init_pbdma_intr_descs HAL ops is used to update the internal values of
the struct intr within struct fifo_gk20a. Three kinds of
intr_descriptors are filled i.e. device_fatal_0, channel_fatal_0 and
restartable_0. Breaking them into separate HALs has the advantage of
reusing the h/w headers corresponding to the device_fatal_0 as they are
same across all the architectures while those of channel_fatal_0 varies.
Another advantage is to now decouple pbdma from filling in values
within the fifo_gk20a struct. A new method gk20a_fifo_init_pbdma_descs
is constructed that initializes the above intr struct by calling the
separate HAL ops for these.
Jira NVGPU-2950
Change-Id: I78ddc61a5d9b2088d34259af90f8b85817bf19d9
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2072741
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The following HAL pointers are moved to a separate HAL unit named pbdma.
pbdma_acquire_val
get_pbdma_signature
dump_pbdma_status
handle_pbdma_intr_0
handle_pbdma_intr_1
read_pbdma_data
reset_pbdma_header
The functions corresponding to these HAL units are also moved to
pbdma_{arch} files under hal/fifo correspondinging to arch gm20b,
gp10b, gv11b and tu104. Any calls to gk20a_readl and gk20a_writel
are replaced by nvgpu_readl and nvgpu_writel respectively.
Jira NVGPU-2950
Change-Id: I9723f30ddf6582df02c03fceb1fba26a206e1230
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2071782
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move load_tpc_mask and setup_rop_mapping hal functions to hal.gr.init.
Existing load_tpc_mask hal code is split to two parts, one as a common
code in gr_load_tpc_mask and register write to init.tpc_mask hal
functions.
Modify pd_tpc_per_gpc and pd_skip_table_gpc hals in the
hal.gr.init to pass struct nvgpu_gr_config as a parameter.
JIRA NVGPU-2951
Change-Id: I52e26d0f023afa511a8cf8c3e4c54f45350be4ae
Signed-off-by: Vinod G <vinodg@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2074892
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
nvgpu_gr_ctx_load_golden_ctx_image() in common.gr.ctx unit programs
initial pm_mode in context. gk20a_alloc_obj_ctx() then disables pm_mode
ctxsw by default.
Fix this by disabling pm_mode ctxsw by default in
nvgpu_gr_ctx_load_golden_ctx_image() itself. Remove corresponding code
from gk20a_alloc_obj_ctx()
Jira NVGPU-1887
Change-Id: I6e1f83cefcb6229394da353e4cd87f1f5a0b10d4
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2076273
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add new hals in unit hal.gr.init to commit RTV circular buffer
g->ops.gr.init.commit_rtv_cb()
g->ops.gr.init.commit_gfxp_rtv_cb()
Remove tu104 hal to commit global ctx buffers
gr_tu104_commit_global_ctx_buffers() since we have specific hals to
commit RTB circular buffer
Update gr_gk20a_commit_global_ctx_buffers() to directly call
hal.gr.init hals to commit RTV buffers
Jira NVGPU-2961
Change-Id: I12a53386654ebfeb98bf187385bb8b839070d569
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2075230
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add a new hal.gr.init unit hal g->ops.gr.init.get_rtv_cb_size() to
retrieve RTV buffer size
Update gr_gk20a_alloc_global_ctx_buffers() to initialize RTV buffer
size if g->ops.gr.init.get_rtv_cb_size hal is present
Remove gr_tu104_alloc_global_ctx_buffers() since it is no longer
required
Jira NVGPU-2961
Change-Id: I44be8dfdda5c813eac445192635a3a6c2b867b3a
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2075229
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move g->ops.gr.commit_global_timeslice() hal operation to hal.gr.init
unit as g->ops.gr.init.commit_global_timeslice()
Drop channel pointer in parameter list since it was unused
Also change return type to void since it never returns error
Move corresponding gm20b and gv11b hal operations to hal.gr.init unit
Jira NVGPU-2961
Change-Id: I68deef45af1d52149eb354a1478cc2b5f2e4ec2a
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2075228
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add a new hal operation g->ops.gr.init.load_method_init() in hal.gr.init
unit that reads method init netlist bundle and writes those values to
h/w appropriately
Use new hal in gr_gk20a_init_golden_ctx_image() instead of direct
register accesses
Jira NVGPU-2961
Change-Id: If1edd09445e55b5ad9cb1ec7b0f32cab9bfd6f05
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2075227
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Native and vgpu were using different paths for fifo
init/deinit code.
