sched: Add 'autogroup' scheduling feature: automated per session task groups

A recurring complaint from CFS users is that parallel kbuild has
a negative impact on desktop interactivity.  This patch
implements an idea from Linus, to automatically create task
groups.  Currently, only per session autogroups are implemented,
but the patch leaves the way open for enhancement.

Implementation: each task's signal struct contains an inherited
pointer to a refcounted autogroup struct containing a task group
pointer, the default for all tasks pointing to the
init_task_group.  When a task calls setsid(), a new task group
is created, the process is moved into the new task group, and a
reference to the preveious task group is dropped.  Child
processes inherit this task group thereafter, and increase it's
refcount.  When the last thread of a process exits, the
process's reference is dropped, such that when the last process
referencing an autogroup exits, the autogroup is destroyed.

At runqueue selection time, IFF a task has no cgroup assignment,
its current autogroup is used.

Autogroup bandwidth is controllable via setting it's nice level
through the proc filesystem:

  cat /proc/<pid>/autogroup

Displays the task's group and the group's nice level.

  echo <nice level> > /proc/<pid>/autogroup

Sets the task group's shares to the weight of nice <level> task.
Setting nice level is rate limited for !admin users due to the
abuse risk of task group locking.

The feature is enabled from boot by default if
CONFIG_SCHED_AUTOGROUP=y is selected, but can be disabled via
the boot option noautogroup, and can also be turned on/off on
the fly via:

  echo [01] > /proc/sys/kernel/sched_autogroup_enabled

... which will automatically move tasks to/from the root task group.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Markus Trippelsdorf <markus@trippelsdorf.de>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Paul Turner <pjt@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
[ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
LKML-Reference: <1290281700.28711.9.camel@maggy.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/kernel-parameters.txt

@@ -1622,6 +1622,8 @@ and is between 256 and 4096 characters. It is defined in the file
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
+	noautogroup	Disable scheduler automatic task group creation.
+
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem
 			on "Classic" PPC cores.
 

fs/proc/base.c

@@ -1407,6 +1407,82 @@ static const struct file_operations proc_pid_sched_operations = {
 
 #endif
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+/*
+ * Print out autogroup related information:
+ */
+static int sched_autogroup_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct task_struct *p;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+	proc_sched_autogroup_show_task(p, m);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static ssize_t
+sched_autogroup_write(struct file *file, const char __user *buf,
+	    size_t count, loff_t *offset)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct task_struct *p;
+	char buffer[PROC_NUMBUF];
+	long nice;
+	int err;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+
+	err = strict_strtol(strstrip(buffer), 0, &nice);
+	if (err)
+		return -EINVAL;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	err = nice;
+	err = proc_sched_autogroup_set_nice(p, &err);
+	if (err)
+		count = err;
+
+	put_task_struct(p);
+
+	return count;
+}
+
+static int sched_autogroup_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+
+	ret = single_open(filp, sched_autogroup_show, NULL);
+	if (!ret) {
+		struct seq_file *m = filp->private_data;
+
+		m->private = inode;
+	}
+	return ret;
+}
+
+static const struct file_operations proc_pid_sched_autogroup_operations = {
+	.open		= sched_autogroup_open,
+	.read		= seq_read,
+	.write		= sched_autogroup_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+#endif /* CONFIG_SCHED_AUTOGROUP */
+
 static ssize_t comm_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *offset)
 {
@@ -2732,6 +2808,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 	INF("limits",	  S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
+#endif
+#ifdef CONFIG_SCHED_AUTOGROUP
+	REG("autogroup",  S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
 #endif
 	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK

include/linux/sched.h

@@ -509,6 +509,8 @@ struct thread_group_cputimer {
 	spinlock_t lock;
 };
 
+struct autogroup;
+
 /*
  * NOTE! "signal_struct" does not have it's own
  * locking, because a shared signal_struct always
@@ -576,6 +578,9 @@ struct signal_struct {
 
 	struct tty_struct *tty; /* NULL if no tty */
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+	struct autogroup *autogroup;
+#endif
 	/*
 	 * Cumulative resource counters for dead threads in the group,
 	 * and for reaped dead child processes forked by this group.
@@ -1927,6 +1932,24 @@ int sched_rt_handler(struct ctl_table *table, int write,
 
