Files
linux-nvgpu/drivers/gpu/nvgpu/include/nvgpu/gops/debugger.h
Deepak Nibade 869735cda4 gpu: nvgpu: add dynamic allowlist support
Add gv11b and tu104 HALs to get allowed  HWPM resource register ranges,
offsets, and stride meta data.

Add new enum nvgpu_pm_resource_hwpm_register_type for HWPM register
type. Add new struct nvgpu_pm_resource_register_range_map to store all
the register ranges for HWPM resources. Add pointer of map in struct
nvgpu_profiler_object along with map entry count.

Add new API nvgpu_profiler_build_regops_allowlist() to build the regops
allowlist dynamically while binding the resources. Map entry count is
received with get_pm_resource_register_range_map_entry_count() and only
those resource ranges are added for which resource is reserved by
profiler object.

Add nvgpu_profiler_destroy_regops_allowlist() to destroy the allowlist
while unbinding the resources.

Add static functions allowlist_range_search() to search a register
offset in HWPM resource ranges. Add another static function
allowlist_offset_search() to search the offset in per-resource offset
list.

Add nvgpu_profiler_validate_regops_allowlist() that accepts an offset
value, checks if it is in allowed ranges using allowlist_range_search()
and then checks if offset is in allowlist using allowlist_offset_search().

Update gops.regops.exec_regops() to receive profiler object pointer as
a parameter.

Invoke nvgpu_profiler_validate_regops_allowlist() from
validate_reg_ops() if prof pointer is not-null. This will be true only
for new profiler stack and not legacy profilers.

In gr_exec_ctx_ops(), skip regops execution if offset is invalid.

Bug 2510974
Jira NVGPU-5360

Change-Id: I40acb91cc37508629c83106ea15b062250bba473
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2460001
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
Reviewed-by: svc-mobile-cert <svc-mobile-cert@nvidia.com>
Reviewed-by: svc-mobile-misra <svc-mobile-misra@nvidia.com>
Reviewed-by: Antony Clince Alex <aalex@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
GVS: Gerrit_Virtual_Submit
2021-01-05 12:38:06 -08:00

116 lines
5.1 KiB
C

/*
* Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
#ifndef NVGPU_GOPS_DEBUGGER_H
#define NVGPU_GOPS_DEBUGGER_H
#ifdef CONFIG_NVGPU_DEBUGGER
struct gops_regops {
int (*exec_regops)(struct gk20a *g,
struct nvgpu_tsg *tsg,
struct nvgpu_profiler_object *prof,
struct nvgpu_dbg_reg_op *ops,
u32 num_ops,
u32 *flags);
const struct regop_offset_range* (
*get_global_whitelist_ranges)(void);
u64 (*get_global_whitelist_ranges_count)(void);
const struct regop_offset_range* (
*get_context_whitelist_ranges)(void);
u64 (*get_context_whitelist_ranges_count)(void);
const u32* (*get_runcontrol_whitelist)(void);
u64 (*get_runcontrol_whitelist_count)(void);
u32 (*get_hwpm_perfmon_register_stride)(void);
u32 (*get_hwpm_router_register_stride)(void);
u32 (*get_hwpm_pma_channel_register_stride)(void);
u32 (*get_hwpm_pma_trigger_register_stride)(void);
u32 (*get_smpc_register_stride)(void);
u32 (*get_cau_register_stride)(void);
const u32 *(*get_hwpm_perfmon_register_offset_allowlist)(u32 *count);
const u32 *(*get_hwpm_router_register_offset_allowlist)(u32 *count);
const u32 *(*get_hwpm_pma_channel_register_offset_allowlist)(u32 *count);
const u32 *(*get_hwpm_pma_trigger_register_offset_allowlist)(u32 *count);
const u32 *(*get_smpc_register_offset_allowlist)(u32 *count);
const u32 *(*get_cau_register_offset_allowlist)(u32 *count);
const struct nvgpu_pm_resource_register_range *
(*get_hwpm_perfmon_register_ranges)(u32 *count);
const struct nvgpu_pm_resource_register_range *
(*get_hwpm_router_register_ranges)(u32 *count);
const struct nvgpu_pm_resource_register_range *
(*get_hwpm_pma_channel_register_ranges)(u32 *count);
const struct nvgpu_pm_resource_register_range *
(*get_hwpm_pma_trigger_register_ranges)(u32 *count);
const struct nvgpu_pm_resource_register_range *
(*get_smpc_register_ranges)(u32 *count);
const struct nvgpu_pm_resource_register_range *
(*get_cau_register_ranges)(u32 *count);
const struct nvgpu_pm_resource_register_range *
(*get_hwpm_perfmux_register_ranges)(u32 *count);
};
struct gops_debugger {
void (*post_events)(struct nvgpu_channel *ch);
int (*dbg_set_powergate)(struct dbg_session_gk20a *dbg_s,
bool disable_powergate);
};
struct gops_perf {
void (*enable_membuf)(struct gk20a *g, u32 size, u64 buf_addr);
void (*disable_membuf)(struct gk20a *g);
void (*bind_mem_bytes_buffer_addr)(struct gk20a *g, u64 buf_addr);
void (*init_inst_block)(struct gk20a *g,
struct nvgpu_mem *inst_block);
void (*deinit_inst_block)(struct gk20a *g);
void (*membuf_reset_streaming)(struct gk20a *g);
u32 (*get_membuf_pending_bytes)(struct gk20a *g);
void (*set_membuf_handled_bytes)(struct gk20a *g,
u32 entries, u32 entry_size);
bool (*get_membuf_overflow_status)(struct gk20a *g);
u32 (*get_pmmsys_per_chiplet_offset)(void);
u32 (*get_pmmgpc_per_chiplet_offset)(void);
u32 (*get_pmmfbp_per_chiplet_offset)(void);
int (*update_get_put)(struct gk20a *g, u64 bytes_consumed,
bool update_available_bytes, u64 *put_ptr, bool *overflowed);
const u32 *(*get_hwpm_sys_perfmon_regs)(u32 *count);
const u32 *(*get_hwpm_fbp_perfmon_regs)(u32 *count);
const u32 *(*get_hwpm_gpc_perfmon_regs)(u32 *count);
void (*init_hwpm_pmm_register)(struct gk20a *g);
void (*get_num_hwpm_perfmon)(struct gk20a *g, u32 *num_sys_perfmon,
u32 *num_fbp_perfmon,
u32 *num_gpc_perfmon);
void (*set_pmm_register)(struct gk20a *g, u32 offset, u32 val,
u32 num_chiplets, u32 chiplet_stride, u32 num_perfmons);
void (*reset_hwpm_pmm_registers)(struct gk20a *g);
void (*pma_stream_enable)(struct gk20a *g, bool enable);
void (*disable_all_perfmons)(struct gk20a *g);
int (*wait_for_idle_pmm_routers)(struct gk20a *g);
int (*wait_for_idle_pma)(struct gk20a *g);
};
struct gops_perfbuf {
int (*perfbuf_enable)(struct gk20a *g, u64 offset, u32 size);
int (*perfbuf_disable)(struct gk20a *g);
int (*init_inst_block)(struct gk20a *g);
void (*deinit_inst_block)(struct gk20a *g);
int (*update_get_put)(struct gk20a *g, u64 bytes_consumed, u64 *bytes_available,
void *cpuva, bool wait, u64 *put_ptr, bool *overflowed);
};
#endif
#endif /* NVGPU_GOPS_DEBUGGER_H */