Implement gv11b platform specific rail gating functions
by calling relevant powergate and unpowergate functions
and linux clock frmework functions:
gv11b_tegra_is_railgated
gv11b_tegra_railgate
gv11b_tegra_unrailgate
These calls will take care of hot reset sequence
required for gpu powergate and gpu unpowergate.
Bug 200269361
Bug 200273571
Change-Id: Ib1825e4324d51fc508b3b5dc9e5e2fdb252eeff4
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1589509
Reviewed-by: Automatic_Commit_Validation_User
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>
Convert disable_aspm and references to that field to use
nvgpu_is_enabled(NVGPU_SUPPORT_ASPM). Initialize it from
gk20a_platform struct at probe time.
This removes another dependency to struct gk20a_platform.
JIRA NVGPU-259
Change-Id: I32e30160f817ea275aa190dcf86c5fd594138d75
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1590124
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move gk20a/platform_gk20a.h to linux specific directory as
common/linux/platform_gk20a.h since this file includes all linux specific
stuff
Fix #includes in all the files to include this file with correct path
Remove #include of this file where it is no more needed
Fix gk20a_init_sim_support() to receive struct gk20a as parameter
instead of receiving linux specific struct platform_device
NVGPU-316
Change-Id: I5ec08e776b753af4d39d11c11f6f068be2ac236f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1589938
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This reverts commit a8643b3a99.
Proper resolution is implemented in user space (nvrm_gpu) to idle all channels
of TSG before unbinding a channel from it
And with that we should not see NEXT bit set on channel while unbinding
Hence revert the WAR and again return error if we find NEXT bit set on channel
Also restore the error print
Bug 200327095
Change-Id: Id58e00c4602a4a5c9f65e5ee1329b606f45993d7
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1585991
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In gk20a_gr_reset(), we acquire g->gr.fecs_mutex and call a bunch of APIs
But in case any of these APIs fail, we don't release the mutex and just
return the error leaking the mutex
So the next attempt to acquire g->gr.fecs_mutex results in a deadlock
Fix this by releasing the mutex before returning error
Bug 2015370
Change-Id: I9a0214ff53515f819c6566c7d44d1898027416e1
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1589062
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
API gr_gv11b_create_sysfs() and GR HAL create_gr_sysfs() right now receive
linux specific struct device
But since this function is called from/declared in common code, we need to
remove linux dependency from it
Hence update the API and GR HAL to receive struct gk20a pointer instead
of device pointer
Jira NVGPU-259
Change-Id: I65d717ad9f263f0397f8efa5761c64e55c7846eb
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1588465
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@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>
API gr_gp10b_create_sysfs() and GR HAL create_gr_sysfs() right now receive
linux specific struct device
But since this function is called from/declared in common code, we need to
remove linux dependency from it
Hence update the API and GR HAL to receive struct gk20a pointer instead
of device pointer
Jira NVGPU-259
Change-Id: I7effa16407d47a2ab5f9562ec4a4dec975a32d6c
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1588464
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Nvgpu submit path has a lot of dependency on Linux framework
e.g. use of copy_from_user, use of structures defined in uapi/nvgpu headers,
dma_buf_* calls for trace support etc
Hence to keep common code independent of Linux code, move submit path to
Linux directory
Move below APIs to common/linux/channel.c
trace_write_pushbuffer()
trace_write_pushbuffer_range()
gk20a_submit_prepare_syncs()
gk20a_submit_append_priv_cmdbuf()
gk20a_submit_append_gpfifo()
gk20a_submit_channel_gpfifo()
Move below APIs to common/linux/ce2.c
gk20a_ce_execute_ops()
Define gk20a_ce_execute_ops() in common/linux/ce2.c, and declare it in
gk20a/ce2_gk20a.h since it is needed in common/mm code too
Each OS needs to implement this API separately
gk20a_channel_alloc_gpfifo() use sizeof(nvgpu_gpfifo) to get size of one gpfifo
entry, but structure nvgpu_gpfifo is linux specific
Define new nvgpu_get_gpfifo_entry_size() in linux specific code and use it
in gk20a_channel_alloc_gpfifo() to get gpfifo entry size
Each OS needs to implement this API separately
Export some APIs from gk20a/ce2_gk20a.h and gk20a/channel_gk20a.h that are
needed in linux code
Jira NVGPU-259
Jira NVGPU-313
Change-Id: I360c6cb8ce4494b1e50c66af334a2a379f0d2dc4
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1586277
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This patch adds kernel interface for dynamic TPC-PG feature.
User-space needs to send TPC-PG args to kernel via ioctl.
Dynamic TPC-PG feature will allow every context to specify the
number of TPC's it will use to run its workload.
This way, graphics driver can power off non-required TPC's
if a particular context has light to medium workload.
