[PATCH 0/4] sched: Display deadline bandwidth and other SCHED_DEBUG clean up

[PATCH 0/4] sched: Display deadline bandwidth and other SCHED_DEBUG clean up

[Steven Rostedt]

[ Nothing different since my v2 I posted, except hopefully people
  will look at it this time :-) I also removed the RFC ]

I'm starting to play with SCHED_DEADLINE a bit and I'm able to cause
a bandwidth "leak". Then I realized there's no way to examine what bandwidths
are enabled on which CPUs. I added the bandwith ratios to the
/proc/sched_debug file.

I will be posting the SCHED_DEADLINE issue in a separate thread.

# grep dl /proc/sched_debug         
dl_rq[0]:
  .dl_nr_running                 : 0
  .dl_bw->bw                     : 996147
  .dl_bw->total_bw               : 0
dl_rq[1]:
  .dl_nr_running                 : 0
  .dl_bw->bw                     : 996147
  .dl_bw->total_bw               : 104857
dl_rq[2]:
  .dl_nr_running                 : 0
  .dl_bw->bw                     : 996147
  .dl_bw->total_bw               : 0
dl_rq[3]:
  .dl_nr_running                 : 0
  .dl_bw->bw                     : 996147
  .dl_bw->total_bw               : 0
dl_rq[4]:
  .dl_nr_running                 : 0
  .dl_bw->bw                     : 996147
  .dl_bw->total_bw               : 0
dl_rq[5]:
  .dl_nr_running                 : 0
  .dl_bw->bw                     : 996147
  .dl_bw->total_bw               : 0
dl_rq[6]:
  .dl_nr_running                 : 0
  .dl_bw->bw                     : 996147
  .dl_bw->total_bw               : 0
dl_rq[7]:
  .dl_nr_running                 : 0
  .dl_bw->bw                     : 996147
  .dl_bw->total_bw               : 0

Before adding this code, I also realized there was a bit of 
SCHED_DEBUG code in the kernel/sched/core.c file, and decided to move that
to kernel/sched/debug.c to clean the core.c file up a bit. Those patches
are mostly orthognal to the deadline_bw file, but decided to group them
together here.


Steven Rostedt (Red Hat) (4):
      sched: Move sched_feature file setup into debug.c
      sched: Move sched_domain_sysctl to debug.c
      sched: Add bandwidth ratio to /proc/sched_debug
      tracing: Add __print_ns_to_secs() and __print_ns_without_secs() helpers

----
 include/trace/trace_events.h |  25 ++++
 kernel/sched/core.c          | 311 ------------------------------------------
 kernel/sched/debug.c         | 313 +++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h         |  13 ++
 4 files changed, 351 insertions(+), 311 deletions(-)

[PATCH 1/4] sched: Move sched_feature file setup into debug.c

[Steven Rostedt]

[-- Attachment #1: 0001-sched-Move-sched_feature-file-setup-into-debug.c.patch --]
[-- Type: text/plain, Size: 6768 bytes --]

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

As sched_feature is only created when SCHED_DEBUG is enabled, and the file
debug.c is only compiled when SCHED_DEBUG is enabled, it makes sense to move
sched_feature setup into that file and get rid of the #ifdef.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/sched/core.c  | 133 ---------------------------------------------------
 kernel/sched/debug.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 131 insertions(+), 133 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9503d590e5ef..d075665e4638 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -66,7 +66,6 @@
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
-#include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
@@ -124,138 +123,6 @@ const_debug unsigned int sysctl_sched_features =
 
 #undef SCHED_FEAT
 
-#ifdef CONFIG_SCHED_DEBUG
-#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 HAVE_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(&sched_feat_keys[i]);
-}
-
-static void sched_feat_enable(int i)
-{
-	static_key_enable(&sched_feat_keys[i]);
-}
-#else
-static void sched_feat_disable(int i) { };
-static void sched_feat_enable(int i) { };
-#endif /* HAVE_JUMP_LABEL */
-
-static int sched_feat_set(char *cmp)
-{
-	int i;
-	int neg = 0;
-
-	if (strncmp(cmp, "NO_", 3) == 0) {
-		neg = 1;
-		cmp += 3;
-	}
-
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg) {
-				sysctl_sched_features &= ~(1UL << i);
-				sched_feat_disable(i);
-			} else {
-				sysctl_sched_features |= (1UL << i);
-				sched_feat_enable(i);
-			}
-			break;
-		}
-	}
-
-	return i;
-}
-
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-		size_t cnt, loff_t *ppos)
-{
-	char buf[64];
-	char *cmp;
-	int i;
-	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);
-	inode_lock(inode);
-	i = sched_feat_set(cmp);
-	inode_unlock(inode);
-	if (i == __SCHED_FEAT_NR)
-		return -EINVAL;
-
-	*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,
-};
-
-static __init int sched_init_debug(void)
-{
-	debugfs_create_file("sched_features", 0644, NULL, NULL,
-			&sched_feat_fops);
-
-	return 0;
-}
-late_initcall(sched_init_debug);
-#endif /* CONFIG_SCHED_DEBUG */
-
 /*
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 641511771ae6..593178be8124 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -16,6 +16,7 @@
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
 #include <linux/mempolicy.h>
+#include <linux/debugfs.h>
 