Use same nvgpu_fifo_init_support for init code:
nvgpu_fifo_init_support
g->ops.fifo.setup_sw
vgpu_fifo_setup_sw (NEW)
Use same nvgpu_fifo_remove_support for deinit code:
nvgpu_fifo_remove_support (NEW)
g->ops.fifo.cleanup_sw (NEW)
vgpu_fifo_cleanup_sw (NEW)
Also implemented gk20a_fifo_cleanup_sw for native case.
Jira NVGPU-1306
Jira NVGPU-2855
Change-Id: Iefe303cc224f804a206422e2efffda9da1616d89
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2029649
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Moved cbc related code and data from gr to cbc unit.
Ltc and cbc related data is moved from gr header:
1. Ltc related data moved from gr_gk20a -> gk20a and it
will be moved eventually to ltc unit:
u32 slices_per_ltc;
u32 cacheline_size;
2. cbc data moved from gr_gk20a -> nvgpu_cbc
u32 compbit_backing_size;
u32 comptags_per_cacheline;
u32 gobs_per_comptagline_per_slice;
u32 max_comptag_lines;
struct gk20a_comptag_allocator comp_tags;
struct compbit_store_desc compbit_store;
3. Following config data moved gr_gk20a -> gk20a
u32 comptag_mem_deduct;
u32 max_comptag_mem;
These are part of initial config which should be available
during nvgpu_probe. So it can't be moved to nvgpu_cbc.
Modified code to use above updated data structures.
Removed cbc init sequence from gr and added in
common cbc unit. This sequence is getting called
from common nvgpu init code.
JIRA NVGPU-2896
JIRA NVGPU-2897
Change-Id: I1a1b1e73b75396d61de684f413ebc551a1202a57
Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2033286
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add new hal operation g->ops.gr.init.fe_go_idle_timeout() in hal.gr.init
unit to enable/disable fe_go_idle timeout
Use this hal in gr_gk20a_init_golden_ctx_image() instead of direct
register access
Remove timeout disable/enable code in gk20a_init_sw_bundle() since
parent API gr_gk20a_init_golden_ctx_image() is already taking care of
that
Jira NVGPU-2961
Change-Id: Ice72699059f031ca0b1994fa57661716a6c66cd2
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2072550
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move GR HAL operation g->ops.gr.init_preemption_state() to hal.gr.init
unit as g->ops.gr.init.preemption_state()
Create hal.gr.init unit files for gp10b and gv11b and copy over
corresponding functions to new files
This API now takes gfxp_wfi_timeout_unit and gfxp_wfi_timeout_count as
parameter
Define gfxp_wfi_timeout_unit in struct gr_gk20a as a boolean flag named
gfxp_wfi_timeout_unit_usec
Remove GFXP_WFI_TIMEOUT_UNIT_SYSCLK/USEC macros
Jira NVGPU-2961
Change-Id: I4347b1e30c86c231e44cf274adccd8c70addcdab
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2072549
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move g->ops.fecs_trace.*() HAL operations under gr operations as
g->ops.gr.fecs_trace.*()
Also rename gk20a_ctxsw_*() functions used in common code to the
format nvgpu_gr_fecs_trace_*()
Jira NVGPU-1880
Change-Id: Idf2f8fb3d7ba2832bf1837fd97b70b3cee412123
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2070767
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
We have 3 header files for FECS tracing support
include/nvgpu/gr/fecs_trace.h : common header
include/nvgpu/ctxsw_trace.h : header that includes both common and
os-specific functions
os/linux/ctxsw_trace.h : linux specific header
Remove the second header since it is not needed.
Move all structures that are needed in common code to
include/nvgpu/gr/fecs_trace.h
Move all function declarations that are needed in common code to
include/nvgpu/gr/fecs_trace.h
Move all linux specific declarations in os/linux/ctxsw_trace.h and
rename this file as os/linux/fecs_trace_linux.h
Also rename os/linux/ctxsw_trace.c to os/linux/fecs_trace_linux.c
Jira NVGPU-1880
Change-Id: I05cc4489c4b6a64880b7d59c02b22cd2244d5e22
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2070766
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This struct was earlier moved to falcon_priv.h to give exclusive access
to only falcon unit. However with HAL unit needing access to this we
need to move it public header nvgpu/falcon.h.
