Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fixes from Ingo Molnar:
"Debug info and other statistics fixes and related enhancements"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/numa: Fix numa balancing stats in /proc/pid/sched
sched/numa: Show numa_group ID in /proc/sched_debug task listings
sched/debug: Move print_cfs_rq() declaration to kernel/sched/sched.h
sched/stat: Expose /proc/pid/schedstat if CONFIG_SCHED_INFO=y
sched/stat: Simplify the sched_info accounting dependency
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 1d540b3..87782e8 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -491,14 +491,17 @@
}
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
/*
* Provides /proc/PID/schedstat
*/
static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- seq_printf(m, "%llu %llu %lu\n",
+ if (unlikely(!sched_info_on()))
+ seq_printf(m, "0 0 0\n");
+ else
+ seq_printf(m, "%llu %llu %lu\n",
(unsigned long long)task->se.sum_exec_runtime,
(unsigned long long)task->sched_info.run_delay,
task->sched_info.pcount);
@@ -2787,7 +2790,7 @@
#ifdef CONFIG_STACKTRACE
ONE("stack", S_IRUSR, proc_pid_stack),
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
ONE("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
@@ -3135,7 +3138,7 @@
#ifdef CONFIG_STACKTRACE
ONE("stack", S_IRUSR, proc_pid_stack),
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
ONE("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8aa4a25..ae21f15 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -192,8 +192,6 @@
#ifdef CONFIG_SCHED_DEBUG
extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
extern void proc_sched_set_task(struct task_struct *p);
-extern void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
#endif
/*
@@ -838,7 +836,7 @@
struct backing_dev_info;
struct reclaim_state;
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
struct sched_info {
/* cumulative counters */
unsigned long pcount; /* # of times run on this cpu */
@@ -848,7 +846,7 @@
unsigned long long last_arrival,/* when we last ran on a cpu */
last_queued; /* when we were last queued to run */
};
-#endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
+#endif /* CONFIG_SCHED_INFO */
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
@@ -1397,7 +1395,7 @@
int rcu_tasks_idle_cpu;
#endif /* #ifdef CONFIG_TASKS_RCU */
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
struct sched_info sched_info;
#endif
diff --git a/init/Kconfig b/init/Kconfig
index 53c41a8..af09b4f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -435,6 +435,7 @@
config TASK_DELAY_ACCT
bool "Enable per-task delay accounting"
depends on TASKSTATS
+ select SCHED_INFO
help
Collect information on time spent by a task waiting for system
resources like cpu, synchronous block I/O completion and swapping
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b803e1b..5caa029 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2164,7 +2164,7 @@
set_task_cpu(p, cpu);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
if (likely(sched_info_on()))
memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 315c68e..4222ec5 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -142,7 +142,7 @@
0LL, 0L);
#endif
#ifdef CONFIG_NUMA_BALANCING
- SEQ_printf(m, " %d", task_node(p));
+ 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)));
@@ -517,11 +517,21 @@
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+#ifdef CONFIG_NUMA_BALANCING
+void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
+ unsigned long tpf, unsigned long gsf, unsigned long gpf)
+{
+ SEQ_printf(m, "numa_faults node=%d ", node);
+ SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
+ SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+}
+#endif
+
+
static void sched_show_numa(struct task_struct *p, struct seq_file *m)
{
#ifdef CONFIG_NUMA_BALANCING
struct mempolicy *pol;
- int node, i;
if (p->mm)
P(mm->numa_scan_seq);
@@ -533,26 +543,12 @@
mpol_get(pol);
task_unlock(p);
- SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
-
- for_each_online_node(node) {
- for (i = 0; i < 2; i++) {
- unsigned long nr_faults = -1;
- int cpu_current, home_node;
-
- if (p->numa_faults)
- nr_faults = p->numa_faults[2*node + i];
-
- cpu_current = !i ? (task_node(p) == node) :
- (pol && node_isset(node, pol->v.nodes));
-
- home_node = (p->numa_preferred_nid == node);
-
- SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
- i, node, cpu_current, home_node, nr_faults);
- }
- }
-
+ P(numa_pages_migrated);
+ P(numa_preferred_nid);
+ P(total_numa_faults);
+ SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
+ task_node(p), task_numa_group_id(p));
+ show_numa_stats(p, m);
mpol_put(pol);
#endif
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3d57cc0..65c8f3e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8473,7 +8473,27 @@
print_cfs_rq(m, cpu, cfs_rq);
rcu_read_unlock();
}
-#endif
+
+#ifdef CONFIG_NUMA_BALANCING
+void show_numa_stats(struct task_struct *p, struct seq_file *m)
+{
+ int node;
+ unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0;
+
+ for_each_online_node(node) {
+ if (p->numa_faults) {
+ tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)];
+ tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
+ }
+ if (p->numa_group) {
+ gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)],
+ gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)];
+ }
+ print_numa_stats(m, node, tsf, tpf, gsf, gpf);
+ }
+}
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
__init void init_sched_fair_class(void)
{
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8858891..84d4879 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1689,9 +1689,22 @@
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
+
+#ifdef CONFIG_SCHED_DEBUG
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
extern void print_dl_stats(struct seq_file *m, int cpu);
+extern void
+print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
+
+#ifdef CONFIG_NUMA_BALANCING
+extern void
+show_numa_stats(struct task_struct *p, struct seq_file *m);
+extern void
+print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
+ unsigned long tpf, unsigned long gsf, unsigned long gpf);
+#endif /* CONFIG_NUMA_BALANCING */
+#endif /* CONFIG_SCHED_DEBUG */
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq);
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 077ebbd..b0fbc76 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -47,7 +47,7 @@
# define schedstat_set(var, val) do { } while (0)
#endif
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+#ifdef CONFIG_SCHED_INFO
static inline void sched_info_reset_dequeued(struct task_struct *t)
{
t->sched_info.last_queued = 0;
@@ -156,7 +156,7 @@
#define sched_info_depart(rq, t) do { } while (0)
#define sched_info_arrive(rq, next) do { } while (0)
#define sched_info_switch(rq, t, next) do { } while (0)
-#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
+#endif /* CONFIG_SCHED_INFO */
/*
* The following are functions that support scheduler-internal time accounting.
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b908048..e2894b2 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -841,9 +841,14 @@
that can help debug the scheduler. The runtime overhead of this
option is minimal.
+config SCHED_INFO
+ bool
+ default n
+
config SCHEDSTATS
bool "Collect scheduler statistics"
depends on DEBUG_KERNEL && PROC_FS
+ select SCHED_INFO
help
If you say Y here, additional code will be inserted into the
scheduler and related routines to collect statistics about