JIRA GPUT19x-16
Change-Id: Id4846245a6414b719599d04784cbe2ca5282f4ad
Signed-off-by: Deepak Goyal <dgoyal@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1575848
Reviewed-by: Automatic_Commit_Validation_User
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>
Split the ctxsw trace "core" API code into <nvgpu/ctxsw_trace.h>. This
is not perect though since there's some Linuxisms present in the HAL
and as such that code has to be hidden by the ctxsw tracing CONFIG. But
this patch should work for QNX such that it will allow the code to
build as long as CONFIG_GK20A_CTXSW_TRACE is not set.
Also fix the copywrite notice in the ctxsw code present under
common/linux to be GPL.
JIRA NVGPU-287
Change-Id: I94715864caf335b7220185492e4629d713b025e0
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1589429
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In current code vgpu only set error notifier for the reporting channel
but abort the whole tsg. When the tsg is aborted, all channels of the
tsg are supposed have had their error notifiers set. Set it for all
channels once any of the channels gets an MMU fault.
For now, RM server still reports num-of-channel times for tsg mmu fault.
We may optimize it in future.
Jira VFND-3798
Change-Id: I6deaca55e7420899af8eabec72ad888d2726ad3c
Signed-off-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1588098
Reviewed-by: Aingara Paramakuru <aparamakuru@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove the buffer_attrs struct and replace it with a more
streamlined nvgpu_ctag_buffer_info struct. This struct allows
several different fields to all be passed by pointer to the
various kind/compression functions in the VM map process.
This path also moves several comptag/kind related functions
to the core vm.c code since these functions can be reused by
other OSes.
Change-Id: I2a0f0a1c4b554ce4c8f2acdbe3161392e717d3bf
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1583984
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove the always true field 'user_mapped' from the mapped_buf
struct. All mapped_bufs are mapped by a user request since they
always originate from a dma_buf (for Linux, that is). As such
there is a fair amount of logic that could be deleted.
Linux specific: the own_mem_ref field was also be deleted. The
logic of only storing a dma_buf ref when the buffer is mapped
for the first time by a user is easy: when the mapped buffer is
found in the map cache release the outstanding dma_buf ref taken
earlier on in the map path. If the map cache does not have the
buffer simply let the higher level map code keep the dma_buf ref.
The dma_buf ref is released when the nvgpu_vm_unmap_system()
call-back is called by the unmap path.
JIRA NVGPU-30
JIRA NVGPU-71
Change-Id: I229d136713812a7332bdadd5ebacd85d983bbbf0
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1583983
Reviewed-by: Automatic_Commit_Validation_User
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>
Re-organize the unmap code to be better split between OS specific
requirements and common core requirements. The new code flow works
as follows:
nvgpu_vm_unmap()
Is the primary entrance to the unmap path. It takes a VM and a GPU
virtual address to unmap. There's also an optional batch mapping
struct.
This function is responsible for making sure there is a real buffer
and that if it's being called on a fixed mapping then the mapping
will definitely be freed (since buffers are ref-counted). Then this
function decrements the ref-count and returns.
If the ref-count hits zero then __nvgpu_vm_unmap_ref() is called
which just calls __nvgpu_vm_unmap() with the relevant batch struct
if present. This is where the real work is done. __nvgpu_vm_unmap()
clears the GMMU mapping, removes the mapped buffer from the various
lists and trees it may be in and then calls the
nvgpu_vm_unmap_system() function. This function handles any OS
specific stuff and must be defined by all VM OS implementations.
There's a a short cut used by some other core VM code to free
mappings without going through nvgpu_vm_map(). Mostly they just
directly decrement the mapping ref-count which can then call
__nvgpu_vm_unmap_ref() if the ref-count hits zero.
JIRA NVGPU-30
JIRA NVGPU-71
Change-Id: Ic626d37ab936819841bab45214f027b40ffa4e5a
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1583982
Reviewed-by: Automatic_Commit_Validation_User
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>
TSG enable sequence in native has been modified due to a
hardware bug requiring enabling all channels with NEXT and
CTX_RELOAD set in a TSG, and then enabling rest of channels.
However it is not possible to check if NEXT and CTX_RELOAD
is set in vgpu. Have a separate implementation for enabling
tsg sequence in vgpu till the fix for hardware bug is
implemented for virtualized configuration.
Bug 200348087
Change-Id: I6bfc52138bc540c0ea0ad18a85155eeff6f9efa8
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1588740
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
TSG enable sequence in native has been modified due to a
hardware bug requiring enabling all channels with NEXT and
CTX_RELOAD set in a TSG, and then enabling rest of
channels.However it is not possible to check if NEXT and
CTX_RELOAD is set in vgpu. Have a separate implementation
for enabling tsg sequence in vgpu till the fix for
hardware bug is implemented for virtualized configuration.
Bug 200348087
Change-Id: I8e6c2ba8722531563de65e51e3d6af6acb7af213
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1588739
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Richard Zhao <rizhao@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Nirav Patel <nipatel@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Issue
Currently bitmask of engine indices is being saved.