JIRA NVGPU-1993
Change-Id: Ia3b211798009107f64828c9765040d628448812a
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2069688
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add fifo sub-unit to common.fifo to handle init/deinit code
and global support functions.
Split init into:
- nvgpu_channel_setup_sw
- nvgpu_tsg_setup_sw
- nvgpu_fifo_setup_sw
- nvgpu_runlist_setup_sw
- nvgpu_engine_setup_sw
- nvgpu_userd_setup_sw
- nvgpu_pbdma_setup_sw
Split de-init into
- nvgpu_channel_cleanup_sw
- nvgpu_tsg_cleanup_sw
- nvgpu_fifo_cleanup_sw
- nvgpu_runlist_cleanup_sw
- nvgpu_engine_cleanup_sw
- nvgpu_userd_cleanup_sw
- nvgpu_pbdma_cleanup_sw
Added the following HALs
- runlist.length_max
- fifo.init_pbdma_info
- fifo.userd_entry_size
Last 2 HALs should be moved resp. to pbdma and userd sub-units,
when available.
Added vgpu implementation of above hals
- vgpu_runlist_length_max
- vgpu_userd_entry_size
- vgpu_channel_count
Use hals in vgpu_fifo_setup_sw.
Jira NVGPU-1306
Change-Id: I954f56be724eee280d7b5f171b1790d33c810470
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2029620
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Register write from gr_gk20a_init_fs_state function are moved to hal.
New hal added for setting the pd_tpc_per_gpc, pd_skip_table_gpc and
cwd_gpcs_tpcs_num.
pd_tpc_per_gpc helps to describe the number of tpcs in each logical
gpc.
pd_skip_table helps to skip certain TPCs during distribution.
cwd_gpcs_tpcs_num helps to set number of tpcs and gpcs in CWD.
remove write for depreciated NV_PBE_PRI_ZROP_SETTING_NUM_ACTIVE_FBPS
and NV_PBE_PRI_CROP_SETTINS_NUM_ACTIVE_FBPS fields from
BES_ZROP_SETTINGS and BES_CROP_SETTINGS registers. Both these fields
changed to NUM_ACTIVE_LTCS from gm20b onwards and those are being
set in existing hal functions.
JIRA NVGPU-2951
Change-Id: I905b98356e8eadaf7e2481850de841c050ea50c5
Signed-off-by: Vinod G <vinodg@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2072249
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
create new hals for wait_idle and wait_fe_idle under gr.init.
modify functions to following hals and use same hals for all chips.
gr_gk20a_wait_idle -> gm20b_gr_init_wait_idle
gr_gk20a_wait_fe_idle -> gm20b_gr_init_wait_fe_idle
JIRA NVGPU-2951
Change-Id: Ie60675a08cba12e31557711b6f05f06879de8965
Signed-off-by: Vinod G <vinodg@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2072051
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
gr_gk20a_init_golden_ctx_image() right now resets sys/gpc/be units by
directly accessing gr_fecs_ctxsw_reset_ctl_r() register
Move this register write/read sequence to common.hal.gr.init unit
through HAL operation g->ops.gr.init.override_context_reset()
Use new HAL in gr_gk20a_init_golden_ctx_image()
Also fix the delay() operations. delay() should be added before we read
back gr_fecs_ctxsw_reset_ctl_r() register and not after
Jira NVGPU-2961
Change-Id: I70d3a61b5aa60846815dee52ecac544066542695
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2070608
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add new HAL unit common.hal.gr.init with below source files
hal/gr/init/gr_init_gm20b.c
hal/gr/init/gr_init_gm20b.h
In gr_gk20a_init_golden_ctx_image() we force FE power mode on and also
disable it. Extract out this sequence into new unit and expose new HAL
operation that takes a boolean flag to enable/disable power mode
g->ops.gr.init.fe_pwr_mode_force_on()
Use new HAL operation in gr_gk20a_init_golden_ctx_image()
Set this HAL for all the chips
Jira NVGPU-2961
Change-Id: I1dd35d94fda5e5296af67c0abc944e200fb752ea
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2070607
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Rename gr_reset_mutex to engines_reset_mutex and acquire it
before initiating recovery. Recovery running in parallel with
engine reset is not recommended.