 #include "sched.h"
 
@@ -58,6 +59,136 @@ static unsigned long nsec_low(unsigned long long nsec)
 
 #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 HAVE_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(&sched_feat_keys[i]);
+}
+
+static void sched_feat_enable(int i)
+{
+	static_key_enable(&sched_feat_keys[i]);
+}
+#else
+static void sched_feat_disable(int i) { };
+static void sched_feat_enable(int i) { };
+#endif /* HAVE_JUMP_LABEL */
+
+static int sched_feat_set(char *cmp)
+{
+	int i;
+	int neg = 0;
+
+	if (strncmp(cmp, "NO_", 3) == 0) {
+		neg = 1;
+		cmp += 3;
+	}
+
+	for (i = 0; i < __SCHED_FEAT_NR; i++) {
+		if (strcmp(cmp, sched_feat_names[i]) == 0) {
+			if (neg) {
+				sysctl_sched_features &= ~(1UL << i);
+				sched_feat_disable(i);
+			} else {
+				sysctl_sched_features |= (1UL << i);
+				sched_feat_enable(i);
+			}
+			break;
+		}
+	}
+
+	return i;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	char *cmp;
+	int i;
+	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);
+	inode_lock(inode);
+	i = sched_feat_set(cmp);
+	inode_unlock(inode);
+	if (i == __SCHED_FEAT_NR)
+		return -EINVAL;
+
+	*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,
+};
+
+static __init int sched_init_debug(void)
+{
+	debugfs_create_file("sched_features", 0644, NULL, NULL,
+			&sched_feat_fops);
+
+	return 0;
+}
+late_initcall(sched_init_debug);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
-- 
2.6.4

[PATCH 2/4] sched: Move sched_domain_sysctl to debug.c

[Steven Rostedt]

[-- Attachment #1: 0002-sched-Move-sched_domain_sysctl-to-debug.c.patch --]
[-- Type: text/plain, Size: 11900 bytes --]

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

The sched_domain_sysctl setup is only enabled when SCHED_DEBUG is
configured. As debug.c is only compiled when SCHED_DEBUG is configured as
well, move the setup of sched_domain_sysctl into that file.

Note, the (un)register_sched_domain_sysctl() functions had to be changed
from static to allow access to them from core.c.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/sched/core.c  | 178 ---------------------------------------------------
 kernel/sched/debug.c | 173 +++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h |  13 ++++
 3 files changed, 186 insertions(+), 178 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d075665e4638..f1ce7a804da4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -70,7 +70,6 @@
 #include <linux/ftrace.h>
 #include <linux/slab.h>
 #include <linux/init_task.h>
-#include <linux/binfmts.h>
 #include <linux/context_tracking.h>
 #include <linux/compiler.h>
 