 extern unsigned int sysctl_sched_compat_yield;
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+extern unsigned int sysctl_sched_autogroup_enabled;
+
+extern void sched_autogroup_create_attach(struct task_struct *p);
+extern void sched_autogroup_detach(struct task_struct *p);
+extern void sched_autogroup_fork(struct signal_struct *sig);
+extern void sched_autogroup_exit(struct signal_struct *sig);
+#ifdef CONFIG_PROC_FS
+extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
+extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice);
+#endif
+#else
+static inline void sched_autogroup_create_attach(struct task_struct *p) { }
+static inline void sched_autogroup_detach(struct task_struct *p) { }
+static inline void sched_autogroup_fork(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit(struct signal_struct *sig) { }
+#endif
+
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);

init/Kconfig

@@ -728,6 +728,19 @@ config NET_NS
 
 endif # NAMESPACES
 
+config SCHED_AUTOGROUP
+	bool "Automatic process group scheduling"
+	select EVENTFD
+	select CGROUPS
+	select CGROUP_SCHED
+	select FAIR_GROUP_SCHED
+	help
+	  This option optimizes the scheduler for common desktop workloads by
+	  automatically creating and populating task groups.  This separation
+	  of workloads isolates aggressive CPU burners (like build jobs) from
+	  desktop applications.  Task group autogeneration is currently based
+	  upon task session.
+
 config MM_OWNER
 	bool
 

kernel/fork.c

@@ -174,8 +174,10 @@ static inline void free_signal_struct(struct signal_struct *sig)
 
 static inline void put_signal_struct(struct signal_struct *sig)
 {
-	if (atomic_dec_and_test(&sig->sigcnt))
+	if (atomic_dec_and_test(&sig->sigcnt)) {
+		sched_autogroup_exit(sig);
 		free_signal_struct(sig);
+	}
 }
 
 void __put_task_struct(struct task_struct *tsk)
@@ -904,6 +906,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	posix_cpu_timers_init_group(sig);
 
 	tty_audit_fork(sig);
+	sched_autogroup_fork(sig);
 
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;

kernel/sched.c

@@ -79,6 +79,7 @@
 
 #include "sched_cpupri.h"
 #include "workqueue_sched.h"
+#include "sched_autogroup.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
@@ -271,6 +272,10 @@ struct task_group {
 	struct task_group *parent;
 	struct list_head siblings;
 	struct list_head children;
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+	struct autogroup *autogroup;
+#endif
 };
 
 #define root_task_group init_task_group
@@ -603,11 +608,14 @@ static inline int cpu_of(struct rq *rq)
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
+	struct task_group *tg;
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
-	return container_of(css, struct task_group, css);
+	tg = container_of(css, struct task_group, css);
+
+	return autogroup_task_group(p, tg);
 }
 
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -1869,6 +1877,7 @@ static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_autogroup.c"
 #include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
@@ -7750,7 +7759,7 @@ void __init sched_init(void)
 #ifdef CONFIG_CGROUP_SCHED
 	list_add(&init_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&init_task_group.children);
-
+	autogroup_init(&init_task);
 #endif /* CONFIG_CGROUP_SCHED */
 
