From e636c8d336489bf3eed5878299e6cc045bbad077 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:17:29 +0000
Subject: [PATCH] debug lk
---
kernel/include/trace/events/sched.h | 514 +++++++++------------------------------------------------
1 files changed, 81 insertions(+), 433 deletions(-)
diff --git a/kernel/include/trace/events/sched.h b/kernel/include/trace/events/sched.h
index 14efeb2..bcd7f1f 100644
--- a/kernel/include/trace/events/sched.h
+++ b/kernel/include/trace/events/sched.h
@@ -91,7 +91,7 @@
/*
* Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG.
- * It it not always called from the waking context.
+ * It is not always called from the waking context.
*/
DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
TP_PROTO(struct task_struct *p),
@@ -198,6 +198,7 @@
__field( int, prio )
__field( int, orig_cpu )
__field( int, dest_cpu )
+ __field( int, running )
),
TP_fast_assign(
@@ -206,11 +207,13 @@
__entry->prio = p->prio; /* XXX SCHED_DEADLINE */
__entry->orig_cpu = task_cpu(p);
__entry->dest_cpu = dest_cpu;
+ __entry->running = (p->state == TASK_RUNNING);
),
- TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d",
+ TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d running=%d",
__entry->comm, __entry->pid, __entry->prio,
- __entry->orig_cpu, __entry->dest_cpu)
+ __entry->orig_cpu, __entry->dest_cpu,
+ __entry->running)
);
DECLARE_EVENT_CLASS(sched_process_template,
@@ -241,7 +244,6 @@
DEFINE_EVENT(sched_process_template, sched_process_free,
TP_PROTO(struct task_struct *p),
TP_ARGS(p));
-
/*
* Tracepoint for a task exiting:
@@ -336,11 +338,20 @@
__entry->pid, __entry->old_pid)
);
+
+#ifdef CONFIG_SCHEDSTATS
+#define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT
+#define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS
+#else
+#define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT_NOP
+#define DECLARE_EVENT_CLASS_SCHEDSTAT DECLARE_EVENT_CLASS_NOP
+#endif
+
/*
* XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
* adding sched_stat support to SCHED_FIFO/RR would be welcome.
*/
-DECLARE_EVENT_CLASS(sched_stat_template,
+DECLARE_EVENT_CLASS_SCHEDSTAT(sched_stat_template,
TP_PROTO(struct task_struct *tsk, u64 delay),
@@ -363,12 +374,11 @@
(unsigned long long)__entry->delay)
);
-
/*
* Tracepoint for accounting wait time (time the task is runnable
* but not actually running due to scheduler contention).
*/
-DEFINE_EVENT(sched_stat_template, sched_stat_wait,
+DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_wait,
TP_PROTO(struct task_struct *tsk, u64 delay),
TP_ARGS(tsk, delay));
@@ -376,7 +386,7 @@
* Tracepoint for accounting sleep time (time the task is not runnable,
* including iowait, see below).
*/
-DEFINE_EVENT(sched_stat_template, sched_stat_sleep,
+DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_sleep,
TP_PROTO(struct task_struct *tsk, u64 delay),
TP_ARGS(tsk, delay));
@@ -384,14 +394,14 @@
* Tracepoint for accounting iowait time (time the task is not runnable
* due to waiting on IO to complete).
*/
-DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
+DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_iowait,
TP_PROTO(struct task_struct *tsk, u64 delay),
TP_ARGS(tsk, delay));
/*
* Tracepoint for accounting blocked time (time the task is in uninterruptible).
*/
-DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
+DEFINE_EVENT_SCHEDSTAT(sched_stat_template, sched_stat_blocked,
TP_PROTO(struct task_struct *tsk, u64 delay),
TP_ARGS(tsk, delay));
@@ -412,7 +422,7 @@
TP_fast_assign(
__entry->pid = tsk->pid;
- __entry->caller = (void*)get_wchan(tsk);
+ __entry->caller = (void *)get_wchan(tsk);
__entry->io_wait = tsk->in_iowait;
),
@@ -504,7 +514,11 @@
);
#endif /* CONFIG_DETECT_HUNG_TASK */
-DECLARE_EVENT_CLASS(sched_move_task_template,
+/*
+ * Tracks migration of tasks from one runqueue to another. Can be used to
+ * detect if automatic NUMA balancing is bouncing between nodes.
