clk_pmu_freq_controller_load used the default mask and affected
all the clock frequency controllers (CFC) which had their bits
set in the mask. We wish to enable/disable the CFCs in isolation
through debugfs. So we add a parameter(bit_idx) to the function
which will help affect only one CFC at a time
JIRA DNVGPU-207
DEPENDS ON: <http://git-master/r/1563302>
Change-Id: I233f52158b4a987bcc058a425380983dbe53fac8
Signed-off-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1563303
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This change solves two problems:
(*) the possibility of a crash due to interrupting the gpu
initialization following a bind
(*) a IOVA memory leak that could prevent the GPU from binding after
about 200 bind/unbind cycles
A detailed list of fixes:
- chek that arbiter is initialized before freeing it.
- do not re-enable interrupts when MSI is enabled on unbind.
- free the semaphore sea on unbind.
- ensure we dont double load the vbios.
- check return value of nvgpu_mutex_init for semaphores.
- add corresponding nvgpu_mutex_destroy calls.
bug 1816516
Change-Id: Ia8af73019e0e1183998855d55bb3eea09672a8b7
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1465302
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-by: David Jarrett <djarrett@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1563019
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The following changes are part of the porting of the bind/unbind
functionality.
These changes reuse the shutdown codepaths in iGPU and dGPU and fix a locking
issue with in gk20a_busy() where the usage count can lead to a deadlock during
the driver shutdown. It fixes a racing condition with the gr/mm code by
invalidating the sw ready flag while holding the busy lock
JIRA: EVLR-1739
Change-Id: I62ce47378436b21f447f4cd93388759ed3f9bad1
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1554959
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@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>
Remove gk20a_platform dependencies from gk20a.h. This makes
gk20a_platform a Linux platform specific data structure. Add #include
for platform_gk20a.h in the source files that still depend on Linux.
JIRA NVGPU-16
Change-Id: Ib098accd34a1f5066eb8680c387f9b178169f3f0
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1463547
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Fix below sparse warnings by making function
static or including right header:
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/gp10b/fecs_trace_gp10b.c:45:6: warning: symbol 'gp10b_init_fecs_trace_ops' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/gp106/hal_gp106.c:195:5: warning: symbol 'gp106_init_gpu_characteristics' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/pstate/pstate.c:175:5: warning: symbol 'pstate_construct_super' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/pstate/pstate.c:195:5: warning: symbol 'pstate_construct_3x' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/pstate/pstate.c:204:15: warning: symbol 'pstate_construct' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/pstate/pstate.c:218:5: warning: symbol 'pstate_insert' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/clk/clk_arb.c:1457:6: warning: symbol 'nvgpu_clk_arb_ioctl_event_dev' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/pmgr/pmgr.c:68:5: warning: symbol 'pmgr_pwr_devices_get_power_u64' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/pmgr/pmgr.c:80:5: warning: symbol 'pmgr_pwr_devices_get_current_u64' was not declared. Should it be static?
- $TOP/kernel/nvgpu/drivers/gpu/nvgpu/pmgr/pmgr.c:92:5: warning: symbol 'pmgr_pwr_devices_get_voltage_u64' was not declared. Should it be static?
Bug 200299572
Change-Id: I0112ba3af5b858d2ce2a37a8366dcb6be1eb688d
Signed-off-by: Sachin Nikam <snikam@nvidia.com>
Reviewed-on: http://git-master/r/1482866
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
It is currently possible to set GPCCLK lower than the
minimum allowed frequency.
Clip target GPCCLK/MCLK according to valid min/max range
in arbiter. We could do this before submitting request to
arbiter, but then we would loose information on the
requested target frequency. Instead, we cache the clock
range in arbiter context, and check target frequency when
running arbiter.
Bug 200288036
Change-Id: I29f5176e6365a926d1041430c05a63f0c8447e2b
Reviewed-on: http://git-master/r/1460834
(cherry picked from commit eb626903e4fc046fe1f0eaee703c857e9a0f2b4d)
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1461715
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove use of linux/kernel.h and linux/compiler.h. We don't use
anything in those headers.
Also replace use of linux/bitops.h with new wrapper nvgpu/bitops.h.
JIRA NVGPU-13
Change-Id: Iefa6b4598d5a5e7fc386c0a7a554e778a87010d6
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1460777
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
gk20a_err() and gk20a_warn() require a struct device pointer,
which is not portable across operating systems. The new nvgpu_err()
and nvgpu_warn() macros take struct gk20a pointer. Convert code
to use the more portable macros.
JIRA NVGPU-16
Change-Id: I58bb9e2fb7e5b18f74fbb92b70150cce97968fc3
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1457347
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Replace the last of the Linux kmem API usage with nvgpu kmem
calls instead. Several places are left alone - allocating the
struct gk20a in particular.
Also one function was updated in the clk code to take a struct
gk20a as an argument so that it could use nvgpu_kmalloc().
