The calls to nvhost_{register,unregister}_client_domain don't do
anything, so remove the platform device's late_probe and remove ops that
serve no other purpose than calling those empty functions. Remove also
the corresponding #includes which are now unused.
Bug 1853519
Change-Id: I67149d1575be5b3cacc60e6c28e6f2debfabf71c
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1326126
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>
preempt completion should be decided based on pbdma and
engine status. preempt_pending field is no longer used
to detect if preempt finished.
add a new function to to be used for preeempting ch and tsg
during recovery. If preempt timeouts while in recovery, do not
issue recovery.
JIRA GPUT19X-7
Change-Id: I0d69d12ee6a118f6628b33be5ba387c72983b32a
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: http://git-master/r/1309850
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Currently priv, pbus and ltc interrupts are enabled as non-stall but
being handled in stall isr. Fix is to configure them as stall interrupt.
Change-Id: I86adc04f480d5f4befe7e9255b582ce13fa4efc1
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: http://git-master/r/1319018
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
There is no peermem access for gv11b nvlink.
So no need to enable peermem access through l2.
Implemented gv11b specific ltc_cbc_fix_config
function to read correct num_active_ltcs.
JIRA GV11B-71
Change-Id: I348ce3bbf42e864341494e386b6f33478badb3a8
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1315148
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Implemented gv11b specific l2 state init and Configured
ltc_ltcs_ltss_cbc_num_active_ltcs_r with following info:
- cbc_num_active_ltcs is read only for gv11b, so did not
write any data to that field.
- enforced serilized access to l2 from sysmem and peermem.
- nvlink connected peer trafic sent through l2
JIRA GV11B-71
Change-Id: I63d9ee3f0a6da62e672a34e207f1f5214b6ed1b4
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1312831
GVS: Gerrit_Virtual_Submit
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
To get maximum number of subctx, sw should read
NV_PGRAPH_PRI_FE_CHIP_DEF_INFO_MAX_VEID_COUNT instead of
LITTER_NUM_SUBCTX.
JIRA GV11B-72
Change-Id: I4d675ba49d8a600da77e7b60da449d9e5ba48971
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1309591
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: Seema Khowala <seemaj@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
PMU reset for GV11B is PRIV protected.
gp106_pmu_reset() also uses the same register
to reset PMU, therefore used same function for
gv11b.
Change-Id: I633a96256598e73ed02cbdfe0afdb9fba8b76afd
Signed-off-by: Deepak Goyal <dgoyal@nvidia.com>
Reviewed-on: http://git-master/r/1303740
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
In gv11b sync point support is moved to a shim outside of GPU,
and gv11b does not support sync points anymore. Remove use of
the sync point protection.
JIRA GV11B-47
JIRA GV11B-2
Change-Id: I70f3d2ce0cfe016453efe03f2bbf64c59baeb154
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: http://git-master/r/1300964
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
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: Ibbc3c382c31a8c566ed4018fd36d1ffed08bf29e
Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Reviewed-on: http://git-master/r/1300556
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
GVS: Gerrit_Virtual_Submit
Added thermal registers for gv11b. Implemented chip specific
init_elcg_mode. In thermal control register, engine power auto
control config is removed and added new field for engine holdoff
enable signal.
JIRA GV11B-58
Change-Id: I412d9a232800d25efbdb0a40f14949d3f085fb0e
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1300119
Reviewed-by: Automatic_Commit_Validation_User
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Update zcull and perfmon buffer pointers in context header.
For gv11b maximum 49 bits gpu va possible. But,
zcull and perfmon buffer pointers uses maximum 41 bit
va address (258 bytes aligned). To accommodate this, high pointer
registers needs to be updated in context header.
JIRA GV11B-48
Change-Id: Ibe62b6bfedd32c4f3721e4d19d96cce58ef0f366
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1291852
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
Similar HW header update as has been done for all the other chips.
HW header files are located under:
drivers/gpu/nvgpu/include/nvgpu/hw/gv11b/
And can be included like so:
#include <nvgpu/hw/gv11b/hw_gr_gv11b.h>
Bug 1799159
Change-Id: If39bd71480a34f85bf25f4c36aec0f8f6de4dc9f
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1284433
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Restore golden context correctly with subcontext header.
Increase subctx header size to hold complete golden context.
Also fill function pointer for freeing context header.
Bug 1834201
Change-Id: Id8a3437bc437fef02ee15333c1163290217d34d1
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1282440
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: svccoveritychecker <svccoveritychecker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
The fuse headers are unified and moved all the content of
linux/tegra-fuse.h to the soc/tegra/fuse.h to have the
single fuse header for Tegra.
Use unified fuse header soc/tegra/fuse.h.
bug 200260692
Change-Id: Ied87164ea1de793d97a4cc6a754150164af04698
Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Reviewed-on: http://git-master/r/1287500
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The interface for wait_idle() was changed for gk20a, etc, so this
change is necessary to update the wait_idle function for gv11b.
Similarly for wait_fe() - this needs to no longer use an end_jiffie
argument.
Bug 1799159
Change-Id: I192159feffda5476269194e7d6ef15b5fe3055bd
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: http://git-master/r/1280459
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Pre-GP10X
All chips prior to GP10X do not support ZBC (Zero Bandwidth Clear) to stencil
part of the packed kinds (packed kinds refer to Z24S8 and Z32_X24S8 kinds).
Clears for these kinds typically happen in two phases, depth phase and
stencil phase. The depth clears can be compressed or ZBC-ed, whereas the
stencil part is always uncompressed.
Stencil ZBC in GP10X
For GP10X both the depth and the stencil data for these packed kinds can be
ZBC cleared. A given tile will be a cross product of the following states
for depth and stencil.
Depth: Uncompressed, 1-2 plane compressed, 3-4 plane compressed, ZBC index 0,
ZBC index 1
Stencil: Uncompressed, ZBC index 0, ZBC index 1, ZBC index 2
JIRA GV11B-9
Change-Id: I3381fd6305a4fada64211176b8ef98f27b04089f
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: http://git-master/r/1235520
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
gv11b needs atleast one subcontext to submit work. To support
legacy in gv11b, currently main context is always copied into
subcontext0 (veid0) during channel commit instance.
As part of channel commit instance, veid0 for that channel is
created and relevant pdb and context info copied to vedi0.
JIRA GV11B-21
Change-Id: I5147a1708b5e94202fa55e73fa0e53199ab7fced
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1231169
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Fix following sparse warning by making function as static:
$TOP/kernel/nvgpu-t19x/drivers/gpu/nvgpu/gv11b/gr_gv11b.c:1529:5:
warning: symbol 'gr_gv11b_setup_rop_mapping' was not declared.
Should it be static?
Bug 200088648
Change-Id: Idd388170f35e7e6cd7559d8aab8968f7e8e545c6
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1261891
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Add support for new litter values:
GPU_LIT_NUM_SUBCTX
GPU_LIT_NUM_SM_PER_TPC
Also updated get_litter_value api to use int
instead of enum type.
JIRA GV11B-21
Change-Id: Ide06245d03743e2d757d27d045701beb25b6707b
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: http://git-master/r/1254857
GVS: Gerrit_Virtual_Submit
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
