Add new hal g->ops.gr.init.get_patch_slots() in hal.gr.init unit to get
patch slot count. Remove g->ops.gr.get_patch_slots().
Move corresponding functions to hal.gr.init unit
This hal does not need to be set for vGPU since it is not called in
that case
Jira NVGPU-2961
Change-Id: Ide488ae93af53a755da95faa268563070bd24bea
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2097533
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Many of the functions in common.gr.obj_ctx and common.gr.fs_state units
directly dereference struct gr_gk20a to obtain other structures
e.g. API nvgpu_gr_obj_ctx_set_ctxsw_preemption_mode() obtains pointer
to nvgpu_gr_config struct by direct access g->gr.config
Such accesses add dependency of these units on gr.h and hence create
circular dependency with common.gr.gr unit
Fix this by receiving all required structures in the function parameter
list itself
Jira NVGPU-1886
Change-Id: Iee973ae33fc7e1707b8f025ad61683f725dedb53
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2094995
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Created class unit under hal and moved all valid class check related
functionality to this unit. Moved all class defs from gr to a new header
include/nvgpu/class.h.
Moved following hals from gr to newly created class unit:
bool (*is_valid_class)(struct gk20a *g, u32 class_num); -->
bool (*is_valid)(u32 class_num);
bool (*is_valid_gfx_class)(struct gk20a *g, u32 class_num); -->
bool (*is_valid_gfx)(u32 class_num);
bool (*is_valid_compute_class)(struct gk20a *g, u32 class_num); -->
bool (*is_valid_compute)(u32 class_num);
JIRA NVGPU-3109
Change-Id: I01123e9b984613d4bddb2d8cf23d63410e212408
Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2095542
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vinod Gopalakrishnakurup <vinodg@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Added the following HALs
- ramin.base_shift
- ramin.alloc_base
Use above HALs in mm, instead of using hw definitions.
Defined nvgpu_inst_block_ptr to
- get inst_block address,
- shift if by base_shift
- assert upper 32 bits are 0
- return lower 32 bits
Added missing #include for <nvgpu/mm.h>
Jira NVGPU-3015
Change-Id: I558a6f4c9fbc6873a5b71f1557ea9ad8eae2778f
Signed-off-by: Thomas Fleury <tfleury@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2077840
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
g->ops.gr.commit_inst() HAL is used to commit gr context to engine
There is nothing h/w specific in HAL implementation anymore and the
sequence can be unified by checking support for subcontext feature
Remove gr_gv11b_commit_inst() and gr_gk20a_commit_inst() and unify
the sequence in nvgpu_gr_obj_ctx_commit_inst() API in common.gr.obj_ctx
unit. Use this API instead of hal.
Channel subcontext is now directly allocated in gk20a_alloc_obj_ctx()
vGPU code will directly call vGPU implementation vgpu_gr_commit_inst()
Delete the hal apis Since they are no longer needed
Jira NVGPU-1887
Change-Id: Iae1f6be4ab52e3e8628f979f477a300e65c92200
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2090497
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
nvgpu_gr_init_fs_state is right now defined in common.gr.gr unit
This API also needs to be called from common.gr.obj_ctx unit so obj_ctx
unit depends on gr unit for this.
common.gr.gr unit already depends on common.gr.obj_ctx for context
initialization. So this causes a circular dependency
Fix this by moving this API to new standalone unit common.gr.fs_state
Rename it to nvgpu_gr_fs_state_init
Jira NVGPU-1887
Change-Id: I88ca8e1a7bc3c544459462493116f95d92b9ab01
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2090496
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move all fecs methods related code to gr falcon unit and handle it
through generic gr.falocn.ctrl_ctxsw hal.
Following methods are moved from gr_gk20a.c to gr falcon unit.
fecs method and corresponding new fecs method def in gr_falcon.h:
gr_fecs_method_push_adr_discover_image_size_v ->
NVGPU_GR_FALCON_METHOD_CTXSW_DISCOVER_IMAGE_SIZE
gr_fecs_method_push_adr_discover_pm_image_size_v ->
NVGPU_GR_FALCON_METHOD_CTXSW_DISCOVER_PM_IMAGE_SIZE
gr_fecs_method_push_adr_discover_reglist_image_size_v ->
NVGPU_GR_FALCON_METHOD_REGLIST_DISCOVER_IMAGE_SIZE
gr_fecs_method_push_adr_set_reglist_bind_instance_v ->
NVGPU_GR_FALCON_METHOD_REGLIST_BIND_INSTANCE
gr_fecs_method_push_adr_set_reglist_virtual_address_v ->
NVGPU_GR_FALCON_METHOD_REGLIST_SET_VIRTUAL_ADDRESS
Following fecs methods are moved from obj_ctx.c to gr falcon unit.
gr_fecs_method_push_adr_bind_pointer_v ->
NVGPU_GR_FALCON_METHOD_ADDRESS_BIND_PTR
gr_fecs_method_push_adr_wfi_golden_save_v ->
NVGPU_GR_FALCON_METHOD_GOLDEN_IMAGE_SAVE
Following fecs methods are moved from gr_gp10b.c to gr falcon unit.