@@ -5272,183 +5271,6 @@ static void migrate_tasks(struct rq *dead_rq)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(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 int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX-1;
-
-static void
-set_table_entry(struct ctl_table *entry,
-		const char *procname, void *data, int maxlen,
-		umode_t mode, proc_handler *proc_handler,
-		bool load_idx)
-{
-	entry->procname = procname;
-	entry->data = data;
-	entry->maxlen = maxlen;
-	entry->mode = mode;
-	entry->proc_handler = proc_handler;
-
-	if (load_idx) {
-		entry->extra1 = &min_load_idx;
-		entry->extra2 = &max_load_idx;
-	}
-}
-
-static struct ctl_table *
-sd_alloc_ctl_domain_table(struct sched_domain *sd)
-{
-	struct ctl_table *table = sd_alloc_ctl_entry(14);
-
-	if (table == NULL)
-		return NULL;
-
-	set_table_entry(&table[0], "min_interval", &sd->min_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[1], "max_interval", &sd->max_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[9], "cache_nice_tries",
-		&sd->cache_nice_tries,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[10], "flags", &sd->flags,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[11], "max_newidle_lb_cost",
-		&sd->max_newidle_lb_cost,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[12], "name", sd->name,
-		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
-	/* &table[13] 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 struct ctl_table_header *sd_sysctl_header;
-static void register_sched_domain_sysctl(void)
-{
-	int i, cpu_num = num_possible_cpus();
-	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
-	char buf[32];
-
-	WARN_ON(sd_ctl_dir[0].child);
-	sd_ctl_dir[0].child = entry;
-
-	if (entry == NULL)
-		return;
-
-	for_each_possible_cpu(i) {
-		snprintf(buf, 32, "cpu%d", i);
-		entry->procname = kstrdup(buf, GFP_KERNEL);
-		entry->mode = 0555;
-		entry->child = sd_alloc_ctl_cpu_table(i);
-		entry++;
-	}
-
-	WARN_ON(sd_sysctl_header);
-	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
-}
-
-/* may be called multiple times per register */
-static void unregister_sched_domain_sysctl(void)
-{
-	unregister_sysctl_table(sd_sysctl_header);
-	sd_sysctl_header = NULL;
-	if (sd_ctl_dir[0].child)
-		sd_free_ctl_entry(&sd_ctl_dir[0].child);
-}
-#else
-static void register_sched_domain_sysctl(void)
-{
-}
-static void unregister_sched_domain_sysctl(void)
-{
-}
-#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */
-
 static void set_rq_online(struct rq *rq)
 {
 	if (!rq->online) {
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 593178be8124..a5625e793d15 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -189,6 +189,179 @@ static __init int sched_init_debug(void)
 }
 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 int min_load_idx = 0;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
+
+static void
+set_table_entry(struct ctl_table *entry,
+		const char *procname, void *data, int maxlen,
+		umode_t mode, proc_handler *proc_handler,
+		bool load_idx)
+{
+	entry->procname = procname;
+	entry->data = data;
+	entry->maxlen = maxlen;
+	entry->mode = mode;
+	entry->proc_handler = proc_handler;
+
+	if (load_idx) {
+		entry->extra1 = &min_load_idx;
+		entry->extra2 = &max_load_idx;
+	}
+}
+
+static struct ctl_table *
+sd_alloc_ctl_domain_table(struct sched_domain *sd)
+{
+	struct ctl_table *table = sd_alloc_ctl_entry(14);
+
+	if (table == NULL)
+		return NULL;
+
+	set_table_entry(&table[0], "min_interval", &sd->min_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[1], "max_interval", &sd->max_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[9], "cache_nice_tries",
+		&sd->cache_nice_tries,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[10], "flags", &sd->flags,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[11], "max_newidle_lb_cost",
+		&sd->max_newidle_lb_cost,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[12], "name", sd->name,
+		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
+	/* &table[13] 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 struct ctl_table_header *sd_sysctl_header;
+void register_sched_domain_sysctl(void)
+{
+	int i, cpu_num = num_possible_cpus();
+	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
+	char buf[32];
+
+	WARN_ON(sd_ctl_dir[0].child);
+	sd_ctl_dir[0].child = entry;
+
+	if (entry == NULL)
+		return;
+
+	for_each_possible_cpu(i) {
+		snprintf(buf, 32, "cpu%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_cpu_table(i);
+		entry++;
+	}
+
+	WARN_ON(sd_sysctl_header);
+	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
+}
+
+/* may be called multiple times per register */
+void unregister_sched_domain_sysctl(void)
+{
+	unregister_sysctl_table(sd_sysctl_header);
+	sd_sysctl_header = NULL;
+	if (sd_ctl_dir[0].child)
+		sd_free_ctl_entry(&sd_ctl_dir[0].child);
+}
+#endif /* CONFIG_SYSCTL */
+#endif /* CONFIG_SMP */
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 10f16374df7f..b146f5298cb1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3,6 +3,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
+#include <linux/binfmts.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
@@ -909,6 +910,18 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
+void register_sched_domain_sysctl(void);
+void unregister_sched_domain_sysctl(void);
+#else
+static inline void register_sched_domain_sysctl(void)
+{
+}
+static inline void unregister_sched_domain_sysctl(void)
+{
+}
+#endif
+
 #else
 
 static inline void sched_ttwu_pending(void) { }
-- 
2.6.4

[PATCH 3/4] sched: Add bandwidth ratio to /proc/sched_debug

[Steven Rostedt]

[-- Attachment #1: 0003-sched-Add-bandwidth-ratio-to-proc-sched_debug.patch --]
[-- Type: text/plain, Size: 4010 bytes --]

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

Playing with SCHED_DEADLINE and cpusets, I found that I was unable to create
new SCHED_DEADLINE tasks, with the error of EBUSY as if the bandwidth was
already used up. I then realized there wa no way to see what bandwidth is
used by the runqueues to debug the issue.

By adding the dl_bw->bw and dl_bw->total_bw to the output of the deadline
info in /proc/sched_debug, this allows us to see what bandwidth has been
reserved and where a problem may exist.

