Files
linux-nvgpu/drivers/gpu/nvgpu/os/linux/os_linux.h
Deepak Nibade 969b901999 gpu: nvgpu: create device/context profiler dev nodes
Create new dev nodes for device and context profilers. Example of dev
nodes on iGPU
/dev/nvhost-prof-dev-gpu - device scope profiler
/dev/nvhost-prof-ctx-gpu - context scope profiler

Add below APIs to open/close above dev nodes :
nvgpu_prof_dev_fops_open()
nvgpu_prof_ctx_fops_open()
nvgpu_prof_fops_release()

Add common API nvgpu_prof_fops_ioctl() to handle IOCTL call on these
dev nodes. Add IOCTL NVGPU_PROFILER_IOCTL_BIND_CONTEXT to bind the TSG
to profiler objects.

Add nvgpu_tsg_get_from_file() to retrieve TSG struct pointer from
file descriptor. Also store profiler object pointer into TSG struct.

Enable NVGPU_SUPPORT_PROFILER_V2_DEVICE capability on gv11b and tu104.
Note that this is not yet enabled for vGPU.
Keep NVGPU_SUPPORT_PROFILER_V2_CONTEXT capabiity disabled since this
will take longer to support.

Add new IOCTL NVGPU_PROFILER_IOCTL_UNBIND_CONTEXT so that userspace can
explicitly unbind the context and release the resources before closing
the profiler descriptor.

Add context_init flag to profiler object for book keeping.

Bug 2510974
Jira NVGPU-5360

Change-Id: Ie07e0cfd5a9da9d80008f79c955c7ef93b4bc60f
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2384354
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
2020-12-15 14:13:28 -06:00

212 lines
4.5 KiB
C

/*
* Copyright (c) 2017-2020, NVIDIA CORPORATION. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef NVGPU_OS_LINUX_H
#define NVGPU_OS_LINUX_H
#include <linux/cdev.h>
#include <linux/iommu.h>
#include <linux/hashtable.h>
#include <linux/notifier.h>
#include <linux/version.h>
#include <nvgpu/gk20a.h>
#include "cde.h"
#include "sched.h"
struct nvgpu_os_linux_ops {
struct {
void (*get_program_numbers)(struct gk20a *g,
u32 block_height_log2,
u32 shader_parameter,
int *hprog, int *vprog);
bool (*need_scatter_buffer)(struct gk20a *g);
int (*populate_scatter_buffer)(struct gk20a *g,
struct sg_table *sgt,
size_t surface_size,
void *scatter_buffer_ptr,
size_t scatter_buffer_size);
} cde;
struct {
int (*init_debugfs)(struct gk20a *g);
} clk;
struct {
int (*init_debugfs)(struct gk20a *g);
} therm;
struct {
int (*init_debugfs)(struct gk20a *g);
} fecs_trace;
struct {
int (*init_debugfs)(struct gk20a *g);
} volt;
struct {
int (*init_debugfs)(struct gk20a *g);
} s_param;
};
struct dgpu_thermal_alert {
struct workqueue_struct *workqueue;
struct work_struct work;
u32 therm_alert_irq;
u32 event_delay;
};
struct nvgpu_os_linux {
struct gk20a g;
struct device *dev;
struct dgpu_thermal_alert thermal_alert;
struct {
struct cdev cdev;
struct device *node;
} channel;
struct {
struct cdev cdev;
struct device *node;
/* see gk20a_ctrl_priv */
struct nvgpu_list_node privs;
/* guards modifications to the list and its contents */
struct nvgpu_mutex privs_lock;
} ctrl;
struct {
struct cdev cdev;
struct device *node;
} as_dev;
struct {
struct cdev cdev;
struct device *node;
} dbg;
struct {
struct cdev cdev;
struct device *node;
} prof;
struct {
struct cdev cdev;
struct device *node;
} prof_dev;
struct {
struct cdev cdev;
struct device *node;
} prof_ctx;
struct {
struct cdev cdev;
struct device *node;
} tsg;
struct {
struct cdev cdev;
struct device *node;
} ctxsw;
struct {
struct cdev cdev;
struct device *node;
} sched;
dev_t cdev_region;
struct devfreq *devfreq;
struct device_dma_parameters dma_parms;
atomic_t nonstall_ops;
struct work_struct nonstall_fn_work;
struct workqueue_struct *nonstall_work_queue;
struct resource *reg_mem;
void __iomem *regs;
void __iomem *regs_saved;
u64 regs_bus_addr;
struct resource *bar1_mem;
void __iomem *bar1;
void __iomem *bar1_saved;
void __iomem *usermode_regs;
void __iomem *usermode_regs_saved;
u64 usermode_regs_bus_addr;
struct nvgpu_os_linux_ops ops;
struct notifier_block nvgpu_reboot_nb;
#ifdef CONFIG_DEBUG_FS
struct dentry *debugfs;
struct dentry *debugfs_alias;
struct dentry *debugfs_ltc_enabled;
struct dentry *debugfs_timeouts_enabled;
struct dentry *debugfs_disable_bigpage;
struct dentry *debugfs_runlist_interleave;
struct dentry *debugfs_allocators;
struct dentry *debugfs_xve;
struct dentry *debugfs_kmem;
struct dentry *debugfs_hal;
struct dentry *debugfs_ltc;
struct dentry *debugfs_dump_ctxsw_stats;
#endif
DECLARE_HASHTABLE(ecc_sysfs_stats_htable, 5);
struct dev_ext_attribute *ecc_attrs;
struct gk20a_cde_app cde_app;
struct rw_semaphore busy_lock;
struct nvgpu_mutex dmabuf_priv_list_lock;
struct nvgpu_list_node dmabuf_priv_list;
bool init_done;
/** Debugfs knob for forcing syncpt support off in runtime. */
bool disable_syncpoints;
bool enable_platform_dbg;
};
static inline struct nvgpu_os_linux *nvgpu_os_linux_from_gk20a(struct gk20a *g)
{
return container_of(g, struct nvgpu_os_linux, g);
}
static inline struct device *dev_from_gk20a(struct gk20a *g)
{
return nvgpu_os_linux_from_gk20a(g)->dev;
}
#define INTERFACE_NAME "nvhost%s-gpu"
#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 0, 0)
#define totalram_size_in_mb (totalram_pages() >> (10 - (PAGE_SHIFT - 10)))
#else
#define totalram_size_in_mb (totalram_pages >> (10 - (PAGE_SHIFT - 10)))
#endif
#endif