On hitting engine reset, h/w drops the ctxsw_status to INVALID in
fifo_engine_status register. Also while the engine is held in reset
h/w passes busy/idle straight through. fifo_engine_status registers
are correct in that there is no context switch outstanding
as the CTXSW is aborted when reset is asserted.
Use deferred_reset_mutex to protect deferred_reset_pending variable
If deferred_reset_pending is true then acquire engines_reset_mutex
and call gk20a_fifo_deferred_reset.
gk20a_fifo_deferred_reset would also check the value of
deferred_reset_pending before initiating reset process
Bug 2092051
Bug 2429295
Bug 2484211
Bug 1890287
Change-Id: I47de669a6203e0b2e9a8237ec4e4747339b9837c
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2022373
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
set gr.initialized to false in the beginning of gk20a_gr_reset() and
set it to true at the end of successful execution of gk20a_gr_reset.
Use gk20a_gr_wait_initialized() to enable/disable cg/pg
functions to make sure engine is out of reset and initialized.
Bug 2092051
Bug 2429295
Bug 2484211
Bug 1890287
Change-Id: Ic7b0b71382c6d852a625c603dad8609c43b7f20f
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2030827
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
if fecs is sent stop_ctxsw method, elpg entry/exit cannot happen
and may timeout. It could manifest as different error signatures
depending on when stop_ctxsw fecs method gets sent with respect
to pmu elpg sequence. It could come as pmu halt or abort or
maybe ext error too.
If ctxsw failed to disable, do not read engine info and just abort tsg.
Bug 2092051
Bug 2429295
Bug 2484211
Bug 1890287
Change-Id: I5f3ba07663bcafd3f0083d44c603420b0ccf6945
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2014914
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
For handle_sched_error, change err to info print for failing eng
id returned as -1 i.e. FIFO_INVAL_ENGINE_ID as no engine is found
busy doing ctxsw. May be ctxsw already finished for the context
for which ctxsw timeout intr was triggered.
Possible Causes:
a)
On hitting engine reset, h/w drops the ctxsw_status to INVALID in
fifo_engine_status register. Also while the engine is held in reset
h/w passes busy/idle straight through. fifo_engine_status registers
are correct in that there is no context switch outstanding
as the CTXSW is aborted when reset is asserted.
This is just a side effect of how gv100 and earlier versions of
ctxsw_timeout behave.
With gv10b and later, h/w snaps the context at the point of error
so that s/w can see the tsg_id which caused the HW timeout.
b)
If engines are not busy and ctxsw state is valid then intr occurred
in the past and if the ctxsw state has moved on to VALID from LOAD
or SAVE, it means that whatever timed out eventually finished
anyways. The problem with this is that s/w cannot conclude which
context caused the problem as maybe more switches occurred before
intr is handled.
Bug 2092051
Bug 2429295
Bug 2484211
Bug 1890287
Change-Id: Ia79bee6e860fb179ee39024c963671d4f8245227
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2030866
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The functions gk20a_dump_eng_status and gv11b_dump_eng_status belongs
to engine_status HAL unit.
1) The corresponding declaration and definitions of the above functions
are moved from fifo_{arch} files to engine_status_{arch} files.
2) The corresponding HAL pointer .dump_eng_status is moved from
fifo to engine_status HAL unit.
3) gv11b_dump_eng_status is now based to gv100b_dump_eng_status
4) Small changes in the files for ENGINE_STATUS such as correction of
HEADER DEFINES etc
Jira NVGPU-1315
Change-Id: I7fc06eab97206bc3b78c6f5c7aa30fa2c034961c
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2033632
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The corresponding HAL pointer for gk20a_fifo_wait_engine_idle is not
being invoked anywhere and hence they are removed from the code.
The function gk20a_fifo_wait_engine_idle belongs to engine unit and is
only called in a non-safe build, hence its moved to engine unit and is
restricted by a non-safe build flag NVGPU_ENGINE
Also, gk20a_fifo_wait_engine_idle is renamed to nvgpu_engine_wait_for_idle
Jira NVGPU-1315
Change-Id: Ie550c7e46a4284dfe368859d828b1994df34185f
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2033631
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The following functions belong to engine unit and are moved
gk20a_fifo_enable_engine_activity
gk20a_fifo_enable_all_engine_activity
gk20a_fifo_disable_engine_activity
gk20a_fifo_disable_all_engine_activity
These are renamed by replacing gk20a_fifo with nvgpu_engine as prefix.