For example, before the issue we see the ratio of the bandwidth:

 # cat /proc/sys/kernel/sched_rt_runtime_us
 950000
 # cat /proc/sys/kernel/sched_rt_period_us
 1000000

  # grep dl /proc/sched_debug
  dl_rq[0]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[1]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[2]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[3]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[4]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[5]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[6]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[7]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0

Note: (950000 / 1000000) << 20 == 996147

After I played with cpusets and hit the issue, the result is now:

  # grep dl /proc/sched_debug
  dl_rq[0]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857
  dl_rq[1]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 104857
  dl_rq[2]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 104857
  dl_rq[3]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 104857
  dl_rq[4]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857
  dl_rq[5]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857
  dl_rq[6]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857
  dl_rq[7]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857

This shows that there is definitely a problem as we should never have a
negative total bandwidth.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/sched/debug.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index a5625e793d15..a1f161a7500e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -562,8 +562,17 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 
 void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 {
+	struct dl_bw *dl_bw;
+
 	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
 	SEQ_printf(m, "  .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
+#ifdef CONFIG_SMP
+	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
+#else
+	dl_bw = &dl_rq->dl_bw;
+#endif
+	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
+	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
 }
 
 extern __read_mostly int sched_clock_running;
-- 
2.6.4

[PATCH 4/4] tracing: Add __print_ns_to_secs() and __print_ns_without_secs() helpers

[Steven Rostedt]

[-- Attachment #1: 0004-tracing-Add-__print_ns_to_secs-and-__print_ns_withou.patch --]
[-- Type: text/plain, Size: 2556 bytes --]

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

To have nanosecond output displayed in a more human readable format, its
nicer to convert it to a seconds format (XXX.YYYYYYYYY). The problem is that
to do so, the numbers must be divided by NSEC_PER_SEC, and moded too. But as
these numbers are 64 bit, this can not be done simply with '/' and '%'
operators, but must use do_div() instead.

Instead of performing the expensive do_div() in the hot path of the
tracepoint, it is more efficient to perform it during the output phase. But
passing in do_div() can confuse the parser, and do_div() doesn't work
exactly like a normal C function. It modifies the number in place, and we
don't want to modify the actual values in the ring buffer.

Two helper functions are now created:

  __print_ns_to_secs() and __print_ns_without_secs()

They both take a value of nanoseconds, and the former will return that
number divided by NSEC_PER_SEC, and the latter will mod it with NSEC_PER_SEC
giving a way to print a nice human readable format:

 __print_fmt("time=%llu.%09u",
	__print_ns_to_secs(REC->nsec_val),
	__print_ns_without_secs(REC->nsec_val))

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/trace_events.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index 170c93bbdbb7..a1fef8fc352d 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -283,6 +283,21 @@ TRACE_MAKE_SYSTEM_STR();
 		trace_print_symbols_seq(p, value, symbols);		\
 	})
 
+#undef __print_ns_to_secs
+#define __print_ns_to_secs(value)			\
+	({						\
+		u64 ____val = (u64)value;		\
+		do_div(____val, NSEC_PER_SEC);		\
+		____val;				\
+	})
+
+#undef __print_ns_without_secs
+#define __print_ns_without_secs(value)			\
+	({						\
+		u64 ____val = (u64)value;		\
+		do_div(____val, NSEC_PER_SEC);		\
+	})
+	
 #undef __print_symbolic_u64
 #if BITS_PER_LONG == 32
 #define __print_symbolic_u64(value, symbol_array...)			\
@@ -720,6 +735,16 @@ static inline void ftrace_test_probe_##call(void)			\
 #undef __get_bitmask
 #undef __print_array
 
+/*
+ * The below is not executed in the kernel. It is only what is
+ * displayed in the print format for userspace to parse.
+ */
+#undef __print_ns_to_secs
+#define __print_ns_to_secs(val) val / 1000000000UL
+
+#undef __print_ns_without_secs
+#define __print_ns_without_secs(val) val % 1000000000UL
+
 #undef TP_printk
 #define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
 
-- 
2.6.4

Re: [PATCH 3/4] sched: Add bandwidth ratio to /proc/sched_debug

[Juri Lelli]

Hi Steve,

On 22/02/16 16:26, Steven Rostedt wrote:
> From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
> 
> Playing with SCHED_DEADLINE and cpusets, I found that I was unable to create
> new SCHED_DEADLINE tasks, with the error of EBUSY as if the bandwidth was
> already used up. I then realized there wa no way to see what bandwidth is
> used by the runqueues to debug the issue.
> 
> By adding the dl_bw->bw and dl_bw->total_bw to the output of the deadline
> info in /proc/sched_debug, this allows us to see what bandwidth has been
> reserved and where a problem may exist.
> 

[...]

