Remove nvgpu_gpuid_t18x.h since this file is now visible. Migrate
the relevant definitions and defines into their expected places and
make the code use the real defines. No longer is hiding t18x specific
stuff necessary.
Bug 1799159
Change-Id: I47fa2392e46fdb7aacc70aeb0cc8c3f5ca0dc22f
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1300976
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Added fecs trace characteristic flag to vgpu to determine for
platform support
Also moved fecs flag from ctxsw init to fecs init for native linux.
This makes flag init uniform across both platforms.
JIRA EVLR-993
Change-Id: Id62f31954cb5d7028ef01a199548f5f908b51eb0
Signed-off-by: Vishnu Reddy Mandalapu <vmandalapu@nvidia.com>
Reviewed-on: http://git-master/r/1305045
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Implement a worker thread to replace the delayed works in channel
watchdog and job cleanups. Watchdog runs by polling the channel states
periodically, and job cleanup is performed on channels that are appended
on a work queue consumed by the worker thread. Handling both of these
two in the same thread makes it impossible for them to cause a deadlock,
as has previously happened.
The watchdog takes references to channels during checking and possibly
recovering channels. Jobs in the cleanup queue have an additional
reference taken which is released after the channel is processed. The
worker is woken up from periodic sleep when channels are added to the
queue.
Currently, the queue is only used for job cleanups, but it is extendable
for other per-channel works too. The worker can also process other
periodic actions dependent on channels.
Neither the semantics of timeout handling or of job cleanups are yet
significantly changed - this patch only serializes them into one
background thread.
Each job that needs cleanup is tracked and holds a reference to its
channel and a power reference, and timeouts can only be processed on
channels that are tracked, so the thread will always be idle if the
system is going to be suspended, so there is currently no need to
explicitly suspend or stop it.
Bug 1848834
Bug 1851689
Bug 1814773
Bug 200270332
Jira NVGPU-21
Change-Id: I355101802f50841ea9bd8042a017f91c931d2dc7
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1297183
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
fifo_pbdma_status__size_1_v() and fifo_engine_status__size_1_v()
are not same for all gpus. Use litter value to calculate chip
specific fifo*status__size_1(v)
JIRA GV11B-45
Change-Id: I3d3d45bf79d15e14739fcc18cb1ca987669d5c11
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: http://git-master/r/1312688
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
In gk20a_vm_map_duplicate_locked(), we always do a linear search
in rb-tree to find a duplicate entry of the buffer
In case NVGPU_AS_MAP_BUFFER_FLAGS_FIXED_OFFSET is set, we first
traverse whole rb-tree linearly and then compare offset_align
with the address searched from rb-tree
If size of rb-tree is very large this linear lookup takes upto
7mS and causes huge delays
Hence in case of NVGPU_AS_MAP_BUFFER_FLAGS_FIXED_OFFSET, we can
use offset_align to perform a binary search on rb-tree and then
verify that dmabuf and kind match with the node obtained from
the search
This saves a lot of time per-lookup
Bug 1874516
Change-Id: Ia4924b64d66e586c14341ae2e2283beac394bf6f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1309343
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@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>
-Moved ACR interface headers from acr_gm20b.h/acr_gp106.h to
Its specific header files under drivers/gpu/nvgpu/include/nvgpu/acr/
Folder.
- nvgpu_acr.h - Top-level header-file which include ACR interfaces
headers & defines required to communicate with ACR, including this
header file is good to get access into ACR interface & made changes
accordingly,
-Deleted acr.h & acr_t18x.h as not required anymore
& removed its include from dependent files.
Jira NVGPU-19
Change-Id: Ie404043cfe1ab32404eb63a43831f470d8436324
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1304748
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
API DEFINE_MUTEX() is defined in Linux and might
not be available in other OSs.
Hence remove its usage from nvgpu
Declare and explicitly initialize below mutexes
for both nvgpu and vgpu
g->mm.priv_lock
g->mm.tlb_lock
Jira NVGPU-13
Change-Id: If72885a6da0227a1552303206172f1f2b751471d
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1298042
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@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>
mutex_is_locked() API is defined on Linux only
and not on other OS like QNX.
Hence remove use of this API for OS abstraction
support to nvgpu.
Instead of using mutex_is_locked(), use
mutex_trylock() for same purpose
Jira NVGPU-13
Change-Id: I542daf20a2294153da8e8bfe89e0dc0387297523
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1297184
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In the PCI init/de-init code only disable IRQs if they were enabled.
The enable happens in the common power_on code. The PCI routines could
both be called without the common power_on code being called which
causes an extra disable to happen.