Bug 1799159
Bug 1823380
Change-Id: I84fc3f8e19c63d6265bac6098dc727d93e3ff613
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1331702
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move the name field from struct gpu_ops up to struct gk20a. The field
is not a function op, so it doesn't belong in gpu_ops.
Replace all uses of dev_name() with use of g->name when possible.
JIRA NVGPU-16
Change-Id: Ic6e99e39258cbf3bb7c806962cbbd7de5126688f
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1328534
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Use the new kmem API functions in clk/*. Also add a struct gk20a
pointer to the following functions:
nvgpu_clk_notification_queue_alloc()
nvgpu_clk_notification_queue_free()
Bug 1799159
Bug 1823380
Change-Id: I7eb67dc443c0bbe0d3f67dac7bf363da60e1051c
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1318316
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
The driver is not properly tearing down the arbiter on the PCI driver
unload. This change makes sure that the workqueues are drained before
tearing down the driver
bug 200277762
JIRA: EVLR-1023
Change-Id: If98fd00e27949ba1569dd26e2af02b75897231a7
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1320147
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
get_rate is already used for call-back that queries the last set
clock rate. This instance of get_rate actually measures the frequency
so renaming it to measure_freq.
At the same time modify to use hertz instead of megahertz. We use
fractional megahertz already in GPU.
Change-Id: I387473d6a6cbf3bb9b9e5a909677a1a725403c32
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1300111
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Remove MCLK and GPCCLK domain aliases, now that userspace
has swithed to new enumerations.
Jira DNVGPU-211
Change-Id: I2af2fd67dbed47088d7161ba0605e13dd7c674a5
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1292609
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Instead of using Linux APIs for mutex and spinlocks
directly, use new APIs defined in <nvgpu/lock.h>
Replace Linux specific mutex/spinlock declaration,
init, lock, unlock APIs with new APIs
e.g
struct mutex is replaced by struct nvgpu_mutex and
mutex_lock() is replaced by nvgpu_mutex_acquire()
And also include <nvgpu/lock.h> instead of including
<linux/mutex.h> and <linux/spinlock.h>
Add explicit nvgpu/lock.h includes to below
files to fix complilation failures.
gk20a/platform_gk20a.h
include/nvgpu/allocator.h
Jira NVGPU-13
Change-Id: I81a05d21ecdbd90c2076a9f0aefd0e40b215bd33
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1293187
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
GPC2CLK has been replaced with GPCCLK on user API.
Remove related definition from kernel API.
GPCLCK and MCLK are currently assigned EQU values in kernel API.
We want to move to a simple enumeration as used in nvrm_gpu.
During the transition, an alias value will be defined for each
clock, and kernel will accept both.
Jira DNVGPU-210
Jira DNVGPU-211
Change-Id: I944fe78be9f810279f7a69964be7cda9b9c8d40d
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1292593
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
If nvgpu_clk_arb_install_fd() gets an error from
nvgpu_clk_notification_queue_alloc(), it fails to free the
nvgpu_clk_dev that it allocated earlier.
Direct the error case to call an appropriate fail label.
Coverity ID 1862040
Change-Id: I1d804d4f5261ec64831938f997f9efc3f2700b60
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1291683
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
The variable indicating the size of the buffer for GPC vf points
was not reset before the query, thus sporadic failures could
happen if the number of available VF points changed on an update
Maximum number of points increased to 256. This is the maximum
that can fit in the boardobj table
bug 200269804
Change-Id: Icb4ae386135a9bb40d4345eb73c5584fecd79147
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1286028
Reviewed-on: http://git-master/r/1287589
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Internally we use GPC2CLK in the arbiter, but we should expose
GPCCLK on kernel API and in user space. Added GPCCLK on the ioctl
API. Arbiter uses GPC2CLK to make queries, then converts to GPCCLK.
Jira DNVGPU-210
Change-Id: Id0b8134d0505c1f9bfd655a08e902bdcd03ebd96
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1280316
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
nvgpu_clk_arb_init_arbiter() allocates master structure arb, and
sub-structures which is assigns as members of arb. At failure,
there's a single error label, and it tries to free the members of
arb without checking that arb was allocated.
Change-Id: Ifac7552b05dad17036835eb3ee624eae351ccb7d
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1279226
GVS: Gerrit_Virtual_Submit
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
nvgpu_clk_arb_install_fd() leaks dev if it cannot create an fd,
and it leaks both dev and fd if it fails to create a file.
Change-Id: I65c03401dba44d88be543d3aec2fa3fcd2fb0dcc
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1279225
GVS: Gerrit_Virtual_Submit
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
- update gp106 pg engine init/list/features HALs
to support MS engine
- Added defines & interface for lpwr tables read from vbios.
