rtla/src/common.c

// SPDX-License-Identifier: GPL-2.0
#define _GNU_SOURCE

#include <pthread.h>
#include <signal.h>
#include <stdlib.h>
#include <string.h>
#include <getopt.h>
#include <sys/sysinfo.h>

#include "common.h"

struct osnoise_tool *trace_tool;
volatile int stop_tracing;
int nr_cpus;

static void stop_trace(int sig)
{
	if (stop_tracing) {
		/*
		 * Stop requested twice in a row; abort event processing and
		 * exit immediately
		 */
		if (trace_tool)
			tracefs_iterate_stop(trace_tool->trace.inst);
		return;
	}
	stop_tracing = 1;
	if (trace_tool) {
		trace_instance_stop(&trace_tool->trace);
		if (trace_tool->record)
			trace_instance_stop(&trace_tool->record->trace);
	}
}

/*
 * set_signals - handles the signal to stop the tool
 */
static void set_signals(struct common_params *params)
{
	signal(SIGINT, stop_trace);
	if (params->duration) {
		signal(SIGALRM, stop_trace);
		alarm(params->duration);
	}
}

/*
 * unset_signals - unsets the signals to stop the tool
 */
static void unset_signals(struct common_params *params)
{
	signal(SIGINT, SIG_DFL);
	if (params->duration) {
		alarm(0);
		signal(SIGALRM, SIG_DFL);
	}
}

/*
 * getopt_auto - auto-generates optstring from long_options
 */
int getopt_auto(int argc, char **argv, const struct option *long_opts)
{
	char opts[256];
	int n = 0;

	for (int i = 0; long_opts[i].name; i++) {
		if (long_opts[i].val < 32 || long_opts[i].val > 127)
			continue;

		if (n + 4 >= sizeof(opts))
			fatal("optstring buffer overflow");

		opts[n++] = long_opts[i].val;

		if (long_opts[i].has_arg == required_argument)
			opts[n++] = ':';
		else if (long_opts[i].has_arg == optional_argument) {
			opts[n++] = ':';
			opts[n++] = ':';
		}
	}

	opts[n] = '\0';

	return getopt_long(argc, argv, opts, long_opts, NULL);
}

/*
 * common_parse_options - parse common command line options
 *
 * @argc: argument count
 * @argv: argument vector
 * @common: common parameters structure
 *
 * Parse command line options that are common to all rtla tools.
 *
 * Returns: non zero if a common option was parsed, or 0
 * if the option should be handled by tool-specific parsing.
 */
int common_parse_options(int argc, char **argv, struct common_params *common)
{
	struct trace_events *tevent;
	int saved_state = optind;
	int c;

	static struct option long_options[] = {
		{"cpus",                required_argument,      0, 'c'},
		{"cgroup",              optional_argument,      0, 'C'},
		{"debug",               no_argument,            0, 'D'},
		{"duration",            required_argument,      0, 'd'},
		{"event",               required_argument,      0, 'e'},
		{"house-keeping",       required_argument,      0, 'H'},
		{"priority",            required_argument,      0, 'P'},
		{0, 0, 0, 0}
	};

	opterr = 0;
	c = getopt_auto(argc, argv, long_options);
	opterr = 1;

	switch (c) {
	case 'c':
		if (parse_cpu_set(optarg, &common->monitored_cpus))
			fatal("Invalid -c cpu list");
		common->cpus = optarg;
		break;
	case 'C':
		common->cgroup = 1;
		common->cgroup_name = parse_optional_arg(argc, argv);
		break;
	case 'D':
		config_debug = 1;
		break;
	case 'd':
		common->duration = parse_seconds_duration(optarg);
		if (!common->duration)
			fatal("Invalid -d duration");
		break;
	case 'e':
		tevent = trace_event_alloc(optarg);
		if (!tevent)
			fatal("Error alloc trace event");

		if (common->events)
			tevent->next = common->events;
		common->events = tevent;
		break;
	case 'H':
		common->hk_cpus = 1;
		if (parse_cpu_set(optarg, &common->hk_cpu_set))
			fatal("Error parsing house keeping CPUs");
		break;
	case 'P':
		if (parse_prio(optarg, &common->sched_param) == -1)
			fatal("Invalid -P priority");
		common->set_sched = 1;
		break;
	default:
		optind = saved_state;
		return 0;
	}

	return c;
}

/*
 * common_apply_config - apply common configs to the initialized tool
 */
int
common_apply_config(struct osnoise_tool *tool, struct common_params *params)
{
	int retval, i;

	if (!params->sleep_time)
		params->sleep_time = 1;

	retval = osnoise_set_cpus(tool->context, params->cpus ? params->cpus : "all");
	if (retval) {
		err_msg("Failed to apply CPUs config\n");
		goto out_err;
	}

	if (!params->cpus) {
		for (i = 0; i < nr_cpus; i++)
			CPU_SET(i, &params->monitored_cpus);
	}

	if (params->hk_cpus) {
		retval = sched_setaffinity(getpid(), sizeof(params->hk_cpu_set),
					   &params->hk_cpu_set);
		if (retval == -1) {
			err_msg("Failed to set rtla to the house keeping CPUs\n");
			goto out_err;
		}
	} else if (params->cpus) {
		/*
		 * Even if the user do not set a house-keeping CPU, try to
		 * move rtla to a CPU set different to the one where the user
		 * set the workload to run.
		 *
		 * No need to check results as this is an automatic attempt.
		 */
		auto_house_keeping(&params->monitored_cpus);
	}