This will give wrong active engine ids for a given runlist
and s/w will end up checking/polling wrong engine_status
registers as these registers are indexed by active
engine ids. Also reset_eng_bitmask will end up
having wrong value for active engine ids to be reset.
Details for runlists serving engines ids for gv11b are:-
runlist id 0: gr = 0, grcopy 0 = 2, grcopy1 = 3
runlist id 1: async ce = 1
Incorrect values
init_runlist:705 [DBG] runlist 0 : eng bitmask 7 (eng 0, 1, 2)
init_runlist:705 [DBG] runlist 1 : eng bitmask 8 (eng 3)
Fix
Save bitmask of active engine ids in runlist info.
Right value
init_runlist:705 [DBG] runlist 0 : eng bitmask d (eng 0, 2, 3)
init_runlist:705 [DBG] runlist 1 : eng bitmask 2 (eng 1)
Bug 200277163
Bug 1945121
Change-Id: Ia299aa0881c4a258080bb0daa3a542fef0d94e4f
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1584066
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
gk20a/clk_gk20a.h is a common file but still includes linux specific headers
Clean them up as below
- put linux/clk-provider.h include under config CONFIG_COMMON_CLK
- move linux/clkdev.h include to common/linux/platform_gk20a_tegra.c as it is no
longer needed in this file
Jira NVGPU-259
Change-Id: I4f5b996d3dea91ec3d737d4caa45e0eff6a7ee74
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1588220
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Try to fix invalid pte type repalayable faults only.
All other replayable faults will be cancelled so that
next mmu fault for same fault address will be triggered
as non-replayable fault and ch/tsg teardown will take place.
Bug 1958308
Change-Id: I63b90ce7c639ee183f87db3e771f253fd04c3567
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1566576
GVS: Gerrit_Virtual_Submit
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Teardown function should be passed appropriate id and
id_type. E.g. if a channel is marked as tsg, channel teardown/rc
function should be passed it's tsgid as id and type_tsg as
id_type
Bug 200277163
Change-Id: I2e83561c03d515fac28cbb8ce75a9f2c7bf746ac
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1557296
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Use nvgpu_alloc_obj_ctx_args structure specific to Linux code only.
Pass the fields of the structure as separate arguments to all common
functions.
gr_ops_gp10b.h referred to the struct, but it's not used anywhere,
so delete the file.
JIRA NVGPU-259
Change-Id: Idba78d48de1c30f205a42da2fe47a9f8c03735f1
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1586563
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Migrate ctxsw_trace_gk20a.c to common/linux/ctxsw_trace.c. This
has been done becasue the ctxsw tracing code is currently too
tightly tied to the Linux OS due to usage of a couple system calls:
- poll()
- mmap()
And general Linux driver framework code. As a result pulling the
logic out of the FECS tracing code is simply too large a scope for
time time being.
Instead the code was just copied as much as possible. The HAL ops
for the FECS code was hidden behind the FECS tracing config so
that the vm_area_struct is not used when QNX does not define said
config. All other non-HAL functions called by the FECS ctxsw
tracing code ha now also been hidden by this config. This is not
pretty but for the time being it seems like the way to go.
JIRA NVGPU-287
Change-Id: Ib880ab237f4abd330dc66998692c86c4507149c2
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1586547
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In gk20a_fifo_tsg_unbind_channel(), we always verify channel status before
unbinding a channel from TSG
But in case TSG has alread timed out we never re-enable it so it does not
make sense to inspect channel status anyways
So skip channel status verification in case TSG has timed out
Bug 200327095
Change-Id: Iccf601271290643c235c3f2656201549210a6886
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1586015
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>
Native code for verifying tsg status on ctx reload is not
possible on vgpu. Unset gops->fifo.tsg_verify_status_faulted
operation for vgpu for now. This needs to be implemented
separately for vgpu later.
Bug 200348087
Change-Id:Ib427f66e0897e37c34b882ead95ca8b84d595d72
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1585784
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Native code for verifying tsg status on ctx reload is not
possible on vgpu. Unset gops->fifo.tsg_verify_status_faulted
operation for vgpu for now. This needs to be implemented
separately for vgpu later.
Bug 200348087
Change-Id: I73791401de1ce7b7f8644ea4f9ccae3fc51dc7aa
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1585783
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Update all Kconfig files and Makefiles to rely on the kernel overlay
feature. In particular, don't include any Kconfig files or Makefiles
from other overlays. -I directives in CFLAGS are not yet cleaned up.
Bug 1978395
Change-Id: I16386f7f1e76bd68b55f3128b25eada029ae82c1
Signed-off-by: Stephen Warren <swarren@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1571165
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Update all Kconfig files and Makefiles to rely on the kernel overlay
feature. In particular, don't include any Kconfig files or Makefiles
from other overlays. -I directives in CFLAGS are not yet cleaned up.
Bug 1978395
Change-Id: I449ed2f07949785f2dd90a6833f4d8cd1711519a
Signed-off-by: Stephen Warren <swarren@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1566641
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
