-Add sm input param for handle_sm_exception and
pre_process_sm_exception for gr ops/functions.
-Add functions to calculate gpc and tpc reg offsets.
-Add function to find SMs which raised SM exception.
JIRA GPUT19X-75
Change-Id: I257e7342ddabadb1556c9551c50a54d34b0f9d1e
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master/r/1476108
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: David Martinez Nieto <dmartineznie@nvidia.com>
Remove dependency for nvgpu to invoke devfreq govenor on every
gk20a_busy/idle() call. This dependency was originally necessary to
track GPU load (busy vs idle) in software. However, since we currently
read the load GPU from HW/PMU there is no need to invoke the devfreq
governor in this path. Instead it can use timer-based polling.
Jira NVGPU-20
Change-Id: Id09f89a8a562ed49164a2e06dcbb901e4a46e7d5
Signed-off-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-on: https://git-master/r/1473140
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Add vgpu support for ModeE perfbuffers
- VM allocation is handled by the kernel, with final mapping
handled by the RM server
- Enabling/disabling the perfbuffer is handled by the RM server
Bug 1880196
JIRA EVLR-1074
Change-Id: Ifbeb5ede6b07e2e112b930c602c22b66a58ac920
Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com>
Reviewed-on: https://git-master/r/1506747
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reorganize HAL initialization to remove inheritance and construct
the gpu_ops struct at compile time. This patch only covers the ltc
sub-module of the gpu_ops struct.
Perform HAL function assignments in hal_gxxxx.c through the
population of a chip-specific copy of gpu_ops.
Jira NVGPU-74
Change-Id: I1110e301e57b502cf7f97e6739424cb33cc52a69
Signed-off-by: Sunny He <suhe@nvidia.com>
Reviewed-on: https://git-master/r/1507564
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove ltc_common.c and integrate the included functions
into device specific ltc_gXXXX.c files. Merge non-device reg
definition dependent ltc functions into ltc_gk20a.c/h.
Prior to this patch, ltc_common.c was being directly included
into the device specific ltc source files as a workaround to
allow different devices to share the same code but still include
in different hw reg definitions.
Given that this approach was not adopted for other
systems, this code has been separated out for readability and
consistency.
Jira NVGPU-74
Change-Id: I4eea301927418532cc150b029535f165928cab89
Signed-off-by: Sunny He <suhe@nvidia.com>
Reviewed-on: https://git-master/r/1507502
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
- set nvgpu_flcn_reset() to point to gk20a_pmu_reset()
- set PMU interrupt using nvgpu_flcn_enable_irq()
- replace pmu_idle with nvgpu_flcn_wait_idle()
JIRA NVGPU-57
Change-Id: I50d0310ae78ad266da3c1e662f1598d61ff7abb6
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1469478
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- Added flacon reset dependent interface & HAL
methods to perform falcon reset.
- method to wait for idle
- method to reset falcon
- method to set irq
- method to read status of CPU
- Updated falcon ops pointer to point gk20a
falcon HAL methods
- Added members to know support of falcon
& interrupt.
- Added falcon dependency ops member to support
flacon speicifc methods
JIRA NVGPU-99
JIRA NVGPU-101
Change-Id: I411477e5696a61ee73caebfdab625763b522c255
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1469453
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reorder non-function pointer members of gpu_ops to be at the
very end of their respective sub-structs. This allows for
easier debug interpretation and slightly improves readability.
Jira NVGPU-107
Change-Id: Ife3279180306de70f7fad6760f616c6d69769b36
Signed-off-by: Sunny He <suhe@nvidia.com>
Reviewed-on: http://git-master/r/1506591
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
linux/version.h and linux/sched.h are not used by gk20a.h, so remove
them.
acr_gm20b.h and bus_gk20a.h are not needed by gk20a.h, so remove them.
pmu_gp106.c relies on implicit #include of acr_gm20b.h by gk20a.h, so
add that as an explicit #include.
Remove #include of iomap.h. platform_gk20a_tegra.c legacy rail gating
code still relies on access to that header, so add it as explicit
include.
JIRA NVGPU-38
Change-Id: I1cf57b9d3a7ee5e3cad298341107e317b4b8662f
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1505926
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
When contexts are unloaded from GR, the valid bit is reset
but the instance pointer information remains intact.
Check valid bit in *is_channel_ctx_resident* function as
valid bit might not be set when *get_channel_from_ctx function*
is called from gr_isr
Bug 200289491
Change-Id: I4da7f04794c7e7e80b511756dbd851205cd76fbc
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: http://git-master/r/1505908
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
VBIOS memory settings have been updated for PG419, significantly
modifying MCLK switching sequences. This change adds support for
PG419 tables, while remaining backward compatible with PG418.
Bug 1921082
JIRA EVLR-1269
Change-Id: Ia8a1f8b3f482e348a46f0acb540af23287d9c11e
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1484110
(cherry picked from commit c2444ae89caf97da2702e8486cc8fb162b4f50b1)
Reviewed-on: http://git-master/r/1485300
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Always check for valid channel gr_ctx before issuing channel
preempt. Commands like "echo > /dev/nvhost-gpu" create channel
to just power-up gpu without any valid channel context. So
don't try to preempt those channels.
Bug 1937331
Change-Id: I48a4bfd35728b83b27eb968e51a56b900d1fa799
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1505783
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Remove pointer to struct device from gk20a_gpu_ctx. The pointer is
not used anywhere, and it adds an unnecessary Linux dependency.
JIRA NVGPU-38
Change-Id: Id5843a21e4809ca840e4f5d561728f859bbd964e
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1505202
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
GVS: Gerrit_Virtual_Submit
Pass struct gk20a pointer to gk20a_busy_noresume() and
gk20a_idle_nosuspend(). This reduces the number of dependencies to
Linux specific struct device.