	/*
	 * Set workload according to type of thread if the kernel supports it.
	 * On kernels without support, user threads will have already failed
	 * on missing fd, and kernel threads do not need it.
	 */
	retval = osnoise_set_workload(tool->context, params->kernel_workload);
	if (retval < -1) {
		err_msg("Failed to set OSNOISE_WORKLOAD option\n");
		goto out_err;
	}

	return 0;

out_err:
	return -1;
}


/**
 * common_threshold_handler - handle latency threshold overflow
 * @tool: pointer to the osnoise_tool instance containing trace contexts
 *
 * Executes the configured threshold actions (e.g., saving trace, printing,
 * sending signals). If the continue flag is set (--on-threshold continue),
 * restarts the auxiliary trace instances to continue monitoring.
 *
 * Return: 0 for success, -1 for error.
 */
int
common_threshold_handler(const struct osnoise_tool *tool)
{
	actions_perform(&tool->params->threshold_actions);

	if (!should_continue_tracing(tool->params))
		/* continue flag not set, break */
		return 0;

	/* continue action reached, re-enable tracing */
	if (tool->record && trace_instance_start(&tool->record->trace))
		goto err;
	if (tool->aa && trace_instance_start(&tool->aa->trace))
		goto err;

	return 0;

err:
	err_msg("Error restarting trace\n");
	return -1;
}

int run_tool(struct tool_ops *ops, int argc, char *argv[])
{
	struct common_params *params;
	enum result return_value = ERROR;
	struct osnoise_tool *tool;
	bool stopped;
	int retval;

	nr_cpus = get_nprocs_conf();
	params = ops->parse_args(argc, argv);
	if (!params)
		exit(1);

	tool = ops->init_tool(params);
	if (!tool) {
		err_msg("Could not init osnoise tool\n");
		goto out_exit;
	}
	tool->ops = ops;
	tool->params = params;

	/*
	 * Expose the tool to signal handlers so they can stop the trace.
	 * Otherwise, rtla could loop indefinitely when overloaded.
	 */
	trace_tool = tool;

	retval = ops->apply_config(tool);
	if (retval) {
		err_msg("Could not apply config\n");
		goto out_free;
	}

	retval = enable_tracer_by_name(tool->trace.inst, ops->tracer);
	if (retval) {
		err_msg("Failed to enable %s tracer\n", ops->tracer);
		goto out_free;
	}

	if (params->set_sched) {
		retval = set_comm_sched_attr(ops->comm_prefix, &params->sched_param);
		if (retval) {
			err_msg("Failed to set sched parameters\n");
			goto out_free;
		}
	}

	if (params->cgroup && !params->user_data) {
		retval = set_comm_cgroup(ops->comm_prefix, params->cgroup_name);
		if (!retval) {
			err_msg("Failed to move threads to cgroup\n");
			goto out_free;
		}
	}


	if (params->threshold_actions.present[ACTION_TRACE_OUTPUT] ||
	    params->end_actions.present[ACTION_TRACE_OUTPUT]) {
		tool->record = osnoise_init_trace_tool(ops->tracer);
		if (!tool->record) {
			err_msg("Failed to enable the trace instance\n");
			goto out_free;
		}
		params->threshold_actions.trace_output_inst = tool->record->trace.inst;
		params->end_actions.trace_output_inst = tool->record->trace.inst;

		if (params->events) {
			retval = trace_events_enable(&tool->record->trace, params->events);
			if (retval)
				goto out_trace;
		}

		if (params->buffer_size > 0) {
			retval = trace_set_buffer_size(&tool->record->trace, params->buffer_size);
			if (retval)
				goto out_trace;
		}
	}

	if (params->user_workload) {
		pthread_t user_thread;