These functions are only invoked by linux build and not required for
safety build and hence they are defined when
-DNVGPU_ENGINE is enabled.
Jira NVGPU-1315
Change-Id: I39d820879bb55b40e754526c657d794930a4b6a1
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2032606
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
is_fault_engine_subid_gpc HAL pointer belongs to engine HAL unit instead of
fifo. This patch moves the HAL pointer to a newly constructed engine
HAL unit.
The following new files are added under HAL/fifo/
engines_gm20b.h
engines_gm20b.c
engines_gv11b.h
engines_gv11b.c
Jira NVGPU-1315
Change-Id: If28686bf7350563b06b13348a9fe3ef0099c35b2
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2031659
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Pre-volta, cbc config is part of hw ltc and from volta onwards this is
moved to hw fb. Because of this, cbc_init functions are present in both
cbc unit and fb unit. Pre-volta uses cbc_init from cbc unit and from
volta onwards it uses cbc_init from fb unit.
With this patch, unified two cbc_init functions to cbc unit and created
new fb hal for cbc_configure. cbc unit uses fb hal for cbc_config and
fb unit is independent of cbc unit.
JIRA NVGPU-2897
Change-Id: Ib62f0b08547b031bcb5011c837e43c74931a22fe
Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2030906
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Create Compression Bit Cache(CBC) unit to have comptags
cache related functionality in one place. In this patch
Moved following gpu ops from ltc to cbc and renamed accordingly:
void (*init)(struct gk20a *g, struct gr_gk20a *gr);
u64 (*get_base_divisor)(struct gk20a *g);
int (*alloc_comptags)(struct gk20a *g, struct gr_gk20a *gr);
int (*ctrl)(struct gk20a *g, enum gk20a_cbc_op op,
u32 min, u32 max);
u32 (*fix_config)(struct gk20a *g, int base);
To avoid ambiguity renamed function pointer from
init_comptags to alloc_comptags.
Moved following function from ltc.h to cbc.h:
nvgpu_ltc_alloc_cbc -> nvgpu_cbc_alloc
Also changed file name that implemented
nvgpu_cbc_alloc functionality from
os/ltc.c -> os/linux-cbc.c
JIRA NVGPU-2897
Change-Id: Ide32a98567e9a3f0a784d62221a6f484f8343e53
Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2030194
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
In case of FBPA we need to consider mask of active FBPAs on dGPUs.
For that we have GR unit HAL g->ops.gr.add_ctxsw_reg_pm_fbpa()
Generic support to consider active mask of unit need not be in a HAL,
move it to common code in add_ctxsw_buffer_map_entries_subunits() itself
This API now supports providing active_unit_mask as its parameter
In case we don't need to consider unit mask caller will simply pass
~U32(0U) to indicate all units are active
In case of FBPA, add a new HAL g->ops.gr.hwpm_pm.get_active_fbpa_mask()
which gets mask of active FBPAs, and pass this value to common API
add_ctxsw_buffer_map_entries_subunits()
Jira NVGPU-2895
Change-Id: I0d208ce53abcd36929c25a4d248868d6eaa5c70d
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2069472
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Create a new HAL unit hal.gr.hwpm_map that provides chip specific
support to common.gr.hwpm_map unit
We currently have common.gr HAL g->ops.gr.add_ctxsw_reg_perf_pma()
to handle chip specific alignment of perf_pma list
We only adjust the offset of list and remaining code is same
Hence delete above HAL, and add new HAL under hal.gr.hwpm_map
g->ops.gr.hwpm_map.align_regs_perf_pma() which returns correct
alignment if HAL is defined
Remove gr_gv100_add_ctxsw_reg_perf_pma() and
gr_gk20a_add_ctxsw_reg_perf_pma() APIs since they are no longer used
Simplify perf_pma parsing by fixing alignment with new HAL and then
directly calling add_ctxsw_buffer_map_entries()
Jira NVGPU-2895
Change-Id: I1852db846e1f5441e482028c79a3f39c5142b0c2
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2069471
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Loading of ctx/method init values from NET image is done in GR boot
sequence and also in golden image creation
Doing this during GR boot creation is unnecessary since those writes
are anyways part of golden image itself
Hence remove those method loads from gk20a_init_gr_setup_hw()
Also remove g->ops.gr.commit_global_timeslice() call since that too
is covered during golden image creation
Since above code is removed disabling and restoring fe_go_idle timeout
is also not needed
Jira NVGPU-1885
Change-Id: Ic6eb4bea7ceb36bb1420f58446785cefe25066df
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2034042
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add new power/clock gating functions that can be called by
other units.