+ */
+TRACE_EVENT(sched_move_numa,
TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
@@ -536,23 +550,7 @@
__entry->dst_cpu, __entry->dst_nid)
);
-/*
- * Tracks migration of tasks from one runqueue to another. Can be used to
- * detect if automatic NUMA balancing is bouncing between nodes
- */
-DEFINE_EVENT(sched_move_task_template, sched_move_numa,
- TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
-
- TP_ARGS(tsk, src_cpu, dst_cpu)
-);
-
-DEFINE_EVENT(sched_move_task_template, sched_stick_numa,
- TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
-
- TP_ARGS(tsk, src_cpu, dst_cpu)
-);
-
-TRACE_EVENT(sched_swap_numa,
+DECLARE_EVENT_CLASS(sched_numa_pair_template,
TP_PROTO(struct task_struct *src_tsk, int src_cpu,
struct task_struct *dst_tsk, int dst_cpu),
@@ -578,11 +576,11 @@
__entry->src_ngid = task_numa_group_id(src_tsk);
__entry->src_cpu = src_cpu;
__entry->src_nid = cpu_to_node(src_cpu);
- __entry->dst_pid = task_pid_nr(dst_tsk);
- __entry->dst_tgid = task_tgid_nr(dst_tsk);
- __entry->dst_ngid = task_numa_group_id(dst_tsk);
+ __entry->dst_pid = dst_tsk ? task_pid_nr(dst_tsk) : 0;
+ __entry->dst_tgid = dst_tsk ? task_tgid_nr(dst_tsk) : 0;
+ __entry->dst_ngid = dst_tsk ? task_numa_group_id(dst_tsk) : 0;
__entry->dst_cpu = dst_cpu;
- __entry->dst_nid = cpu_to_node(dst_cpu);
+ __entry->dst_nid = dst_cpu >= 0 ? cpu_to_node(dst_cpu) : -1;
),
TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d",
@@ -591,6 +589,23 @@
__entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid,
__entry->dst_cpu, __entry->dst_nid)
);
+
+DEFINE_EVENT(sched_numa_pair_template, sched_stick_numa,
+
+ TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+ struct task_struct *dst_tsk, int dst_cpu),
+
+ TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu)
+);
+
+DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa,
+
+ TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+ struct task_struct *dst_tsk, int dst_cpu),
+
+ TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu)
+);
+
/*
* Tracepoint for waking a polling cpu without an IPI.
@@ -612,423 +627,56 @@
TP_printk("cpu=%d", __entry->cpu)
);
-#ifdef CONFIG_SMP
-#ifdef CREATE_TRACE_POINTS
-static inline
-int __trace_sched_cpu(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-#ifdef CONFIG_FAIR_GROUP_SCHED
- struct rq *rq = cfs_rq ? cfs_rq->rq : NULL;
-#else
- struct rq *rq = cfs_rq ? container_of(cfs_rq, struct rq, cfs) : NULL;
-#endif
- return rq ? cpu_of(rq)
- : task_cpu((container_of(se, struct task_struct, se)));
-}
-
-static inline
-int __trace_sched_path(struct cfs_rq *cfs_rq, char *path, int len)
-{
-#ifdef CONFIG_FAIR_GROUP_SCHED
- int l = path ? len : 0;
-
- if (cfs_rq && task_group_is_autogroup(cfs_rq->tg))
- return autogroup_path(cfs_rq->tg, path, l) + 1;
- else if (cfs_rq && cfs_rq->tg->css.cgroup)
- return cgroup_path(cfs_rq->tg->css.cgroup, path, l) + 1;
-#endif
- if (path)
- strcpy(path, "(null)");
-
- return strlen("(null)");
-}
-
-static inline
-struct cfs_rq *__trace_sched_group_cfs_rq(struct sched_entity *se)
-{
-#ifdef CONFIG_FAIR_GROUP_SCHED
- return se->my_q;
-#else
- return NULL;
-#endif
-}
-#endif /* CREATE_TRACE_POINTS */
-
/*
- * Tracepoint for cfs_rq load tracking:
+ * Following tracepoints are not exported in tracefs and provide hooking
+ * mechanisms only for testing and debugging purposes.