- lpwr module which reads idx/gr/ms table from vbios to
map rppg/mscg support with respective p-state
- lpwr module public functions to control lpwr
features enable/disable mscg/rppg & mclk-change
request whenever change in mclk-change parameters
- lpwr public functions to know rppg/mscg support for
requested pstate,
- added mutex t prevent PG transition while arbiter
executes pstate transition
- nvgpu_clk_arb_get_current_pstate() of clk arbiter to
get current pstate
JIRA DNVGPU-71
Change-Id: Ifcd640cc19ef630be1e2a9ba07ec84023d8202a0
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1247553
(cherry picked from commit 8a441dea2410e1b5196ef24e56a7768b6980e46b)
Reviewed-on: http://git-master/r/1270989
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
(1) Adding additional debug in case of VF update failure
(2) The length of the tables must be re-initialized
prior to requesting the vf table update
JIRA: DNVGPU-193
Change-Id: Id5a369359bc5f52ee58da539bfc3ec1ec7887de1
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1252061
(cherry picked from commit dfb6fec02f8e3ff6a22bbea000347923b0306018)
Reviewed-on: http://git-master/r/1274547
Reviewed-by: Automatic_Commit_Validation_User
Tested-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
bug 1845211
clfc is reset during vf switch. it resets delta values stored in
pmu structure. if voltage has not changed, delta calculation happens
on top of corrected voltage causing volt to keep on increasing in cases
where voltage does not change during a vf switch.
Change-Id: I9d1a58b6b7652f22c3a7304162bb8ca6f7d1da6f
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/1266632
(cherry picked from commit 74e2e97d4d149d3eac65b5f65b358b977fba463e)
Reviewed-on: http://git-master/r/1273911
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
JIRA DNVGPU-175
1)Add functions to be called before and after vf change
2)Capture noise unaware vmin value and pass it as param
to vf change functions
3)Before VF change disable CLFC and update noise unware vmin
4)After VF change is done enable CLFC
Change-Id: I4bb59fbe96ec5a792e8930db3ab4a39ec74c9a71
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/1248211
(cherry picked from commit cf07892204d7ce11a0d27ecbc1f5826fbabbde61)
Reviewed-on: http://git-master/r/1270950
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
bug 200254784
If XBAR and SYS clocks for a given GPC clock point is lower
than minimum value mentioned in P state set the floor to
minimum value mentioned in p state. it was set to value
based ratio of a GPC clk value in VF table which can give
value higher than one mentioned in p state. Ignore ratio
and just set to p state value
Change-Id: I9f7cd1d5842d057aff6d8243a31ab503ce35a8ca
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/1257251
Reviewed-by: Automatic_Commit_Validation_User
(cherry picked from commit 5798680286967ff999f674bedd4fc0411615f914)
Reviewed-on: http://git-master/r/1270949
GVS: Gerrit_Virtual_Submit
Modification of the ARBITER clocks to be P-State aware
Up to now the arbiter just considered the whole range
of the GPC and MCLK domains, which could end up on
illegal combinations of MCLK, GPC2CLK, and set the
SYSCLK and XBARCLK domains below their minimum VCO
The following has been implemented:
(1) Modified VF tables to add which PState are
supported on each point.
(2) Return and store the current PState on the
arbiter state.
(3) Modified logic to prevent illegal combinations of
MCLK and GPC2CLK.
(4) Modified logic to prevent setting VF points for
XBAR and SYS domains below VCO limits.
(5) Modified voltage calculation to account for increased
values of XBAR and SYS on some VF points.
(6) Modified arbiter clock target logic to prevent an
application that has not requested a particular VF point
to set target to default targets.
(7) Remove unnecesary mutexes from critical path
JIRA DNVGPU-182
JIRA DNVGPU-183
Change-Id: I3d1c30903278f848681b8da833a867835acc99bb
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1247937
(cherry picked from commit b8bcc07eb3b5b70ec1ee19ace237df99d6170138)
Reviewed-on: http://git-master/r/1268063
Tested-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
The current code can lead to application hang when
opening device on first time if the arbiter fails
to set the clocks
Also it solves a buffer overrun condition in case
the requested frequency is above the maximum range
of the VF curve
bug 1835042
Change-Id: I385401ea27d5cc4bfa41b7ca2eb3a1db53138418
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1245911
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1268061
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Modification of the arbiter to remove all locking
from the arbiter callback and move the callbacks
out of the global queue
Adding modification to call for updated values of
vf table from arbiter init function and on
vf table update
JIRA: DNVGPU-170
Change-Id: I7a7d34c0590522901e06356c06fd8114ebf10f37
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1243212
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/1268009
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
(1) modified counters debug code to export to the driver
(2) modified arbiter to read from those functions
(3) modified counter for higher accuracy on MHz range
JIRA DNVGPU-164
Change-Id: I2bbf7c9be4dc59718d1d91c53028a39020b5aea5
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1239467
GVS: Gerrit_Virtual_Submit
Reviewed-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1268008