> 
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

This is pretty useful yes.

FWIW,
Acked-by: Juri Lelli <juri.lelli@arm.com>

Best,

- Juri

Re: [PATCH 4/4] tracing: Add __print_ns_to_secs() and __print_ns_without_secs() helpers

[Peter Zijlstra]

On Mon, Feb 22, 2016 at 04:26:53PM -0500, Steven Rostedt wrote:
> From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
> 
> To have nanosecond output displayed in a more human readable format, its
> nicer to convert it to a seconds format (XXX.YYYYYYYYY). The problem is that
> to do so, the numbers must be divided by NSEC_PER_SEC, and moded too. But as
> these numbers are 64 bit, this can not be done simply with '/' and '%'
> operators, but must use do_div() instead.

Would not div_[us]64_rem() make more sense? It would typically result in
just the one division, instead of two.

Re: [PATCH 4/4] tracing: Add __print_ns_to_secs() and __print_ns_without_secs() helpers

[Steven Rostedt]

On Tue, 23 Feb 2016 13:49:15 +0100
Peter Zijlstra <peterz@infradead.org> wrote:

> On Mon, Feb 22, 2016 at 04:26:53PM -0500, Steven Rostedt wrote:
> > From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
> > 
> > To have nanosecond output displayed in a more human readable format, its
> > nicer to convert it to a seconds format (XXX.YYYYYYYYY). The problem is that
> > to do so, the numbers must be divided by NSEC_PER_SEC, and moded too. But as
> > these numbers are 64 bit, this can not be done simply with '/' and '%'
> > operators, but must use do_div() instead.  
> 
> Would not div_[us]64_rem() make more sense? It would typically result in
> just the one division, instead of two.

The problem is, how do you do that in a printf() statement?

We have "%llu.%09ul" which is two arguments in the printf(). And the
values we are processing can't be modified. Which is why the macro uses
({ }) and creates a temp variable.

-- Steve

Re: [PATCH 4/4] tracing: Add __print_ns_to_secs() and __print_ns_without_secs() helpers

[Peter Zijlstra]

On Tue, Feb 23, 2016 at 08:17:57AM -0500, Steven Rostedt wrote:
> On Tue, 23 Feb 2016 13:49:15 +0100
> Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > On Mon, Feb 22, 2016 at 04:26:53PM -0500, Steven Rostedt wrote:
> > > From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
> > > 
> > > To have nanosecond output displayed in a more human readable format, its
> > > nicer to convert it to a seconds format (XXX.YYYYYYYYY). The problem is that
> > > to do so, the numbers must be divided by NSEC_PER_SEC, and moded too. But as
> > > these numbers are 64 bit, this can not be done simply with '/' and '%'
> > > operators, but must use do_div() instead.  
> > 
> > Would not div_[us]64_rem() make more sense? It would typically result in
> > just the one division, instead of two.
> 
> The problem is, how do you do that in a printf() statement?
> 
> We have "%llu.%09ul" which is two arguments in the printf(). And the
> values we are processing can't be modified. Which is why the macro uses
> ({ }) and creates a temp variable.

Hurm,. yes that's not something easily done. We need a temporary limited
in scope to the printf statement, and C doesn't really do that.

Re: [PATCH 4/4] tracing: Add __print_ns_to_secs() and __print_ns_without_secs() helpers

[Steven Rostedt]

On Tue, 23 Feb 2016 15:01:43 +0100
Peter Zijlstra <peterz@infradead.org> wrote:


> > We have "%llu.%09ul" which is two arguments in the printf(). And the
> > values we are processing can't be modified. Which is why the macro uses
> > ({ }) and creates a temp variable.  
> 
> Hurm,. yes that's not something easily done. We need a temporary limited
> in scope to the printf statement, and C doesn't really do that.

The nice thing is, the division is done on output, which is considered
the slow path. Having two divisions instead of just one may be
inconvenient, but it's not slowing much down. And that's only performed
when reading the ASCII trace files. If you use perf or trace-cmd, the
event-parser will do the work for you at post processing.

