs for vgpu.
3. support_clk_freq_controller is assigned true for vgpu
provided guest VM has the privilege to set clock frequency.
Bug 200422845
Bug 2363882
Jira EVLR-3254
Change-Id: I91fc392db381c5db1d52b19d45ec0481fdc27554
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1812379
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Nvgpu uses many ways to check if sync points are enabled. The four
ways used to be:
platform->has_syncpoints
g->has_syncpoints
nvgpu_is_enabled(g, NVPGU_HAS_SYNCPOINTS)
gk20a_platform_has_syncpoints()
This patch standardizes all usage to now be nvgpu_has_syncpoints()
which is based on gk20a_platform_has_syncpoints() - just renamed to
be general to nvgpu.
All usage of the other forms have now been consolidated. However,
under the hood nvgpu_has_syncpoints() does check the is_enabled
flag. This flag is now set where g->has_syncpoints used to be set
based on the platform data.
The basic dependency chain is this:
nvgpu_has_syncpoints -> NVGPU_HAS_SYNCPOINTS ->
platform->has_syncpoints
However, note: there are several places where syncpoints can be
disabled if some other driver initialization fails (for ex. host1x).
Also note that nvgpu_has_syncpoints() also considers a disable
variable set by debugfs.
Bug 2327574
Change-Id: Ia2375a80f5f2e27285e6175568dd13e6bb25fd33
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1803975
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Disable ELCG as it is not POR for GV100
Disable in Platform data for SKU250
Bug 200446261
Change-Id: I70bddf450c7e41e91498c613f315e0c82ac5e8e2
Signed-off-by: absalam <absalam@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1828022
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
-Removed _dmem postfix to some functions which
can be common for DMEM & EMEM queue, and
made changes as needed.
-Defined flcn_queue_push_emem() &
flcn_queue_pop_emem() functions to
to read/write queue data to/from EMEM
-Defined flcn_queue_init_emem_queue()
function to assign EMEM specific functions
to support EMEM queue type.
-Defined QUEUE_TYPE_DMEM to support
DMEM based queue.
-Defined QUEUE_TYPE_EMEM to support
EMEM based queue.
-Modified nvgpu_flcn_queue_init() to call queue
type flcn_queue_init_dmem/emem_queue()
function to assign its ops.
JIRA NVGPU-1161
Change-Id: I06333fa318b7ca4137c977ad63f5a857e7b36cc8
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1841084
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
-Added HAL copy_from_emem & copy_to_emem to struct
nvgpu_falcon_engine_dependency_ops data struct to point to
engine specific EMEM access functions.
-Added function nvgpu_flcn_copy_from_emem() &
nvgpu_flcn_copy_to_emem() at interface layer to
access EMEM using flacon engine EMEM HAL's.
JIRA NVGPU-1161
Change-Id: Ifb72a617277e73f25f1772c969791b642585e7fb
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1807336
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
MISRA Rule 10.4 only allows the usage of arithmetic operations on
operands of the same essential type category.
Adding "U" at the end of the integer literals to have same type of
operands when an arithmetic operation is performed.
This fixes violation where an arithmetic operation is performed on
signed and unsigned int types.
JIRA NVGPU-992
Change-Id: Ic434301441bf43f9eaff43500afb696e4e1395ae
Signed-off-by: Sai Nikhil <snikhil@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1819014
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: Adeel Raza <araza@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
MISRA Rule 10.4 only allows the usage of arithmetic operations on
operands of the same essential type category.
Adding "U" at the end of the integer literals to have same type of
operands when an arithmetic operation is performed.
This fixes violation where an arithmetic operation is performed on
signed and unsigned int types.
JIRA NVGPU-992
Change-Id: Id3b2c8ea1af1807087468c6978abfbfc85bee2ec
Signed-off-by: Sai Nikhil <snikhil@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1809757
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Adeel Raza <araza@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
MISRA rule 21.2 doesn't allow the use of macro names which start with
an underscore. These leading underscores are to be removed from the
macro names. This patch will fix such violations in the
include directory by renaming them to follow the convention,
'NVGPU_HEADER_H'.
JIRA NVGPU-1028
Change-Id: I0289a168252595d17ac47c5ed32cabc4eea33e25
Signed-off-by: smadhavan <smadhavan@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1809755
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Adeel Raza <araza@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
