Add sysfs nodes to manage power of dGPU. Writing
pci dev name to poweroff/poweron sysfs node powers
off/on dGPU.
The format of pci dev name is DDDD:BB:DD.F i.e.
domain:bus:device.function
echo 0001:01:00.0 > /sys/bus/pci/drivers/nvgpu/poweroff
echo 0001:01:00.0 > /sys/bus/pci/drivers/nvgpu/poweron
The permissions of nodes are set such that only root
user can write to the sysfs node to control dGPU power
state.
JIRA NVGPU-1100
Change-Id: I904881cab58c5f553e94510a3a10000194238433
Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1749848
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The power rail of dGPU is managed with help of a set of
GPIOs. Using those GPIOs add an interface to power off and
power on dGPU.
Before dGPU is powered off, new work is blocked by setting
NVGPU_DRIVER_IS_DYING and current jobs are allowed to finish
by waiting for gpu to be idle.
The tegra PCIe controller driver provided APIs
tegra_pcie_attach_controller() and tegra_pcie_detach_controller()
are used to manage PCIe link shutdown, PCIe refclk management
and PCIe rescan.
JIRA NVGPU-1100
Change-Id: Ifae5b81535f40dceca5292a987d3daf6984f3210
Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1749847
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
We right now acquire rulist_submit_mutex to submit runlist and also
to wait for submit completion
But locking is only needed to atomically configure the runlist submit
registers, hence move the locking to inside of
gk20a_fifo_runlist_hw_submit() where we program the registers
Also convert the mutex to spinlock at the same time
Note that similar locking is not required for
tu104_fifo_runlist_hw_submit() since the runlist submit registers
are per-runlist beginning Turing
Bug 200452543
Change-Id: I53d6179b80cb066466b64c6efa9393e55e381bfc
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1919058
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-misra-checker <svc-misra-checker@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>
The POSIX code does not need to be MISRA complient but any macro
code in the POSIX stuff does get checked by nature of the scanner.
Thus we get a lot of false positives that are annoying.
This change fixes a couple of issues in the BUG() and WARN()
macros: '__' prefixes, missing '{}' in if-conditions, and using
a non-boolean in boolean context.
Change-Id: I064b90c2088ef4ea5093ed456241a98f166008ac
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1816681
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Philip Elcan <pelcan@nvidia.com>
Reviewed-by: Scott Long <scottl@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add Turing specific common, unit, hardware header files
Make all the Makefile and Makefile.sources changes to compile
all Turing specific code
Bug 200454999
Change-Id: I62ebff5c078b4b8817fc83ea0e4ee3cfffe668dc
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1917983
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
We right now submit new runlist and wait for submit to complete in
gk20a_fifo_update_runlist_locked()
It is possible that multiple runlists are being updated in parallel
by multiple threads since the lock taken by parent of
gk20a_fifo_update_runlist_locked() is per-runlist
Note that the concurrent threads would still construct their runlists
into per-runlist buffer
But we still have a race condition while submitting these runlists
to hardware.
With an application that creates and destroys multiple contexts in
parallel this race condition gets realized and we see h/w reporting
an error interrupt NV_PFIFO_INTR_SCHED_ERROR_CODE_BAD_TSG which means
a bad TSG was submitted
Fix this by adding a global lock for runlist submit and wait sequence
This ensures that concurrent threads do not try to submit runlists
to the hardware at the same time
Bug 200452543
Bug 2405416
Change-Id: I2660a2e5d9af1da400e7f865361722dc0914f96f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1851114
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-misra-checker <svc-misra-checker@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>
-Call secured_sec2_start() to start SEC2 RTOS ucode execution
on SEC2 falcon in nvgpu_init_sec2_support() function
-Modified nvgpu_init_pmu_support() to do PMU bootstrap
from SEC2 RTOS by sending command.
-Added function nvgpu_sec2_bootstrap_ls_falcons() to
bootstrap LS falcon by taking falcon id as a parameter &
sending request to SEC2 RTOS with command
NV_SEC2_ACR_CMD_ID_BOOTSTRAP_FALCON.
-Modified method gr_gm20b_load_ctxsw_ucode() to
bootstrap FECS & GPCCS falcons using SEC2 RTOS
in cold boot & recovery path.
-Updated ldr_cfg parameters for SEC2 falcon
-Skip adding PMU ucode details to non-wpr blob preparation
to skip supporting of LS PMU falcon bootstrap.
JIRA NVGPUT-85
Change-Id: I5f6828e2737e247767814014801671327bb34a4e
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1832363
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 sec2_ipc.c to support SEC2 IPC.
-Defined nvgpu_sec2_cmd_post() to send command
to SEC2 RTOS from nvgpu along with dependent
methods like seq acquire/release, validate &
write cmd.
-Defined nvgpu_sec2_process_message() to
process message from SEC2 RTOS & route
to correct handler based on flag.
-Method sec2_process_init_msg() helps fetch
parameters sent from SEC2 RTOS to setup
queue, debug buffer as parameters.
-Created sec2 ops under gops to access
sec2 engine specific HALs.
-Defined nvgpu_sec2_queue_init() init
command & message for SEC2 RTOS using
common falcon queue.
-Made Makefile changes to include sec2_ipc.c for build
JIRA NVGPUT-82
Change-Id: I6e4c2d6ec71aa61a543f34680d1412167c9a8cc6
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1828034
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add separate unit for perfbuf in common/perf/perfbuf.c which does not need to
include any h/w file. This unit will utilize HALs exported by
perf_*.c units for h/w accesses.
Add corresponding header file at include/nvgpu/perfbuf.h
Add new HAL gops.perfbuf with below operations :
gops.perfbuf.perfbuf_enable()
gops.perfbuf.perfbuf_disable()
Remove below debug session specific HALs
gops.dbg_session_ops.perfbuffer_enable()
gops.dbg_session_ops.perfbuffer_disable()
Delete file gv11b/dbg_gpu_gv11b.c since it is no longer needed now as it was
only including perfbuf sequence
Also remove perfbuf sequences from gk20a/dbg_gpu_gk20a.c
Jira NVGPU-1102
Change-Id: I57b87c9f0dcd85784f8002bc92728b6d78a68d98
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1819303
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add separate unit for perf under common/perf/ to provide accesses to h/w
unit hw_perf_*_.c
Implement below HALs in gm20b and gv11b specific h/w files and set them to
appropriate chips
gops.perf.enable_membuf()
gops.perf.disable_membuf()
gops.perf.membuf_reset_streaming()
gops.perf.get_membuf_pending_bytes()
gops.perf.set_membuf_handled_bytes()
gops.perf.get_membuf_overflow_status()
Jira NVGPU-1102
Change-Id: I161990fdb7283f33c0fb2ab6a8051f4bfc3bb181
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1819302
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>