-- Steve

[tip:sched/core] sched/debug: Move the /sys/kernel/debug/sched_features file setup into debug.c

[tip-bot for Steven Rostedt (Red Hat)]

Commit-ID:  d6ca41d7922ce0110a840ef4f8ec4afdd5a239d3
Gitweb:     http://git.kernel.org/tip/d6ca41d7922ce0110a840ef4f8ec4afdd5a239d3
Author:     Steven Rostedt (Red Hat) <rostedt@goodmis.org>
AuthorDate: Mon, 22 Feb 2016 16:26:50 -0500
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Mon, 29 Feb 2016 09:53:06 +0100

sched/debug: Move the /sys/kernel/debug/sched_features file setup into debug.c

As /sys/kernel/debug/sched_features is only created when SCHED_DEBUG is enabled, and the file
debug.c is only compiled when SCHED_DEBUG is enabled, it makes sense to move
sched_feature setup into that file and get rid of the #ifdef.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160222212825.464193063@goodmis.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  | 133 ---------------------------------------------------
 kernel/sched/debug.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 131 insertions(+), 133 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bb565b4..ffaaeb8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -66,7 +66,6 @@
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
-#include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
@@ -124,138 +123,6 @@ const_debug unsigned int sysctl_sched_features =
 
 #undef SCHED_FEAT
 
-#ifdef CONFIG_SCHED_DEBUG
-#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 HAVE_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(&sched_feat_keys[i]);
-}
-
-static void sched_feat_enable(int i)
-{
-	static_key_enable(&sched_feat_keys[i]);
-}
-#else
-static void sched_feat_disable(int i) { };
-static void sched_feat_enable(int i) { };
-#endif /* HAVE_JUMP_LABEL */
-
-static int sched_feat_set(char *cmp)
-{
-	int i;
-	int neg = 0;
-
-	if (strncmp(cmp, "NO_", 3) == 0) {
-		neg = 1;
-		cmp += 3;
-	}
-
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg) {
-				sysctl_sched_features &= ~(1UL << i);
-				sched_feat_disable(i);
-			} else {
-				sysctl_sched_features |= (1UL << i);
-				sched_feat_enable(i);
-			}
-			break;
-		}
-	}
-
-	return i;
-}
-
-static ssize_t
-sched_feat_write(struct file *filp, const char __user *ubuf,
-		size_t cnt, loff_t *ppos)
-{
-	char buf[64];
-	char *cmp;
-	int i;
-	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);
-	inode_lock(inode);
-	i = sched_feat_set(cmp);
-	inode_unlock(inode);
-	if (i == __SCHED_FEAT_NR)
-		return -EINVAL;
-
-	*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,
-};
-
-static __init int sched_init_debug(void)
-{
-	debugfs_create_file("sched_features", 0644, NULL, NULL,
-			&sched_feat_fops);
-
-	return 0;
-}
-late_initcall(sched_init_debug);
-#endif /* CONFIG_SCHED_DEBUG */
-
 /*
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 7cfa87b..d2dedfc 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -16,6 +16,7 @@
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
 #include <linux/mempolicy.h>
+#include <linux/debugfs.h>
 
 #include "sched.h"
 
@@ -58,6 +59,136 @@ static unsigned long nsec_low(unsigned long long nsec)
 
 #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 HAVE_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(&sched_feat_keys[i]);
+}
+
+static void sched_feat_enable(int i)
+{
+	static_key_enable(&sched_feat_keys[i]);
+}
+#else
+static void sched_feat_disable(int i) { };
+static void sched_feat_enable(int i) { };
+#endif /* HAVE_JUMP_LABEL */
+
+static int sched_feat_set(char *cmp)
+{
+	int i;
+	int neg = 0;
+
+	if (strncmp(cmp, "NO_", 3) == 0) {
+		neg = 1;
+		cmp += 3;
+	}
+
+	for (i = 0; i < __SCHED_FEAT_NR; i++) {
+		if (strcmp(cmp, sched_feat_names[i]) == 0) {
+			if (neg) {
+				sysctl_sched_features &= ~(1UL << i);
+				sched_feat_disable(i);
+			} else {
+				sysctl_sched_features |= (1UL << i);
+				sched_feat_enable(i);
+			}
+			break;
+		}
+	}
+
+	return i;
+}
+
+static ssize_t
+sched_feat_write(struct file *filp, const char __user *ubuf,
+		size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	char *cmp;
+	int i;
+	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);
+	inode_lock(inode);
+	i = sched_feat_set(cmp);
+	inode_unlock(inode);
+	if (i == __SCHED_FEAT_NR)
+		return -EINVAL;
+
+	*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,
+};
+
+static __init int sched_init_debug(void)
+{
+	debugfs_create_file("sched_features", 0644, NULL, NULL,
+			&sched_feat_fops);
+
+	return 0;
+}
+late_initcall(sched_init_debug);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {

[tip:sched/core] sched/debug: Move sched_domain_sysctl to debug.c

[tip-bot for Steven Rostedt (Red Hat)]

Commit-ID:  3866e845ed522258c77da2eaa9f849ef55206ca2
Gitweb:     http://git.kernel.org/tip/3866e845ed522258c77da2eaa9f849ef55206ca2
Author:     Steven Rostedt (Red Hat) <rostedt@goodmis.org>
AuthorDate: Mon, 22 Feb 2016 16:26:51 -0500
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Mon, 29 Feb 2016 09:53:06 +0100

sched/debug: Move sched_domain_sysctl to debug.c

The sched_domain_sysctl setup is only enabled when SCHED_DEBUG is
configured. As debug.c is only compiled when SCHED_DEBUG is configured as
well, move the setup of sched_domain_sysctl into that file.

