Below hals are used to get preemption buffer sizes
g->ops.gr.get_ctx_spill_size()
g->ops.gr.get_ctx_pagepool_size()
g->ops.gr.get_ctx_betacb_size()
g->ops.gr.get_ctx_attrib_cb_size()
Move them to hal.gr.init unit
Copy over corresponding gp10b/gv11b definitions
Remove pagepool and attrib_cb size hals from gv11b since gv11b can
re-use gp10b hals
Add spill size and betacb size hals for gv100 and tu104 too since
register values are different on those chips
Remove g->ops.gr.init_gfxp_rtv_cb() hal and replace it by
g->ops.gr.init.get_gfxp_rtv_cb_size() which returns the size of RTV
cb size
Jira NVGPU-2961
Change-Id: I3f2f973c120dbfd22067366f87d06b5c9162defb
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2084747
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove use of struct gk20a and struct gr_gk20a from common.gr.config
hal functions.
This requires a reference to struct gk20a *g for many nvgpu_* ops. Also,
nvgpu_gr_config is updated to include sm_count_per_tpc.
JIRA NVGPU-1884
Change-Id: I874c2b3970d97ef3940b74d8ef121a7261061670
Signed-off-by: Nitin Kumbhar <nkumbhar@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2075681
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Move g->ops.gr.get_global_ctx_cb_buffer_size() and
g->ops.gr.get_global_ctx_pagepool_buffer_size() hals to hal.gr.init
unit
Move corresponding hal definitions to hal.gr.init unit
Jira NVGPU-2961
Change-Id: Ifff3e2073f6d9bca5b37244f7e107bad885e7ca7
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2077215
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Add new unit vgpu subctx under common/vgpu/gr to manage
GR subcontext. This unit provides interfaces to allocate
and free subctx header.
Rename vgpu_subctx_gv11b* files to subctx_vgpu* files
renaming functions vgpu_gv11b_alloc_subctx_header to
vgpu_alloc_subctx_header and vgpu_gv11b_free_subctx_header
to vgpu_free_subctx_header which are called only if
NVGPU_SUPPORT_TSG_SUBCONTEXTS is enabled or free_channel_ctx_header
HAL op is set which is set only for gv11b for virtualization.
Also assign fifo HAL op free_channel_ctx_header to
vgpu_channel_free_ctx_header for vgpu gv11b which in turn
calls vgpu_free_subctx_header.
Jira GVSCI-334
Change-Id: Ib46e7be911632eba01cd21881077683b795f8bad
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2075872
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Remove below variables from struct gr_gk20a
u32 bundle_cb_default_size;
u32 min_gpm_fifo_depth;
u32 bundle_cb_token_limit;
u32 attrib_cb_default_size;
u32 alpha_cb_default_size;
u32 attrib_cb_gfxp_default_size;
u32 attrib_cb_gfxp_size;
u32 attrib_cb_size;
u32 alpha_cb_size;
Instead add below hals in hal.gr.init unit to get all of above sizes
u32 (*get_bundle_cb_default_size)(struct gk20a *g);
u32 (*get_min_gpm_fifo_depth)(struct gk20a *g);
u32 (*get_bundle_cb_token_limit)(struct gk20a *g);
u32 (*get_attrib_cb_default_size)(struct gk20a *g);
u32 (*get_alpha_cb_default_size)(struct gk20a *g);
u32 (*get_attrib_cb_gfxp_default_size)(struct gk20a *g);
u32 (*get_attrib_cb_gfxp_size)(struct gk20a *g);
u32 (*get_attrib_cb_size)(struct gk20a *g, u32 tpc_count);
u32 (*get_alpha_cb_size)(struct gk20a *g, u32 tpc_count);
u32 (*get_global_attr_cb_size)(struct gk20a *g, u32 max_tpc);
Define these hals for all gm20b/gp10b/gv11b/gv100/tu104 chips
Also add hal.gr.init support for gv100 chip
Remove all accesses to variables from struct gr_gk20a and start using
newly defined hals
Remove below hals to initialize sizes since they are no more required
g->ops.gr.bundle_cb_defaults(g);
g->ops.gr.cb_size_default(g);
g->ops.gr.calc_global_ctx_buffer_size(g);
Also remove definitions of above hals from all the chip files
Jira NVGPU-2961
Change-Id: I130b578ababf22328d68fe19df581e46aebeccc9
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2077214
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>
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>
MISRA Rule-17.7 requires the return value of all functions to be used.
Fix is either to use the return value or change the function to return
void. This patch ensures that WARN and WARN_ON always return void; and
introduces a new nvgpu_do_assert construct to trigger the equivalent
of WARN_ON(true) so that stack can be dumped (depends on OS support)
JIRA NVGPU-677
Change-Id: Ie2312c5588ceb5b1db825d15a096149b63b69af4
Signed-off-by: Nicolas Benech <nbenech@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2018706
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
- rename vgpu_gr_gm20b_init_cyclestats() to vgpu_gr_init_cyclestats()
moving to gr_vgpu.c common to all vgpu chips.
- rename vgpu_gr_gp10b_init_ctxsw_preemption_mode() to
vgpu_gr_init_ctxsw_preemption_mode() moving to ctx_vgpu.c common
to all vgpu chips.
- rename vgpu_gr_gp10b_set_ctxsw_preemption_mode() to
vgpu_gr_set_ctxsw_preemption_mode() moving to ctx_vgpu.c common
to all vgpu chips.
- rename vgpu_gr_gp10b_set_preemption_mode() to
vgpu_gr_set_preemption_mode() moving to ctx_vgpu.c common
to all vgpu chips.
- rename vgpu_gr_gp10b_init_ctx_state() to vgpu_gr_init_ctx_state()
moving to ctx_vgpu.c common to all vgpu chips.
- combine vgpu_gr_gv11b_commit_ins() to vgpu_gr_commit_inst()
executing alloc/free subctx header code only if chip supports
subctx.
- remove inclusion of hw header files from vgpu gr code by
introducing hal ops for the following:
- alloc_global_ctx_buffers:
- hal op for getting global ctx cb buffer
- hal op for getting global ctx pagepool buffer size
- set_ctxsw_preemption_mode:
- hal op for getting ctx spill size
- hal op for getting ctx pagepool size
- hal op for getting ctx betacb size
- hal op for getting ctx attrib cb size
These chip specific function definitions are currently implemented in
chip specific gr files which will need to be moved to hal units.
Also use these hal ops for corresponding functions for native. This
makes gr_gv11b_set_ctxsw_preemption_mode() function redundant. Use
gr_gp10b_set_ctxsw_preemption_mode() for gv11b as well.
Jira GVSCI-334
Change-Id: I60be86f932e555176a972c125e3ea31270e6cba7
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2025428
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Create a new directory gr under common vgpu path moving all
vgpu common gr files under that directory.
Move vgpu gr ctx implementations to a new file ctx_vgpu.c
and create corresponding header file.
Also modify parameters of some functions in ctx_vgpu.c to
not access channel/tsg/fifo constructs.
Jira GVSCI-334
Change-Id: I3498b10db62194df2871eb81fc5c5cb04b42abc3
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/2013350
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