+ *
+ * Postfixed with _tp to make them easily identifiable in the code.
*/
-TRACE_EVENT(sched_load_cfs_rq,
-
+DECLARE_TRACE(pelt_cfs_tp,
TP_PROTO(struct cfs_rq *cfs_rq),
+ TP_ARGS(cfs_rq));
- TP_ARGS(cfs_rq),
-
- TP_STRUCT__entry(
- __field( int, cpu )
- __dynamic_array(char, path,
- __trace_sched_path(cfs_rq, NULL, 0) )
- __field( unsigned long, load )
- __field( unsigned long, rbl_load )
- __field( unsigned long, util )
- ),
-
- TP_fast_assign(
- __entry->cpu = __trace_sched_cpu(cfs_rq, NULL);
- __trace_sched_path(cfs_rq, __get_dynamic_array(path),
- __get_dynamic_array_len(path));
- __entry->load = cfs_rq->avg.load_avg;
- __entry->rbl_load = cfs_rq->avg.runnable_load_avg;
- __entry->util = cfs_rq->avg.util_avg;
- ),
-
- TP_printk("cpu=%d path=%s load=%lu rbl_load=%lu util=%lu",
- __entry->cpu, __get_str(path), __entry->load,
- __entry->rbl_load,__entry->util)
-);
-
-/*
- * Tracepoint for rt_rq load tracking:
- */
-struct rq;
-TRACE_EVENT(sched_load_rt_rq,
-
+DECLARE_TRACE(pelt_rt_tp,
TP_PROTO(struct rq *rq),
+ TP_ARGS(rq));
- TP_ARGS(rq),
+DECLARE_TRACE(pelt_dl_tp,
+ TP_PROTO(struct rq *rq),
+ TP_ARGS(rq));
- TP_STRUCT__entry(
- __field( int, cpu )
- __field( unsigned long, util )
- ),
+DECLARE_TRACE(pelt_thermal_tp,
+ TP_PROTO(struct rq *rq),
+ TP_ARGS(rq));
- TP_fast_assign(
- __entry->cpu = rq->cpu;
- __entry->util = rq->avg_rt.util_avg;
- ),
+DECLARE_TRACE(pelt_irq_tp,
+ TP_PROTO(struct rq *rq),
+ TP_ARGS(rq));
- TP_printk("cpu=%d util=%lu", __entry->cpu,
- __entry->util)
-);
-
-/*
- * Tracepoint for sched_entity load tracking:
- */
-TRACE_EVENT(sched_load_se,
-
+DECLARE_TRACE(pelt_se_tp,
TP_PROTO(struct sched_entity *se),
+ TP_ARGS(se));
- TP_ARGS(se),
+DECLARE_TRACE(sched_cpu_capacity_tp,
+ TP_PROTO(struct rq *rq),
+ TP_ARGS(rq));
- TP_STRUCT__entry(
- __field( int, cpu )
- __dynamic_array(char, path,
- __trace_sched_path(__trace_sched_group_cfs_rq(se), NULL, 0) )
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( unsigned long, load )
- __field( unsigned long, rbl_load )
- __field( unsigned long, util )
- ),
+DECLARE_TRACE(sched_overutilized_tp,
+ TP_PROTO(struct root_domain *rd, bool overutilized),
+ TP_ARGS(rd, overutilized));
- TP_fast_assign(
- struct cfs_rq *gcfs_rq = __trace_sched_group_cfs_rq(se);
- struct task_struct *p = gcfs_rq ? NULL
- : container_of(se, struct task_struct, se);
-
- __entry->cpu = __trace_sched_cpu(gcfs_rq, se);
- __trace_sched_path(gcfs_rq, __get_dynamic_array(path),
- __get_dynamic_array_len(path));
- memcpy(__entry->comm, p ? p->comm : "(null)",
- p ? TASK_COMM_LEN : sizeof("(null)"));
- __entry->pid = p ? p->pid : -1;
- __entry->load = se->avg.load_avg;
- __entry->rbl_load = se->avg.runnable_load_avg;
- __entry->util = se->avg.util_avg;
- ),
-
- TP_printk("cpu=%d path=%s comm=%s pid=%d load=%lu rbl_load=%lu util=%lu",
- __entry->cpu, __get_str(path), __entry->comm, __entry->pid,
- __entry->load, __entry->rbl_load, __entry->util)
-);
-
-/*
- * Tracepoint for task_group load tracking:
- */
-#ifdef CONFIG_FAIR_GROUP_SCHED
-TRACE_EVENT(sched_load_tg,
-
+DECLARE_TRACE(sched_util_est_cfs_tp,