JIRA NVGPU-38
Change-Id: I5e05be32e2376bc8be5402bb973c20e28c35a1c3
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1505177
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Delete a version of WRITE_ONCE() that gk20a.h defines only for
kernels older than 3.18. We don't support kernels below 4.4.
JIRA NVGPU-38
Change-Id: I0af50936523fde9929c21eea0547b91dac4a0081
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1505175
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
GVS: Gerrit_Virtual_Submit
The function tsg_gk20a_from_ch() is an operation on tsg_gk20a
structure, so move it to be part of tsg_gk20a.c and export
via tsg_gk20a.h.
JIRA NVGPU-38
Change-Id: I2afba3533ac829088a5edf8b16cf4e071b69b77a
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1505172
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
GVS: Gerrit_Virtual_Submit
Add devfreq governor support in order to allow frequency scaling
in virtualization config. GPU clock frequency operations are
re-directed to the server over RPC.
Bug 200237433
Change-Id: I1c8e565a4fff36d3456dc72ebb20795b7822650e
Signed-off-by: Sachit Kadle <skadle@nvidia.com>
Reviewed-on: http://git-master/r/1295542
(cherry picked from commit d5c956fc06697eda3829c67cb22987e538213b29)
Reviewed-on: http://git-master/r/1280968
(cherry picked from commit 25e2b3cf7cb5559a6849c0024d42c157564a9be2)
Reviewed-on: http://git-master/r/1321835
(cherry picked from commit f871b52fd3)
Reviewed-on: http://git-master/r/1313468
Tested-by: Aparna Das <aparnad@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
GVS: Gerrit_Virtual_Submit
Remove the two other unnecessary options based on jiffies and
gettimeofday, leaving only the time stamp counter clocksource.
Jira NVGPU-83
Change-Id: I289951aba832eda36cb9cb68b7e41e6061ec3a03
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1503000
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
In order to perform timestamps correlation for FECS
traces, we need to collect GPU / GPU timestamps
samples. In virtualization case, it is possible for
a guest to get GPU timestamps by using read_ptimer.
However, if the CPU timestamp is read on guest side,
and the GPU timestamp is read on vm-server side,
then it introduces some latency that will create an
artificial offset for GPU timestamps (~2 us in
average). For better CPU / GPU timestamps correlation,
Added a command to collect all timestamps on vm-server
side.
Bug 1900475
Change-Id: Idfdc6ae4c16c501dc5e00053a5b75932c55148d6
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1472447
(cherry picked from commit 56f56b5cd9)
Reviewed-on: http://git-master/r/1489183
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove <soc/tegra/fuse.h> includes and include
<nvgpu/fuse.h> header to remove direct dependency
on platform specific header
Use specific APIs like below to read/write fuses
nvgpu_tegra_fuse_write_bypass()
nvgpu_tegra_fuse_write_opt_gpu_tpc0_disable()
Remove old code which was compiled for kernel versions
less than 4.4 since we support only k4.4 and greater
versions now
Jira NVGPU-75
Change-Id: Iddd8e1a8da7effbce2aff217e8e25f7de04962d6
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1497518
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Bharat Nihalani <bnihalani@nvidia.com>
To make do_idle work when nvgpu is built as a module, reverse the order
of call dependencies for do_idle. Don't provide visible
gk20a_do_{idle,unidle}() functions for the kernel but instead call the
kernel for registering and unregistering pointers to them when the
driver loads and unloads.
Refactor the internal __gk20a_do_{idle,unidle} functions to take a
struct gk20a * instead of struct device *, and use the callback api for
providing that g instead of retrieving the plat device from device tree.
Bug 200290850
Change-Id: Ibef8b069302e547b298069cbb97734f461a10cc3
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1493774
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
To support deterministic channels even with platforms where railgating
is supported, have each deterministic-marked channel hold a power
reference during their lifetime, and skip taking power refs for jobs in
submit path for those.
Previously, railgating blocked deterministic submits in general because
of gk20a_busy()/gk20a_idle() calls in submit path possibly taking time
and more significantly because the gpu may need turning on which takes a
nondeterministic and long amount of time.
As an exception, gk20a_do_idle() can still block deterministic submits
until gk20a_do_unidle() is called. Add a rwsem to guard this. VPR resize
needs do_idle, which conflicts with deterministic channels' requirement
to keep the GPU on. This is documented in the ioctl header now.
Make NVGPU_GPU_FLAGS_SUPPORT_DETERMINISTIC_SUBMIT_NO_JOBTRACKING always
set in the gpu characteristics now that it's supported. The only thing
left now blocking NVGPU_GPU_FLAGS_SUPPORT_DETERMINISTIC_SUBMIT_FULL is
the sync framework.
Make the channel debug dump show which channels are deterministic.
Bug 200291300
Jira NVGPU-70
Change-Id: I47b6f3a8517cd6e4255f6ca2855e3dd912e4f5f3
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1483038
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- moved pg related code to pmu_pg.c under common/pmu folder
PG state machine support methods
PG ACK handlers
AELPG methods
PG enable/disable methods
-prepended with nvgpu_ for elpg/aelpg global methods
by replacing gk20a_
JIRA NVGPU-97
Change-Id: I2148a69ff86b5c5d43c521ff6e241db84afafd82
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1498363
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- Moved pmu f/w related support from pmu_gk20a.c
to "drivers/gpu/nvgpu/common/pmu/pmu_fw.c" file
- Prepended with nvgpu_ for global functions & replaced
wherever used
- Moved below list related to PMU f/w
init/remove,
PMU version specific ops,
non-secure ucode blob prepare,
JIRA NVGPU-56
Change-Id: Ifdad8c560bd233e98728717d5868119e9d8e8d90
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1480636
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