Note, the (un)register_sched_domain_sysctl() functions had to be changed
from static to allow access to them from core.c.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160222212825.599278093@goodmis.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  | 178 ---------------------------------------------------
 kernel/sched/debug.c | 173 +++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h |  13 ++++
 3 files changed, 186 insertions(+), 178 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ffaaeb8..6dbb21f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -70,7 +70,6 @@
 #include <linux/ftrace.h>
 #include <linux/slab.h>
 #include <linux/init_task.h>
-#include <linux/binfmts.h>
 #include <linux/context_tracking.h>
 #include <linux/compiler.h>
 
@@ -5342,183 +5341,6 @@ static void migrate_tasks(struct rq *dead_rq)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(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 int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX-1;
-
-static void
-set_table_entry(struct ctl_table *entry,
-		const char *procname, void *data, int maxlen,
-		umode_t mode, proc_handler *proc_handler,
-		bool load_idx)
-{
-	entry->procname = procname;
-	entry->data = data;
-	entry->maxlen = maxlen;
-	entry->mode = mode;
-	entry->proc_handler = proc_handler;
-
-	if (load_idx) {
-		entry->extra1 = &min_load_idx;
-		entry->extra2 = &max_load_idx;
-	}
-}
-
-static struct ctl_table *
-sd_alloc_ctl_domain_table(struct sched_domain *sd)
-{
-	struct ctl_table *table = sd_alloc_ctl_entry(14);
-
-	if (table == NULL)
-		return NULL;
-
-	set_table_entry(&table[0], "min_interval", &sd->min_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[1], "max_interval", &sd->max_interval,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
-		sizeof(int), 0644, proc_dointvec_minmax, true);
-	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[9], "cache_nice_tries",
-		&sd->cache_nice_tries,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[10], "flags", &sd->flags,
-		sizeof(int), 0644, proc_dointvec_minmax, false);
-	set_table_entry(&table[11], "max_newidle_lb_cost",
-		&sd->max_newidle_lb_cost,
-		sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[12], "name", sd->name,
-		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
-	/* &table[13] 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 struct ctl_table_header *sd_sysctl_header;
-static void register_sched_domain_sysctl(void)
-{
-	int i, cpu_num = num_possible_cpus();
-	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
-	char buf[32];
-
-	WARN_ON(sd_ctl_dir[0].child);
-	sd_ctl_dir[0].child = entry;
-
-	if (entry == NULL)
-		return;
-
-	for_each_possible_cpu(i) {
-		snprintf(buf, 32, "cpu%d", i);
-		entry->procname = kstrdup(buf, GFP_KERNEL);
-		entry->mode = 0555;
-		entry->child = sd_alloc_ctl_cpu_table(i);
-		entry++;
-	}
-
-	WARN_ON(sd_sysctl_header);
-	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
-}
-
-/* may be called multiple times per register */
-static void unregister_sched_domain_sysctl(void)
-{
-	unregister_sysctl_table(sd_sysctl_header);
-	sd_sysctl_header = NULL;
-	if (sd_ctl_dir[0].child)
-		sd_free_ctl_entry(&sd_ctl_dir[0].child);
-}
-#else
-static void register_sched_domain_sysctl(void)
-{
-}
-static void unregister_sched_domain_sysctl(void)
-{
-}
-#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */
-
 static void set_rq_online(struct rq *rq)
 {
 	if (!rq->online) {
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index d2dedfc..313c65f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -189,6 +189,179 @@ static __init int sched_init_debug(void)
 }
 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 int min_load_idx = 0;
+static int max_load_idx = CPU_LOAD_IDX_MAX-1;
+
+static void
+set_table_entry(struct ctl_table *entry,
+		const char *procname, void *data, int maxlen,
+		umode_t mode, proc_handler *proc_handler,
+		bool load_idx)
+{
+	entry->procname = procname;
+	entry->data = data;
+	entry->maxlen = maxlen;
+	entry->mode = mode;
+	entry->proc_handler = proc_handler;
+
+	if (load_idx) {
+		entry->extra1 = &min_load_idx;
+		entry->extra2 = &max_load_idx;
+	}
+}
+
+static struct ctl_table *
+sd_alloc_ctl_domain_table(struct sched_domain *sd)
+{
+	struct ctl_table *table = sd_alloc_ctl_entry(14);
+
+	if (table == NULL)
+		return NULL;
+
+	set_table_entry(&table[0], "min_interval", &sd->min_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[1], "max_interval", &sd->max_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
+		sizeof(int), 0644, proc_dointvec_minmax, true);
+	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[9], "cache_nice_tries",
+		&sd->cache_nice_tries,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[10], "flags", &sd->flags,
+		sizeof(int), 0644, proc_dointvec_minmax, false);
+	set_table_entry(&table[11], "max_newidle_lb_cost",
+		&sd->max_newidle_lb_cost,
+		sizeof(long), 0644, proc_doulongvec_minmax, false);
+	set_table_entry(&table[12], "name", sd->name,
+		CORENAME_MAX_SIZE, 0444, proc_dostring, false);
+	/* &table[13] 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 struct ctl_table_header *sd_sysctl_header;
+void register_sched_domain_sysctl(void)
+{
+	int i, cpu_num = num_possible_cpus();
+	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
+	char buf[32];
+
+	WARN_ON(sd_ctl_dir[0].child);
+	sd_ctl_dir[0].child = entry;
+
+	if (entry == NULL)
+		return;
+
+	for_each_possible_cpu(i) {
+		snprintf(buf, 32, "cpu%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_cpu_table(i);
+		entry++;
+	}
+
+	WARN_ON(sd_sysctl_header);
+	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
+}
+
+/* may be called multiple times per register */
+void unregister_sched_domain_sysctl(void)
+{
+	unregister_sysctl_table(sd_sysctl_header);
+	sd_sysctl_header = NULL;
+	if (sd_ctl_dir[0].child)
+		sd_free_ctl_entry(&sd_ctl_dir[0].child);
+}
+#endif /* CONFIG_SYSCTL */
+#endif /* CONFIG_SMP */
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d3606e4..ef5875f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3,6 +3,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
+#include <linux/binfmts.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
@@ -908,6 +909,18 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
+void register_sched_domain_sysctl(void);
+void unregister_sched_domain_sysctl(void);
+#else
+static inline void register_sched_domain_sysctl(void)
+{
+}
+static inline void unregister_sched_domain_sysctl(void)
+{
+}
+#endif
+
 #else
 
