982 lines · 23.0 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-only/* * kernel/sched/debug.c * * Print the CFS rbtree and other debugging details * * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar */#include "sched.h" static DEFINE_SPINLOCK(sched_debug_lock); /* * This allows printing both to /proc/sched_debug and * to the console */#define SEQ_printf(m, x...)			\ do {						\	if (m)					\		seq_printf(m, x);		\	else					\		pr_cont(x);			\ } while (0) /* * Ease the printing of nsec fields: */static long long nsec_high(unsigned long long nsec){	if ((long long)nsec < 0) {		nsec = -nsec;		do_div(nsec, 1000000);		return -nsec;	}	do_div(nsec, 1000000); 	return nsec;} static unsigned long nsec_low(unsigned long long nsec){	if ((long long)nsec < 0)		nsec = -nsec; 	return do_div(nsec, 1000000);} #define SPLIT_NS(x) nsec_high(x), nsec_low(x) #define SCHED_FEAT(name, enabled)	\	#name , static const char * const sched_feat_names[] = {#include "features.h"}; #undef SCHED_FEAT static int sched_feat_show(struct seq_file *m, void *v){	int i; 	for (i = 0; i < __SCHED_FEAT_NR; i++) {		if (!(sysctl_sched_features & (1UL << i)))			seq_puts(m, "NO_");		seq_printf(m, "%s ", sched_feat_names[i]);	}	seq_puts(m, "\n"); 	return 0;} #ifdef CONFIG_JUMP_LABEL #define jump_label_key__true  STATIC_KEY_INIT_TRUE#define jump_label_key__false STATIC_KEY_INIT_FALSE #define SCHED_FEAT(name, enabled)	\	jump_label_key__##enabled , struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {#include "features.h"}; #undef SCHED_FEAT static void sched_feat_disable(int i){	static_key_disable_cpuslocked(&sched_feat_keys[i]);} static void sched_feat_enable(int i){	static_key_enable_cpuslocked(&sched_feat_keys[i]);}#elsestatic void sched_feat_disable(int i) { };static void sched_feat_enable(int i) { };#endif /* CONFIG_JUMP_LABEL */ static int sched_feat_set(char *cmp){	int i;	int neg = 0; 	if (strncmp(cmp, "NO_", 3) == 0) {		neg = 1;		cmp += 3;	} 	i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp);	if (i < 0)		return i; 	if (neg) {		sysctl_sched_features &= ~(1UL << i);		sched_feat_disable(i);	} else {		sysctl_sched_features |= (1UL << i);		sched_feat_enable(i);	} 	return 0;} static ssize_tsched_feat_write(struct file *filp, const char __user *ubuf,		size_t cnt, loff_t *ppos){	char buf[64];	char *cmp;	int ret;	struct inode *inode; 	if (cnt > 63)		cnt = 63; 	if (copy_from_user(&buf, ubuf, cnt))		return -EFAULT; 	buf[cnt] = 0;	cmp = strstrip(buf); 	/* Ensure the static_key remains in a consistent state */	inode = file_inode(filp);	cpus_read_lock();	inode_lock(inode);	ret = sched_feat_set(cmp);	inode_unlock(inode);	cpus_read_unlock();	if (ret < 0)		return ret; 	*ppos += cnt; 	return cnt;} static int sched_feat_open(struct inode *inode, struct file *filp){	return single_open(filp, sched_feat_show, NULL);} static const struct file_operations sched_feat_fops = {	.open		= sched_feat_open,	.write		= sched_feat_write,	.read		= seq_read,	.llseek		= seq_lseek,	.release	= single_release,}; __read_mostly bool sched_debug_enabled; static __init int sched_init_debug(void){	debugfs_create_file("sched_features", 0644, NULL, NULL,			&sched_feat_fops); 	debugfs_create_bool("sched_debug", 0644, NULL,			&sched_debug_enabled); 	return 0;}late_initcall(sched_init_debug); #ifdef CONFIG_SMP #ifdef CONFIG_SYSCTL static struct ctl_table sd_ctl_dir[] = {	{		.procname	= "sched_domain",		.mode		= 0555,	},	{}}; static struct ctl_table sd_ctl_root[] = {	{		.procname	= "kernel",		.mode		= 0555,		.child		= sd_ctl_dir,	},	{}}; static struct ctl_table *sd_alloc_ctl_entry(int n){	struct ctl_table *entry =		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); 	return entry;} static void sd_free_ctl_entry(struct ctl_table **tablep){	struct ctl_table *entry; 	/*	 * In the intermediate directories, both the child directory and	 * procname are dynamically allocated and could fail but the mode	 * will always be set. In the lowest directory the names are	 * static strings and all have proc handlers.	 */	for (entry = *tablep; entry->mode; entry++) {		if (entry->child)			sd_free_ctl_entry(&entry->child);		if (entry->proc_handler == NULL)			kfree(entry->procname);	} 	kfree(*tablep);	*tablep = NULL;} static voidset_table_entry(struct ctl_table *entry,		const char *procname, void *data, int maxlen,		umode_t mode, proc_handler *proc_handler){	entry->procname = procname;	entry->data = data;	entry->maxlen = maxlen;	entry->mode = mode;	entry->proc_handler = proc_handler;} static struct ctl_table *sd_alloc_ctl_domain_table(struct sched_domain *sd){	struct ctl_table *table = sd_alloc_ctl_entry(9); 	if (table == NULL)		return NULL; 	set_table_entry(&table[0], "min_interval",	  &sd->min_interval,	    sizeof(long), 0644, proc_doulongvec_minmax);	set_table_entry(&table[1], "max_interval",	  &sd->max_interval,	    sizeof(long), 0644, proc_doulongvec_minmax);	set_table_entry(&table[2], "busy_factor",	  &sd->busy_factor,	    sizeof(int),  0644, proc_dointvec_minmax);	set_table_entry(&table[3], "imbalance_pct",	  &sd->imbalance_pct,	    sizeof(int),  0644, proc_dointvec_minmax);	set_table_entry(&table[4], "cache_nice_tries",	  &sd->cache_nice_tries,    sizeof(int),  0644, proc_dointvec_minmax);	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0644, proc_dointvec_minmax);	set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax);	set_table_entry(&table[7], "name",		  sd->name,	       CORENAME_MAX_SIZE, 0444, proc_dostring);	/* &table[8] is terminator */ 	return table;} static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu){	struct ctl_table *entry, *table;	struct sched_domain *sd;	int domain_num = 0, i;	char buf[32]; 	for_each_domain(cpu, sd)		domain_num++;	entry = table = sd_alloc_ctl_entry(domain_num + 1);	if (table == NULL)		return NULL; 	i = 0;	for_each_domain(cpu, sd) {		snprintf(buf, 32, "domain%d", i);		entry->procname = kstrdup(buf, GFP_KERNEL);		entry->mode = 0555;		entry->child = sd_alloc_ctl_domain_table(sd);		entry++;		i++;	}	return table;} static cpumask_var_t		sd_sysctl_cpus;static struct ctl_table_header	*sd_sysctl_header; void register_sched_domain_sysctl(void){	static struct ctl_table *cpu_entries;	static struct ctl_table **cpu_idx;	static bool init_done = false;	char buf[32];	int i; 	if (!cpu_entries) {		cpu_entries = sd_alloc_ctl_entry(num_possible_cpus() + 1);		if (!cpu_entries)			return; 		WARN_ON(sd_ctl_dir[0].child);		sd_ctl_dir[0].child = cpu_entries;	} 	if (!cpu_idx) {		struct ctl_table *e = cpu_entries; 		cpu_idx = kcalloc(nr_cpu_ids, sizeof(struct ctl_table*), GFP_KERNEL);		if (!cpu_idx)			return; 		/* deal with sparse possible map */		for_each_possible_cpu(i) {			cpu_idx[i] = e;			e++;		}	} 	if (!cpumask_available(sd_sysctl_cpus)) {		if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))			return;	} 	if (!init_done) {		init_done = true;		/* init to possible to not have holes in @cpu_entries */		cpumask_copy(sd_sysctl_cpus, cpu_possible_mask);	} 	for_each_cpu(i, sd_sysctl_cpus) {		struct ctl_table *e = cpu_idx[i]; 		if (e->child)			sd_free_ctl_entry(&e->child); 		if (!e->procname) {			snprintf(buf, 32, "cpu%d", i);			e->procname = kstrdup(buf, GFP_KERNEL);		}		e->mode = 0555;		e->child = sd_alloc_ctl_cpu_table(i); 		__cpumask_clear_cpu(i, sd_sysctl_cpus);	} 	WARN_ON(sd_sysctl_header);	sd_sysctl_header = register_sysctl_table(sd_ctl_root);} void dirty_sched_domain_sysctl(int cpu){	if (cpumask_available(sd_sysctl_cpus))		__cpumask_set_cpu(cpu, sd_sysctl_cpus);} /* may be called multiple times per register */void unregister_sched_domain_sysctl(void){	unregister_sysctl_table(sd_sysctl_header);	sd_sysctl_header = NULL;}#endif /* CONFIG_SYSCTL */#endif /* CONFIG_SMP */ #ifdef CONFIG_FAIR_GROUP_SCHEDstatic void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg){	struct sched_entity *se = tg->se[cpu]; #define P(F)		SEQ_printf(m, "  .