Bug 200275531
Change-Id: I43a8a9881f1e9ae254bf36230f29849df074657f
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1301701
(cherry picked from commit cca70e9adccee1ef65a0a6d95a4494fc87500c17)
Reviewed-on: http://git-master/r/1298954
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Commit 7e403974d3 ("gpu: nvgpu: Simplify
ref-counting on VMs") accidentally broke the CE context creation while
moving away from direct ch->vm assignments. ce_ctx->vm isn't part of
that simplification, so initialize it because it's used elsewhere and
were left NULL.
Bug 1846718
Change-Id: I6219880227b881d2175005b7eaf6e6e08a6f888e
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1306221
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
In two places we used broadcast register as base, but added the
unicast offset to it. This causes the write to go well beyond
valid register range.
Change the broadcast base to use unicast base instead in sequence
to resume a single SM and to record error state of SM.
Bug 200256272
Change-Id: I4ca9af2bb5877dba20ab96575f5094d42949c9e2
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
(cherry-picked from commit 04177b3414535ce5092c8baeae29883bada9d36c)
Reviewed-on: http://git-master/r/1306331
Reviewed-by: Automatic_Commit_Validation_User
Remove gm204/gm206 support. It was used only in the interim until
Pascal cards were available, and we don't maintain that code anymore.
This patch leaves only BIOS code.
Change-Id: I215988603d4588ef710bdda6e47449e9235e78ac
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1302224
GVS: Gerrit_Virtual_Submit
Most of BIOS parsing code is not specific to any particular GPU. Move
most of the code to generic files, and leave only chip specific parts
dealing with microcontroller boot into chip specific files.
As most of the parsing is generic, they do not need to be called via
HALs so remove the HALs and change the calls into direct function
calls.
All definitions meant to be used outside BIOS code itself are now in
<nvgpu/bios.h>
Change-Id: Id48e94c74511d6e95645e90e5bba5c12ef8da45d
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1302222
GVS: Gerrit_Virtual_Submit
This ioctl can be used on gp10b to set a flag in the context header
indicating this context should be run at elevated clock
frequency. FECS ctxsw ucode will read this flag as part of the context
switch and will request higher GPU clock frequencies from BPMP for the
duration of the context execution.
Bug 1819874
Change-Id: I84bf580923d95585095716d49cea24e58c9440ed
Signed-off-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-on: http://git-master/r/1292746
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Change the prefix in the semaphore code to 'nvgpu_' since this code
is global to all chips.
Bug 1799159
Change-Id: Ic1f3e13428882019e5d1f547acfe95271cc10da5
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1284628
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Move semaphore_gk20a.c drivers/gpu/nvgpu/common/ since the semaphore
code is common to all chips.
Move the semaphore_gk20a.h header file to drivers/gpu/nvgpu/include/nvgpu
and rename it to semaphore.h. Also update all places where the header
is inluced to use the new path.
This revealed an odd location for the enum gk20a_mem_rw_flag. This should
be in the mm headers. As a result many places that did not need anything
semaphore related had to include the semaphore header file. Fixing this
oddity allowed the semaphore include to be removed from many C files that
did not need it.
Bug 1799159
Change-Id: Ie017219acf34c4c481747323b9f3ac33e76e064c
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1284627
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Move nvgpu_common.c to drivers/gpu/nvgpu/common since it is a common
C file to all drivers.
Similarly move nvgpu_common.h to drivers/gpu/nvgpu/include/nvgpu since
this follows the new include guidelines.
Bug 1799159
Change-Id: I00ebed289973b27704c2cff073526e36505bf699
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1284612
Reviewed-by: Varun Colbert <vcolbert@nvidia.com>
Tested-by: Varun Colbert <vcolbert@nvidia.com>
Add HAL for enabling and disabling shadow ROM. This removes XVE dependency
from bios code.
Change-Id: Icafec72dae71669376bbfb97077661b7165badb8
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1302223
Moved pmuif/* headers to drivers/gpu/nvgpu/include/nvgpu folder
to support cross platform feature implementation.
Made changes to files which accessed include pmuif/* to reflect
pmuif/* movement changes.
Deleted includes of gk20a.h/pmu_gk20a.h from pmuif/*.h files.
Jira NVGPU-19
Change-Id: Iace4e107c24bdaff08a407eae3b147959173e485
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1299823
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Use upstream function tegra_get_chip_id and chip id macros,
as downstream function tegra_get_chipid() and chip_id macros
is going to be deprecated.
This is done as a part to removing duplicate code.