gr_fecs_method_push_adr_discover_preemption_image_size_v ->
NVGPU_GR_FALCON_METHOD_PREEMPT_IMAGE_SIZE
gr_fecs_method_push_adr_configure_interrupt_completion_option_v ->
NVGPU_GR_FALCON_METHOD_CONFIGURE_CTXSW_INTR
Following fecs method is moved from zcull_gm20b.c:
gr_fecs_method_push_adr_discover_zcull_image_size_v ->
NVGPU_GR_FALCON_METHOD_CTXSW_DISCOVER_ZCULL_IMAGE_SIZE
Following fecs method is moved from fecs_trace_gp10b.c:
gr_fecs_method_push_adr_write_timestamp_record_v
-> NVGPU_GR_FALCON_METHOD_FECS_TRACE_FLUSH
Added new HAL in gr falcon for moving fecs_current_ctx_data from
gr_gk20a.c to gr_falcon_gm20b.c.
u32 (*get_fecs_current_ctx_data)(struct gk20a *g,
struct nvgpu_mem *inst_block);
Added overlay for gm20b_gr_falcon_ctrl_ctxsw in newly added in
gr_falcon_gp10b.c for handling gp10b+ specific fecs methods:
gp10b_gr_falcon_ctrl_ctxsw
JIRA NVGPU-1881
Change-Id: I662d06f5176b29e6837d63c25e42de67505d48f5
Signed-off-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2087148
Reviewed-by: svc-misra-checker <svc-misra-checker@nvidia.com>
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
nvgpu_gr_obj_ctx_alloc_golden_ctx_image() right now uses global variable
g->gr.ctx_vars.golden_image_size to get size of golden image which is
then used to initialize local golden image
Use nvgpu_gr_obj_ctx_get_golden_image_size() API to get the size instead
of using global variable
Jira NVGPU-1887
Change-Id: I39b0cfe8f051c828e2b279c1836a259962c3d3bd
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2089581
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-by: Vinod Gopalakrishnakurup <vinodg@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
These HALs are used to initialize and set preeemption modes
g->ops.gr.init_ctxsw_preemption_mode()
g->ops.gr.set_ctxsw_preemption_mode()
g->ops.gr.update_ctxsw_preemption_mode()
They are all h/w independent except for the functional support for
GFXP/CILP preemption support which is only present on gp10b+ chips
Add a characteristics flag NVGPU_SUPPORT_PREEMPTION_GFXP for these
preemption modes and set this flag for gp10b+ chips
Use this flag and unify all above HALs into below common functions
nvgpu_gr_obj_ctx_init_ctxsw_preemption_mode()
nvgpu_gr_obj_ctx_set_ctxsw_preemption_mode()
nvgpu_gr_obj_ctx_update_ctxsw_preemption_mode()
vGPU specific code also directly calls below vGPU specific APIs
vgpu_gr_init_ctxsw_preemption_mode()
vgpu_gr_set_ctxsw_preemption_mode()
g->ops.gr.update_ctxsw_preemption_mode() is not needed for vGPU since
it is handled by vserver
Above g->ops.gr.*_ctxsw_preemption_mode() HALs are no more required
hence delete them
Jira NVGPU-1887
Change-Id: I9b3164bcf01e5e3c27e52369c9364e0ee23a9662
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2088507
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
gr_gk20a_commit_global_ctx_buffers() is h/w independent, hence move it
to common unit common.gr.obj_ctx and rename it as
nvgpu_gr_obj_ctx_commit_global_ctx_buffers()
Delete g->ops.gr.commit_global_ctx_buffers hal
Jira NVGPU-1887
Change-Id: If1c840237b8ba2c13bed40a4315810073756aeb9
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2088506
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add a new unit common.gr.obj_ctx which allocates and initializes GR
context. This unit also takes care of creating global golden image
used to initialize every context.
Add private header obj_ctx_priv.h that defines struct
nvgpu_gr_obj_ctx_golden_image
Add public header obj_ctx.h that exposes functions supported by new unit
This unit now exposes below API to allocate and initialize context
nvgpu_gr_obj_ctx_alloc()
Remove below functions from gk20a/gr_gk20a.c and move them to new unit
with below renames
gr_gk20a_fecs_ctx_bind_channel() -> nvgpu_gr_obj_ctx_bind_channel()
gr_gk20a_fecs_ctx_image_save() -> nvgpu_gr_obj_ctx_image_save()
gk20a_init_sw_bundle() -> nvgpu_gr_obj_ctx_alloc_sw_bundle()
gr_gk20a_alloc_gr_ctx() -> nvgpu_gr_obj_ctx_gr_ctx_alloc()
gr_gk20a_init_golden_ctx_image() ->
nvgpu_gr_obj_ctx_alloc_golden_ctx_image()
Use new APIs in gk20a_alloc_obj_ctx() to allocate context
For now this unit includes <nvgpu/gr/gr.h> and some h/w headers.
But they will be removed in follow up patches
Jira NVGPU-1887
Change-Id: Ib95ec1c19c5b74810f85c2feed8fdd63889d3d22
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2087662
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Alex Waterman <alexw@nvidia.com>
Reviewed-by: Vinod Gopalakrishnakurup <vinodg@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