TP_PROTO(struct cfs_rq *cfs_rq),
+ TP_ARGS(cfs_rq));
- TP_ARGS(cfs_rq),
+DECLARE_TRACE(sched_util_est_se_tp,
+ TP_PROTO(struct sched_entity *se),
+ TP_ARGS(se));
- TP_STRUCT__entry(
- __field( int, cpu )
- __dynamic_array(char, path,
- __trace_sched_path(cfs_rq, NULL, 0) )
- __field( long, load )
- ),
+DECLARE_TRACE(sched_update_nr_running_tp,
+ TP_PROTO(struct rq *rq, int change),
+ TP_ARGS(rq, change));
- TP_fast_assign(
- __entry->cpu = cfs_rq->rq->cpu;
- __trace_sched_path(cfs_rq, __get_dynamic_array(path),
- __get_dynamic_array_len(path));
- __entry->load = atomic_long_read(&cfs_rq->tg->load_avg);
- ),
-
- TP_printk("cpu=%d path=%s load=%ld", __entry->cpu, __get_str(path),
- __entry->load)
-);
-#endif /* CONFIG_FAIR_GROUP_SCHED */
-
-/*
- * Tracepoint for tasks' estimated utilization.
- */
-TRACE_EVENT(sched_util_est_task,
-
- TP_PROTO(struct task_struct *tsk, struct sched_avg *avg),
-
- TP_ARGS(tsk, avg),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, cpu )
- __field( unsigned int, util_avg )
- __field( unsigned int, est_enqueued )
- __field( unsigned int, est_ewma )
-
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
- __entry->pid = tsk->pid;
- __entry->cpu = task_cpu(tsk);
- __entry->util_avg = avg->util_avg;
- __entry->est_enqueued = avg->util_est.enqueued;
- __entry->est_ewma = avg->util_est.ewma;
- ),
-
- TP_printk("comm=%s pid=%d cpu=%d util_avg=%u util_est_ewma=%u util_est_enqueued=%u",
- __entry->comm,
- __entry->pid,
- __entry->cpu,
- __entry->util_avg,
- __entry->est_ewma,
- __entry->est_enqueued)
-);
-
-/*
- * Tracepoint for root cfs_rq's estimated utilization.
- */
-TRACE_EVENT(sched_util_est_cpu,
-
- TP_PROTO(int cpu, struct cfs_rq *cfs_rq),
-
- TP_ARGS(cpu, cfs_rq),
-
- TP_STRUCT__entry(
- __field( int, cpu )
- __field( unsigned int, util_avg )
- __field( unsigned int, util_est_enqueued )
- ),
-
- TP_fast_assign(
- __entry->cpu = cpu;
- __entry->util_avg = cfs_rq->avg.util_avg;
- __entry->util_est_enqueued = cfs_rq->avg.util_est.enqueued;
- ),
-
- TP_printk("cpu=%d util_avg=%u util_est_enqueued=%u",
- __entry->cpu,
- __entry->util_avg,
- __entry->util_est_enqueued)
-);
-
-/*
- * Tracepoint for find_best_target
- */
-TRACE_EVENT(sched_find_best_target,
-
- TP_PROTO(struct task_struct *tsk, bool prefer_idle,
- unsigned long min_util, int best_idle, int best_active,
- int target, int backup),
-
- TP_ARGS(tsk, prefer_idle, min_util, best_idle,
- best_active, target, backup),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( unsigned long, min_util )
- __field( bool, prefer_idle )
- __field( int, best_idle )
- __field( int, best_active )
- __field( int, target )
- __field( int, backup )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
- __entry->pid = tsk->pid;
- __entry->min_util = min_util;
- __entry->prefer_idle = prefer_idle;
- __entry->best_idle = best_idle;
- __entry->best_active = best_active;
- __entry->target = target;
- __entry->backup = backup;
- ),
-
- TP_printk("pid=%d comm=%s prefer_idle=%d "
- "best_idle=%d best_active=%d target=%d backup=%d",
- __entry->pid, __entry->comm, __entry->prefer_idle,