 static inline void sched_ttwu_pending(void) { }

[tip:sched/core] sched/debug: Add deadline scheduler bandwidth ratio to /proc/sched_debug

[tip-bot for Steven Rostedt (Red Hat)]

Commit-ID:  ef477183d06b0aa41c9e7c02cf5bfec41536e2c4
Gitweb:     http://git.kernel.org/tip/ef477183d06b0aa41c9e7c02cf5bfec41536e2c4
Author:     Steven Rostedt (Red Hat) <rostedt@goodmis.org>
AuthorDate: Mon, 22 Feb 2016 16:26:52 -0500
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Mon, 29 Feb 2016 09:53:07 +0100

sched/debug: Add deadline scheduler bandwidth ratio to /proc/sched_debug

Playing with SCHED_DEADLINE and cpusets, I found that I was unable to create
new SCHED_DEADLINE tasks, with the error of EBUSY as if the bandwidth was
already used up. I then realized there wa no way to see what bandwidth is
used by the runqueues to debug the issue.

By adding the dl_bw->bw and dl_bw->total_bw to the output of the deadline
info in /proc/sched_debug, this allows us to see what bandwidth has been
reserved and where a problem may exist.

For example, before the issue we see the ratio of the bandwidth:

 # cat /proc/sys/kernel/sched_rt_runtime_us
 950000
 # cat /proc/sys/kernel/sched_rt_period_us
 1000000

  # grep dl /proc/sched_debug
  dl_rq[0]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[1]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[2]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[3]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[4]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[5]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[6]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0
  dl_rq[7]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 0

Note: (950000 / 1000000) << 20 == 996147

After I played with cpusets and hit the issue, the result is now:

  # grep dl /proc/sched_debug
  dl_rq[0]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857
  dl_rq[1]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 104857
  dl_rq[2]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 104857
  dl_rq[3]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : 104857
  dl_rq[4]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857
  dl_rq[5]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857
  dl_rq[6]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857
  dl_rq[7]:
    .dl_nr_running                 : 0
    .dl_bw->bw                     : 996147
    .dl_bw->total_bw               : -104857

This shows that there is definitely a problem as we should never have a
negative total bandwidth.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Clark Williams <williams@redhat.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160222212825.756849091@goodmis.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/debug.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 313c65f..4fbc3bd 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -566,8 +566,17 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 
 void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 {
+	struct dl_bw *dl_bw;
+
 	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
 	SEQ_printf(m, "  .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
+#ifdef CONFIG_SMP
+	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
+#else
+	dl_bw = &dl_rq->dl_bw;
+#endif
+	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
+	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
 }
 
 extern __read_mostly int sched_clock_running;