The main driver structure is not refcounted properly,
so when the driver unload, file desciptors associated to the
driver are kept open with dangling references to the main object.
This change adds referencing to the gk20a structure.
bug 200277762
JIRA: EVLR-1023
Change-Id: Id892e9e1677a344789e99bf649088c076f0bf8de
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1317420
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@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>
In gk20a_channel_clean_up_jobs, move removal of job from channel's job list
to before fences are cleaned up; this will prevent gk20a_channel_abort from
asynchronously trying to dereference an already freed job.
Bug 1844305
JIRA EVLR-849
Change-Id: I1ba05237aa74be1350007630bfa5eba9988f859a
Signed-off-by: Peter Daifuku <pdaifuku@nvidia.com>
(cherry picked from commit 2a9ce58b1b318b95ecfcdf78462f918d090eab99)
Reviewed-on: http://git-master/r/1319026
(cherry picked from commit 990f070b0a363159ce1b21f936b7512f469018ca)
Reviewed-on: http://git-master/r/1321624
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Move all programming of FB to fb_*.c files, and remove the inclusion
of FB hardware headers from other files.
TLB invalidate function took previously a pointer to VM, but the new
API takes only a PDB mem_desc, because FB does not need to know about
higher level VM.
GPC MMU is programmed from the same function as FB MMU, so added
dependency to GR hardware header to FB.
GP106 ACR was also triggering a VPR fetch, but that's not applicable
to dGPU, so removed that call.
Change-Id: I4eb69377ac3745da205907626cf60948b7c5392a
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1321516
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move clock APIs from gk20a_platform to gpu_ops. At the same time
allow use of internal get_rate/set_rate for querying both GPCCLK
and PWRCLK on iGPU.
At the same time we can replace calls to clk framework with the
new HAL and drop direct dependency to clk framework.
gp10b ops were replaced as a whole at HAL initialization. That
replaces anything set in platform probe stage, so reduce that to
touch only clock gating regs.
Change-Id: Iaf219b1f000d362dbf397d45832f52d25463b31c
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1300113
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Platform files are used for adding code to probe for Tegra Linux
platform. Move the files to Tegra Linux directory to make this
clear.
Change-Id: Ida66af835688325f095260c618dad90395851267
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1300112
Reviewed-by: Alex Waterman <alexw@nvidia.com>
GVS: Gerrit_Virtual_Submit
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>
The call site (gk20a_submit_prepare_syncs) owns the incr_cmd buffer
passed to __gk20a_channel_semaphore_incr. Delete the free in the error
path of the latter case to avoid freeing the same buffer twice.
Bug 1853519
Change-Id: I9b90ce7ebb17ac63992938c7f9fe90bbd139f85f
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1321117
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: David Martinez Nieto <dmartineznie@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
In gk20a_suspend_all_sms(), we currently loop
over all GPCs and then loop over all TPCs in inner
loop
But this is incorrect and leads to SM with
invalid GPC,TPC ids
Fix this by looping over number of TPCs in each
GPC in inner loop
Also, fix gk20a_gr_wait_for_sm_lock_down() as
per below
- we right now wait infinitely for SM to lock down
- restrict this wait with a timeout on silicon
platforms
- return ETIMEDOUT instead of EAGAIN
- add more debug prints with additional data
for SM lock down failures
Bug 200258704
Change-Id: Id6fe32e579647fd8ac287a4b2ec80cbf98791e0d
Signed-off-by: Cory Perry <cperry@nvidia.com>
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1316471
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
JIRA: EVLR-1004
(*) Refactor the non-stalling interrupt path to execute clear on the
top half, so on dGPU case processing of stalling interrupts does not
block non-stalling one.
(*) Use a worker thread to do semaphore wakeups and allow batching of
the non-stalling operations.