		/* rtla asked to stop */
		params->user.should_run = 1;
		/* all threads left */
		params->user.stopped_running = 0;

		params->user.set = &params->monitored_cpus;
		if (params->set_sched)
			params->user.sched_param = &params->sched_param;
		else
			params->user.sched_param = NULL;

		params->user.cgroup_name = params->cgroup_name;

		retval = pthread_create(&user_thread, NULL, timerlat_u_dispatcher, &params->user);
		if (retval) {
			err_msg("Error creating timerlat user-space threads\n");
			goto out_trace;
		}
	}

	retval = ops->enable(tool);
	if (retval)
		goto out_trace;

	tool->start_time = time(NULL);
	set_signals(params);

	retval = ops->main(tool);
	if (retval)
		goto out_signals;

	if (params->user_workload && !params->user.stopped_running) {
		params->user.should_run = 0;
		sleep(1);
	}

	ops->print_stats(tool);

	actions_perform(&params->end_actions);

	return_value = PASSED;

	stopped = osnoise_trace_is_off(tool, tool->record) && !stop_tracing;
	if (stopped) {
		printf("%s hit stop tracing\n", ops->tracer);
		return_value = FAILED;
	}

	if (ops->analyze)
		ops->analyze(tool, stopped);

out_signals:
	unset_signals(params);
out_trace:
	trace_events_destroy(&tool->record->trace, params->events);
	params->events = NULL;
out_free:
	ops->free(tool);
	osnoise_destroy_tool(tool->record);
	osnoise_destroy_tool(tool);
	actions_destroy(&params->threshold_actions);
	actions_destroy(&params->end_actions);
	free(params);
out_exit:
	exit(return_value);
}

int top_main_loop(struct osnoise_tool *tool)
{
	struct common_params *params = tool->params;
	struct trace_instance *trace = &tool->trace;
	struct osnoise_tool *record = tool->record;
	int retval;

	while (!stop_tracing) {
		sleep(params->sleep_time);

		if (params->aa_only && !osnoise_trace_is_off(tool, record))
			continue;

		retval = tracefs_iterate_raw_events(trace->tep,
						    trace->inst,
						    NULL,
						    0,
						    collect_registered_events,
						    trace);
		if (retval < 0) {
			err_msg("Error iterating on events\n");
			return retval;
		}

		if (!params->quiet)
			tool->ops->print_stats(tool);

		if (osnoise_trace_is_off(tool, record)) {
			if (stop_tracing)
				/* stop tracing requested, do not perform actions */
				return 0;

			retval = common_threshold_handler(tool);
			if (retval)
				return retval;


			if (!should_continue_tracing(params))
				return 0;

			trace_instance_start(trace);
		}

		/* is there still any user-threads ? */
		if (params->user_workload) {
			if (params->user.stopped_running) {
				debug_msg("timerlat user space threads stopped!\n");
				break;
			}
		}
	}

	return 0;
}

int hist_main_loop(struct osnoise_tool *tool)
{
	struct common_params *params = tool->params;
	struct trace_instance *trace = &tool->trace;
	int retval = 0;

	while (!stop_tracing) {
		sleep(params->sleep_time);

		retval = tracefs_iterate_raw_events(trace->tep,
						    trace->inst,
						    NULL,
						    0,
						    collect_registered_events,
						    trace);
		if (retval < 0) {
			err_msg("Error iterating on events\n");
			break;
		}

		if (osnoise_trace_is_off(tool, tool->record)) {
			if (stop_tracing)
				/* stop tracing requested, do not perform actions */
				break;

			retval = common_threshold_handler(tool);
			if (retval)
				return retval;

			if (!should_continue_tracing(params))
				return 0;

			trace_instance_start(trace);
		}

		/* is there still any user-threads ? */
		if (params->user_workload) {
			if (params->user.stopped_running) {
				debug_msg("user-space threads stopped!\n");
				break;
			}
		}
	}

	return retval;
}

int osn_set_stop(struct osnoise_tool *tool)
{
	struct common_params *params = tool->params;
	int retval;

	retval = osnoise_set_stop_us(tool->context, params->stop_us);
	if (retval) {
		err_msg("Failed to set stop us\n");
		return retval;
	}

	retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
	if (retval) {
		err_msg("Failed to set stop total us\n");
		return retval;
	}

	return 0;
}

static void print_msg_array(const char * const *msgs)
{
	if (!msgs)
		return;

	for (int i = 0; msgs[i]; i++)
		fprintf(stderr, "%s\n", msgs[i]);
}

/*
 * common_usage - print complete usage information
 */
void common_usage(const char *tool, const char *mode,
		  const char *desc, const char * const *start_msgs, const char * const *opt_msgs)
{
	static const char * const common_options[] = {
		"	  -h/--help: print this menu",
		NULL
	};
	fprintf(stderr, "rtla %s", tool);
	if (strcmp(mode, ""))
		fprintf(stderr, " %s", mode);
	fprintf(stderr, ": %s (version %s)\n\n", desc, VERSION);
	fprintf(stderr, "  usage: [rtla] %s ", tool);

	if (strcmp(mode, "top") == 0)
		fprintf(stderr, "[top] [-h] ");
	else
		fprintf(stderr, "%s [-h] ", mode);

	print_msg_array(start_msgs);
	fprintf(stderr, "\n");
	print_msg_array(common_options);
	print_msg_array(opt_msgs);

	exit(EXIT_SUCCESS);
}