Change-Id: I846384955e983a36af0b3501d2b23c47e1d0798c
Signed-off-by: Shardar Shariff Md <smohammed@nvidia.com>
Reviewed-on: http://git-master/r/1299873
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Deleted PMU fecs override interface from pmu_api.h
header file as feature not used anymore
& its dependent code too.
Deleted file pmu_api.h as file dont
have any interfaces left inside
Jira NVGPU-19
Change-Id: I490cf67ae60ce2f1de37da063199ee04835b940d
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1297370
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
The driver file includes <linux/tegra-powergate.h> but does
not use anything from this header.
Remove this unnecessarily inclusion of header file.
bug 200257351
Change-Id: Idc9c79bfdcad0081b1121ec746fcc7a70306adf5
Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Reviewed-on: http://git-master/r/1300555
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Moved falcon-controller common interface code
from pmu_common.h to flcnif_cmn.h file.
Interfaces are common for falcons irrespective
of F/W on falcon controllers
Jira NVGPU-19
Change-Id: Iad11b2fade8cf6716888773b2b1c23919cbcc07b
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1296695
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Moved PMU/Falcon interface which are present
in pmu_gk20a.h & pmu_common.h to new files
as per feature
nvgpu_gpmu_cmdif.h - Top-level header-file that defines
the command/message interfaces used to communicate with PMU
gpmuif_pmu.h - PMU Command/Message init interfaces
gpmuif_cmn.h - Common definitions used by interfaces
Jira NVGPU-19
Change-Id: Id8ea6075e4dbba7697036951dcb85487eb861710
Signed-off-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-on: http://git-master/r/1296415
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Similar to patch 67fc462989 fix
more circular dependencies arising from #include'ing gk20a.h
for no apparent reason.
Bug 200192125
Coverity ID 2011397
Coverity ID 2011398
Change-Id: I75bcb3e4e66b680498b0e20d645ab9543aae6697
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1296947
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Remove the broke ref counting from as_share. The ref-count is
incremented for every bind channel but never decremented. This
results in VMs never being freed.
Bug 1846718
Change-Id: I6253b3eab7c7471d3ed6feddb3705c49a8704bed
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1296900
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Simplify ref-counting on VMs: take a ref when a VM is bound to a
channel and drop a ref when a channel is freed.
Previously ref-counts were scattered over the driver. Also the CE
and CDE code would bind channels with custom rolled code. This was
because the gk20a_vm_bind_channel() function took an as_share as
the VM argument (the VM was then inferred from that as_share).
However, it is trivial to abtract that bit out and allow a central
bind channel function that just takes a VM and a channel.
Bug 1846718
Change-Id: I156aab259f6c7a2fa338408c6c4a3a464cd44a0c
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1261886
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
gk20a_init_sw_bundle() has a couple of places where it continues
even despite an error is returned. Also it does not check the
return value from gops->gr.init_sw_veid_bundle().
Add an error goto label which restores pipeline state. Add gotos
to that label for all error cases.
Coverity ID 490376
Change-Id: I65338272d2817fa831370c8f070019debbfcd673
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1300098
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Changes to the context header after the context has been loaded may
not be visible to the GPU when mapped as cacheable memory. Examples
include updating the preemption modes or boosted_ctx bits at runtime.
This patch changes the mapping to non-cacheable.
Bug 1819874
Bug 1852094
Bug 200265538
Change-Id: I3b9e87adeaf32e337ec48e01631ad9dea61cc7da
Signed-off-by: Peter Boonstoppel <pboonstoppel@nvidia.com>
Reviewed-on: http://git-master/r/1297601
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Currently, when reading from ctxsw device node, we are collecting
traces that occurred before enabling tracing. This is not wanted,
and makes testing unpredicatable.
This change drops existing data in FECS ring buffer when enabling
traces, as currently done on vm-server side.
Jira EVLR-991
Change-Id: Idd2544d4667396f90778b7be82bdf73d1f8b8dc8
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1293303
Reviewed-by: Vishnu Reddy Mandalapu <vmandalapu@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@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>
On PG418, we hard code SW threshold table for over power
monitoring. On PG419, there is a dedicated INA for over
power monitoring. It is programmed in VBIOS devinit.
Added a platform flag to indicate if devinit has already
taken care of programming.
Jira DNVGPU-206
Change-Id: I28e70ac5621b692864a24e0eadb6d24b9957c0af
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1291813
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Allow platforms to choose whether or not to have unified GPU
VA spaces. This is useful for the dGPU where having a unified
address space has no problems. On iGPUs testing issues is
getting in the way of enabling this feature.
Bug 1396644
Bug 1729947
Change-Id: I65985f1f9a818f4b06219715cc09619911e4824b
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1265303
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