%-30s: %lld\n",	#F, (long long)F)#define P_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld\n",	#F, (long long)schedstat_val(F))#define PN(F)		SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))#define PN_SCHEDSTAT(F)	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(F))) 	if (!se)		return; 	PN(se->exec_start);	PN(se->vruntime);	PN(se->sum_exec_runtime); 	if (schedstat_enabled()) {		PN_SCHEDSTAT(se->statistics.wait_start);		PN_SCHEDSTAT(se->statistics.sleep_start);		PN_SCHEDSTAT(se->statistics.block_start);		PN_SCHEDSTAT(se->statistics.sleep_max);		PN_SCHEDSTAT(se->statistics.block_max);		PN_SCHEDSTAT(se->statistics.exec_max);		PN_SCHEDSTAT(se->statistics.slice_max);		PN_SCHEDSTAT(se->statistics.wait_max);		PN_SCHEDSTAT(se->statistics.wait_sum);		P_SCHEDSTAT(se->statistics.wait_count);	} 	P(se->load.weight);#ifdef CONFIG_SMP	P(se->avg.load_avg);	P(se->avg.util_avg);	P(se->avg.runnable_avg);#endif #undef PN_SCHEDSTAT#undef PN#undef P_SCHEDSTAT#undef P}#endif #ifdef CONFIG_CGROUP_SCHEDstatic char group_path[PATH_MAX]; static char *task_group_path(struct task_group *tg){	if (autogroup_path(tg, group_path, PATH_MAX))		return group_path; 	cgroup_path(tg->css.cgroup, group_path, PATH_MAX); 	return group_path;}#endif static voidprint_task(struct seq_file *m, struct rq *rq, struct task_struct *p){	if (rq->curr == p)		SEQ_printf(m, ">R");	else		SEQ_printf(m, " %c", task_state_to_char(p)); 	SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",		p->comm, task_pid_nr(p),		SPLIT_NS(p->se.vruntime),		(long long)(p->nvcsw + p->nivcsw),		p->prio); 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",		SPLIT_NS(schedstat_val_or_zero(p->se.statistics.wait_sum)),		SPLIT_NS(p->se.sum_exec_runtime),		SPLIT_NS(schedstat_val_or_zero(p->se.statistics.sum_sleep_runtime))); #ifdef CONFIG_NUMA_BALANCING	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));#endif#ifdef CONFIG_CGROUP_SCHED	SEQ_printf(m, " %s", task_group_path(task_group(p)));#endif 	SEQ_printf(m, "\n");} static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu){	struct task_struct *g, *p; 	SEQ_printf(m, "\n");	SEQ_printf(m, "runnable tasks:\n");	SEQ_printf(m, " S           task   PID         tree-key  switches  prio"		   "     wait-time             sum-exec        sum-sleep\n");	SEQ_printf(m, "-------------------------------------------------------"		   "----------------------------------------------------\n"); 	rcu_read_lock();	for_each_process_thread(g, p) {		if (task_cpu(p) != rq_cpu)			continue; 		print_task(m, rq, p);	}	rcu_read_unlock();} void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq){	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,		spread, rq0_min_vruntime, spread0;	struct rq *rq = cpu_rq(cpu);	struct sched_entity *last;	unsigned long flags; #ifdef CONFIG_FAIR_GROUP_SCHED	SEQ_printf(m, "\n");	SEQ_printf(m, "cfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg));#else	SEQ_printf(m, "\n");	SEQ_printf(m, "cfs_rq[%d]:\n", cpu);#endif	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",			SPLIT_NS(cfs_rq->exec_clock)); 	raw_spin_lock_irqsave(&rq->lock, flags);

Lines 1–500 of 982.