New clock_gating functions will reside in cg.c under
common/power_features/cg unit.
New power gating functions will reside in pg.c under
common/power_features/pg unit.
Use nvgpu_pg_elpg_disable and nvgpu_pg_elpg_enable to disable/enable
elpg and also in gr_gk20a_elpg_protected macro to access gr registers.
Add cg_pg_lock to make elpg_enabled, elcg_enabled, blcg_enabled
and slcg_enabled thread safe.
JIRA NVGPU-2014
Change-Id: I00d124c2ee16242c9a3ef82e7620fbb7f1297aff
Signed-off-by: Seema Khowala <seemaj@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2025493
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move below calls to gr/fecs_trace unit
gk20a_fecs_trace_bind_channel()
gk20a_fecs_trace_unbind_channel()
And rename them to
nvgpu_gr_fecs_trace_bind_channel()
nvgpu_gr_fecs_trace_unbind_channel()
We are not accessing any fifo/ch/tsg construct in gr/fecs_trace unit
hence update parameter list of above APIs to receive inst_block,
gr_ctx, subctx pointers directly instead of receiving channel_gk20a
Delete gk20a/fecs_trace_gk20a.* files since they are no longer
required. All the contents in those files are now moved to gr/fecs_trace
unit
Jira NVGPU-1880
Change-Id: I7ef9f0b66781b45155035237172ae400f02740e4
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2032707
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Create new unit common.gr.hwpm_map with source file common/gr/hwpm_map.c
and public header include/nvgpu/gr/hwpm_map.h
Move all APIs in gr_gk20a.c that handle hwpm_map functionality to this
new unit. This unit now exposes below struct that is included in struct
gr_gk20a
struct nvgpu_gr_hwpm_map {
u32 pm_ctxsw_image_size;
u32 count;
struct ctxsw_buf_offset_map_entry *map;
bool init;
}
Expose below APIs
nvgpu_gr_hwpm_map_init() - initialize HWPM map meta-data with given size
nvgpu_gr_hwpm_map_deinit() - deinitialize HWPM map
nvgpu_gr_hwmp_map_find_priv_offset() - find a given offset in the map
The sequence to create the map by reading various netlist segments is
moved to a static API nvgpu_gr_hwpm_map_create()
Jira NVGPU-2894
Change-Id: I07d31169d2ff18a496eb79a726027b847d5f0e06
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2032777
GVS: Gerrit_Virtual_Submit
Reviewed-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This reverts commit f67bc51e51.
Currently a fifo_runlist_info_gk20a structure is allocated and
initialized for each possible runlist. But only a few runlists
are actually used.
Skip allocation and initialization of inactive runlists. Active
runlists info is stored in the active_runlist_info array.If a
runlist is active, then runlist_info[runlist_id] points to one
entry in active_runlist_info. Otherwise, runlist_info[runlist_id]
is NULL.
Operations that used to walk through all runlists are modified
to walk though active runlists only.
Bug 2470115
Bug 2522374
Change-Id: I98253ebebb4b1ba5957b57329820b94444b9d41b
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2030409
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
This reverts commit ade1d50cbe.
Currently a fifo_runlist_info_gk20a structure is allocated and
initialized for each possible runlist. But only a few runlists
are actually used.
Use an array of pointers to runlists in fifo_gk20a. The array
keeps existing indexing by runlist_id. In this patch a context
is still allocated for each possible runlist, but follow up
patch will allow to skip context allocation for inactive
runlists.
Bug 2470115
Bug 2522374
Change-Id: I0deb6981bc6f5152bdf121f0a44429748aa14687
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2030407
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