(*) Fix a bug where some gpus will not properly track the completion
of interrupts, preventing safe driver unloads
Change-Id: Icc90a3acba544c97ec6a9285ab235d337ab9eefa
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1312796
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Lakshmanan M <lm@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Navneet Kumar <navneetk@nvidia.com>
Add ability to suspend/resume contexts for a debug session
(NVGPU_DBG_GPU_IOCTL_SUSPEND_RESUME_CONTEXTS), in virtualized
case:
- added hal function to resume contexts.
- added vgpu support for suspend contexts, i.e. build a list
of channel ids, and send TEGRA_VGPU_CMD_SUSPEND_CONTEXTS
- added vgpu support for resume contexts, i.e. build a list
of channel ids, and send TEGRA_VGPU_CMD_RESUME_CONTEXTS
Bug 1791111
Change-Id: Icc1c00d94a94dab6384ac263fb811c00fa4b07bf
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: http://git-master/r/1294761
(cherry picked from commit d17a38eda312ffa92ce92e5bafc30727a8b76c4e)
Reviewed-on: http://git-master/r/1299059
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Cory Perry <cperry@nvidia.com>
Tested-by: Cory Perry <cperry@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Add a debugfs interface to profile the kickoff ioctl
it provides the probability distribution and separates the information
between time spent in: the full ioctl, the kickoff function, the amount
of time spent in job tracking and the amount of time doing pushbuffer
copies
JIRA: EVLR-1003
Change-Id: I9888b114c3fbced61b1cf134c79f7a8afce15f56
Signed-off-by: David Nieto <dmartineznie@nvidia.com>
Reviewed-on: http://git-master/r/1308997
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
1) Trace buffer allocation now calls generic gmmu alloc/map.
so for dGPUs they are allocated in vidmem and iGPUs they
are allocated in sysmem
2) Use pmu surface mechanism to setup trace buffer params as
dGPU binaries follow falcon memory structure to get mem surface
params
3) Fix minor coverity issue by removing unnecessary overwrite
of count variable in trace print function
JIRA DNVGPU-217
Coverity ID 2431386
Change-Id: I2ae49a4e0450481cde2a778447c270a796681dad
Signed-off-by: Vijayakumar <vsubbu@nvidia.com>
Reviewed-on: http://git-master/r/1312404
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
-Handle pbus and priv stall interrupts first.
In general critical interrupts should be
handled before any other non critical ones.
-Dump info enabled with gpu_dbg_intr if priv_ring
interrupt is flagged by fmodel.
JIRA NVGPU-25
Change-Id: Iee767d8c9c933ceb57532c1b5a7fd7812daf1b6d
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: http://git-master/r/1311273
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
trace_printk() does an extra stringify operation before calling
do_trace_printk(). The string ends up unused. This has an impact
to kernel even if we never end up using trace_printk().
Disable use of trace_printk() and introduce a Kconfig option for
re-enabling it.
Change-Id: I2e1014f5231f2089d7dc3cb2539e3eb5f4d58361
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1295298
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Implement kmem abstraction and tracking in nvgpu. The abstraction
helps move nvgpu's core code away from being Linux dependent and
allows kmem allocation tracking to be done for Linux and any other
OS supported by nvgpu.
Bug 1799159
Bug 1823380
Change-Id: Ieaae4ca1bbd1d4db4a1546616ab8b9fc53a4079d
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1283828
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Change nvgpu_kalloc() to nvgpu_big_[mz]alloc(). This is necessary
since the natural free function name for this is nvgpu_kfree() but
that conflicts with nvgpu_k[mz]alloc() (implemented in a subsequent
patch).
This API exists becasue not all allocation sizes can be determined
at compile time and in some cases sizes may vary across the system
page size. Thus always using kmalloc() could lead to OOM errors due
to fragmentation. But always using vmalloc() is wastful of memory
for small allocations. This API tries to alleviate those problems.
Bug 1799159
Bug 1823380
Change-Id: I49ec5292ce13bcdecf112afbb4a0cfffeeb5ecfc
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1283827
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
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
