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>
To avoid the other hal calls from gr_gv11b_init_fs_state
and gr_gm20b_init_fs_state hal, move the load_tpc_mask and
load_smid_config hal to nvgpu_gr_init_fs_state common gr function.
bes_zrop_setting and bes_crop_setting for active_ltcs is moved before
the nvgpu_gr_init_fs_state call from those hals.
replace gk20a_writel and gk20a_readl in modified hal function with
nvgpu_writel and nvgpu_readl.
JIRA NVGPU-1885
Change-Id: Ic0bf4a4bfa4da032f33bbe4af89031bbbdd9cd94
Signed-off-by: Vinod G <vinodg@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2072414
Reviewed-by: Seshendra Gadagottu <sgadagottu@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>
Access to falcon's EMEM has to be synchronized to ensure atomic access
to EMEM control and data registers. Add this locking.
Not all falcons support EMEM hence handle mutex based on the enabled
flag emem_supported that is set only for TU104 currently.
JIRA NVGPU-1993
Change-Id: Idaedfb564ea0068d4690a2717d7983eb2384a69f
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2030618
GVS: Gerrit_Virtual_Submit
Reviewed-by: Mahantesh Kumbar <mkumbar@nvidia.com>
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Earlier falcon HAL ops were embedded in the falcon structure. For clear
separation of common and HAL these ops will have to be accessed through
g->ops.falcon interfaces.
With these changes nvgpu_falcon_* functions directly call falcon gpu
ops functions for falcon. Falcon registers and HAL functions are
exported from falcon_gk20a.h. HAL files per platform are now
updated with base falcon functions.
Falcon software state such as is_falcon_supported, is_interrupt_enabled
and flcn_base are set from software init functions defined per chip.
JIRA NVGPU-2038
Change-Id: Ib1729d2833cd2c6c7b2c8ed7cbc17d4d6daeba73
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2023077
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>
In the commit "gpu: nvgpu: unit: update misc atomics to use gcc
builtins" the cmpxchg macro used by the "POSIX" build changed and
introduced a MISRA 17.3 violation for a macro parameter that needed
parentheses. This updates the macro to resolve this violation.
Change-Id: I16927ecaa751964f8c397c95086c663a683f8241
Signed-off-by: Philip Elcan <pelcan@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2070064
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Tejal Kudav <tkudav@nvidia.com>
Reviewed-by: Adeel Raza <araza@nvidia.com>
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>
Add VM unit tests for the following requirements:
- NVGPU-RQCD-45.C1: A valid GPU virtual address is/is not generated
for the buffer passed into nvgpu_vm_map().
- NVGPU-RQCD-45.C2: When a GPU virtual address is passed into the
nvgpu_vm_map() function the resulting GPU virtual address of the
map does/does not match the requested GPU virtual address.
JIRA NVGPU-1927
Change-Id: I7c9f7204772a611ff7baa56b6434a70d5b70cd27
Signed-off-by: Adeel Raza <araza@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2036213
Reviewed-by: Philip Elcan <pelcan@nvidia.com>
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Nicolas Benech <nbenech@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Some chips bypass the IOMMU on tegra. Essentially any chip using
nvlink will fall into this category.
This imposes certain oddities in the memory management for these
chips. For these chips we do not want nor need IOMMU mappings
and the overhead that comes with doing that. Instead nvgpu can
manage allocation of pages itself.
For contiguous memory nvgpu still does need to rely on the CMA.
As such this flag can be used for determining whether to use the
special nvgpu managed page allocation (for normal allocs) or the
DMA API (and therefor the CMA) for contiguous allocs.
Bug 200444660
Change-Id: I3dc4ba6ea9523f2a59966b13527d5a416aaa761a
Signed-off-by: Alex Waterman <alexw@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2071090
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The latest GPU uses nvlink and its own MMU to access memory,
instead of SMMU like others. So it doesn't go through IOMMU
framework to allocate physically non-contiguous memory. The
DMA API had a pair of downstream functions to allocate the
memory for this situation, but it is removed since it's not
likely acceptable for upstream kernel.
In order not to hack the dma-direct ops that by its meaning
is supposed to provide contiguous memory, this patch adds a
pair of memory-allocation functions inside the gpu driver,
since nvgpu is the only user.
This pair of functions are only used when GPU driver doesn't
go through either dma-direct (FORCE_CONTIGUOUS) or iommu. It
also requires GPU driver to map the non-contiguous pages.
Bug 200444660
Change-Id: I26678a3f8d63bba340872beeecbb7b0e1e7a35fa
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2029680
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The flag NVGPU_DMA_FORCE_CONTIGUOUS simply means that the memory
or the pages should be forced contiguous. Meanwhile, the other
flag NVGPU_DMA_PHYSICALLY_ADDRESSED means that the memory should
be contiguous from GPU perspective, either physically contiguous
when IOMMU is not used, or virtually contiguous by IOMMU.
Thus the NVGPU_DMA_FORCE_CONTIGUOUS flag is now redundant.
This patch cleans up the NVGPU_DMA_FORCE_CONTIGUOUS flag.
Bug 200444660
Change-Id: I63bb06fea728b34ec2c6f831504392d42c426d55
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2035403
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
The original free routine has three options:
if (NVGPU_DMA_NO_KERNEL_MAPPING)
dma_free_attrs(d, mem->aligned_size, mem->priv.pages,
else if (other flags)
dma_free_attrs(d, mem->aligned_size, mem->cpu_va,
else /* No flags */
dma_free_coherent(d, mem->aligned_size, mem->cpu_va,
The last dma_free_coherent() can be unwrapped to dma_free_attrs
with its dma_attrs=0, while the former two are identical except
cpu_addr. So this patch merges these three into one single call
but differentiate the cpu_addr and dma_attrs parameters.
Note that the dma_free_attrs returns 0 when flags is not set.
Bug 200444660
Change-Id: I92ec0390138c79c5109973e476ea0ea719d4e2b9
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2029679
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
vgpu_vm_init and vgpu_vm_remove are called directly from
common code if virtualization is supported. Introduce mm
HAL ops vm_as_alloc_share and vm_as_free_share and call
these functions through these HAL ops. Also rename these functions
from vgpu_vm_init to vgpu_vm_as_alloc_share and vgpu_vm_remove to
vgpu_vm_as_free_share as these function names are too generic and
rename to reflect their actual functionality.
For now these HAL ops are initialized only for vgpu.
Jira GVSCI-517
Change-Id: I7c5af1ab5a64ce562092f75b1488524e93e8f53f
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2032310
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>
Semantics of the engine bootloader bootstrap are to set falcon mailbox0
register to non-zero value and verify that it is cleared to ascertain
successful completion of bootstrap.
Read was done in the engine bl_bootstrap related functions. Hence move
the write as well to those functions.
JIRA NVGPU-1993
Change-Id: I6d04148fbf1d517f0af8b4cfc2ee144d38704647
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2034511
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
To validate the imem & dmem port being accessed by nvgpu, allowed ports
need to be known from hwcfg1 register. Update the hw header with these
to use for checking the valid ports in later patch.
JIRA NVGPU-1993
Change-Id: I1146a85d452d02fefcc75065a0cd546fff688fd2
Signed-off-by: Sagar Kamble <skamble@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2030622
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>
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>