- __entry->best_idle, __entry->best_active,
- __entry->target, __entry->backup)
-);
-
-/*
- * Tracepoint for accounting CPU boosted utilization
- */
-TRACE_EVENT(sched_boost_cpu,
-
- TP_PROTO(int cpu, unsigned long util, long margin),
-
- TP_ARGS(cpu, util, margin),
-
- TP_STRUCT__entry(
- __field( int, cpu )
- __field( unsigned long, util )
- __field(long, margin )
- ),
-
- TP_fast_assign(
- __entry->cpu = cpu;
- __entry->util = util;
- __entry->margin = margin;
- ),
-
- TP_printk("cpu=%d util=%lu margin=%ld",
- __entry->cpu,
- __entry->util,
- __entry->margin)
-);
-
-/*
- * Tracepoint for schedtune_tasks_update
- */
-TRACE_EVENT(sched_tune_tasks_update,
-
- TP_PROTO(struct task_struct *tsk, int cpu, int tasks, int idx,
- int boost, int max_boost, u64 group_ts),
-
- TP_ARGS(tsk, cpu, tasks, idx, boost, max_boost, group_ts),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( int, cpu )
- __field( int, tasks )
- __field( int, idx )
- __field( int, boost )
- __field( int, max_boost )
- __field( u64, group_ts )
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
- __entry->pid = tsk->pid;
- __entry->cpu = cpu;
- __entry->tasks = tasks;
- __entry->idx = idx;
- __entry->boost = boost;
- __entry->max_boost = max_boost;
- __entry->group_ts = group_ts;
- ),
-
- TP_printk("pid=%d comm=%s "
- "cpu=%d tasks=%d idx=%d boost=%d max_boost=%d timeout=%llu",
- __entry->pid, __entry->comm,
- __entry->cpu, __entry->tasks, __entry->idx,
- __entry->boost, __entry->max_boost,
- __entry->group_ts)
-);
-
-/*
- * Tracepoint for schedtune_boostgroup_update
- */
-TRACE_EVENT(sched_tune_boostgroup_update,
-
- TP_PROTO(int cpu, int variation, int max_boost),
-
- TP_ARGS(cpu, variation, max_boost),
-
- TP_STRUCT__entry(
- __field( int, cpu )
- __field( int, variation )
- __field( int, max_boost )
- ),
-
- TP_fast_assign(
- __entry->cpu = cpu;
- __entry->variation = variation;
- __entry->max_boost = max_boost;
- ),
-
- TP_printk("cpu=%d variation=%d max_boost=%d",
- __entry->cpu, __entry->variation, __entry->max_boost)
-);
-
-/*
- * Tracepoint for accounting task boosted utilization
- */
-TRACE_EVENT(sched_boost_task,
-
- TP_PROTO(struct task_struct *tsk, unsigned long util, long margin),
-
- TP_ARGS(tsk, util, margin),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN )
- __field( pid_t, pid )
- __field( unsigned long, util )
- __field( long, margin )
-
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
- __entry->pid = tsk->pid;
- __entry->util = util;
- __entry->margin = margin;
- ),
-
- TP_printk("comm=%s pid=%d util=%lu margin=%ld",
- __entry->comm, __entry->pid,
- __entry->util,
- __entry->margin)
-);
-
-/*
- * Tracepoint for system overutilized flag
-*/
-TRACE_EVENT(sched_overutilized,
-
- TP_PROTO(int overutilized),
-
- TP_ARGS(overutilized),
-
- TP_STRUCT__entry(
- __field( int, overutilized )
- ),
-
- TP_fast_assign(
- __entry->overutilized = overutilized;
- ),
-
- TP_printk("overutilized=%d",
- __entry->overutilized)
-);
-
-#endif /* CONFIG_SMP */
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
--
Gitblit v1.6.2