 	for_each_possible_cpu(i) {

kernel/sched_autogroup.c

@@ -0,0 +1,229 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/utsname.h>
+
+unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
+static struct autogroup autogroup_default;
+static atomic_t autogroup_seq_nr;
+
+static void autogroup_init(struct task_struct *init_task)
+{
+	autogroup_default.tg = &init_task_group;
+	init_task_group.autogroup = &autogroup_default;
+	kref_init(&autogroup_default.kref);
+	init_rwsem(&autogroup_default.lock);
+	init_task->signal->autogroup = &autogroup_default;
+}
+
+static inline void autogroup_free(struct task_group *tg)
+{
+	kfree(tg->autogroup);
+}
+
+static inline void autogroup_destroy(struct kref *kref)
+{
+	struct autogroup *ag = container_of(kref, struct autogroup, kref);
+
+	sched_destroy_group(ag->tg);
+}
+
+static inline void autogroup_kref_put(struct autogroup *ag)
+{
+	kref_put(&ag->kref, autogroup_destroy);
+}
+
+static inline struct autogroup *autogroup_kref_get(struct autogroup *ag)
+{
+	kref_get(&ag->kref);
+	return ag;
+}
+
+static inline struct autogroup *autogroup_create(void)
+{
+	struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL);
+	struct task_group *tg;
+
+	if (!ag)
+		goto out_fail;
+
+	tg = sched_create_group(&init_task_group);
+
+	if (IS_ERR(tg))
+		goto out_free;
+
+	kref_init(&ag->kref);
+	init_rwsem(&ag->lock);
+	ag->id = atomic_inc_return(&autogroup_seq_nr);
+	ag->tg = tg;
+	tg->autogroup = ag;
+
+	return ag;
+
+out_free:
+	kfree(ag);
+out_fail:
+	if (printk_ratelimit()) {
+		printk(KERN_WARNING "autogroup_create: %s failure.\n",
+			ag ? "sched_create_group()" : "kmalloc()");
+	}
+
+	return autogroup_kref_get(&autogroup_default);
+}
+
+static inline bool
+task_wants_autogroup(struct task_struct *p, struct task_group *tg)
+{
+	if (tg != &root_task_group)
+		return false;
+
+	if (p->sched_class != &fair_sched_class)
+		return false;
+
+	/*
+	 * We can only assume the task group can't go away on us if
+	 * autogroup_move_group() can see us on ->thread_group list.
+	 */
+	if (p->flags & PF_EXITING)
+		return false;
+
+	return true;
+}
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+
+	if (enabled && task_wants_autogroup(p, tg))
+		return p->signal->autogroup->tg;
+
+	return tg;
+}
+
+static void
+autogroup_move_group(struct task_struct *p, struct autogroup *ag)
+{
+	struct autogroup *prev;
+	struct task_struct *t;
+	unsigned long flags;
+
+	BUG_ON(!lock_task_sighand(p, &flags));
+
+	prev = p->signal->autogroup;
+	if (prev == ag) {
+		unlock_task_sighand(p, &flags);
+		return;
+	}
+
+	p->signal->autogroup = autogroup_kref_get(ag);
+
+	t = p;
+	do {
+		sched_move_task(t);
+	} while_each_thread(p, t);
+
+	unlock_task_sighand(p, &flags);
+	autogroup_kref_put(prev);
+}
+
+/* Allocates GFP_KERNEL, cannot be called under any spinlock */
+void sched_autogroup_create_attach(struct task_struct *p)
+{
+	struct autogroup *ag = autogroup_create();
+
+	autogroup_move_group(p, ag);
+	/* drop extra refrence added by autogroup_create() */
+	autogroup_kref_put(ag);
+}
+EXPORT_SYMBOL(sched_autogroup_create_attach);
+
+/* Cannot be called under siglock.  Currently has no users */
+void sched_autogroup_detach(struct task_struct *p)
+{
+	autogroup_move_group(p, &autogroup_default);
+}
+EXPORT_SYMBOL(sched_autogroup_detach);
+
+void sched_autogroup_fork(struct signal_struct *sig)
+{
+	struct task_struct *p = current;
+
+	spin_lock_irq(&p->sighand->siglock);
+	sig->autogroup = autogroup_kref_get(p->signal->autogroup);
+	spin_unlock_irq(&p->sighand->siglock);
+}
+
+void sched_autogroup_exit(struct signal_struct *sig)
+{
+	autogroup_kref_put(sig->autogroup);
+}
+
+static int __init setup_autogroup(char *str)
+{
+	sysctl_sched_autogroup_enabled = 0;
+
+	return 1;
+}
+
+__setup("noautogroup", setup_autogroup);
+
+#ifdef CONFIG_PROC_FS
+
+/* Called with siglock held. */
+int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice)
+{
+	static unsigned long next = INITIAL_JIFFIES;
+	struct autogroup *ag;
+	int err;
+
+	if (*nice < -20 || *nice > 19)
+		return -EINVAL;
+
+	err = security_task_setnice(current, *nice);
+	if (err)
+		return err;
+
+	if (*nice < 0 && !can_nice(current, *nice))
+		return -EPERM;
+
+	/* this is a heavy operation taking global locks.. */
+	if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next))
+		return -EAGAIN;
+
+	next = HZ / 10 + jiffies;
+	ag = autogroup_kref_get(p->signal->autogroup);
+
+	down_write(&ag->lock);
+	err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]);
+	if (!err)
+		ag->nice = *nice;
+	up_write(&ag->lock);
+
+	autogroup_kref_put(ag);
+
+	return err;
+}
+
+void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
+{
+	struct autogroup *ag = autogroup_kref_get(p->signal->autogroup);
+
+	down_read(&ag->lock);
+	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
+	up_read(&ag->lock);
+
+	autogroup_kref_put(ag);
+}
+#endif /* CONFIG_PROC_FS */
+
+#ifdef CONFIG_SCHED_DEBUG
+static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
+{
+	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
+}
+#endif /* CONFIG_SCHED_DEBUG */
+
+#endif /* CONFIG_SCHED_AUTOGROUP */

kernel/sched_autogroup.h

@@ -0,0 +1,32 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+struct autogroup {
+	struct kref		kref;
+	struct task_group	*tg;
+	struct rw_semaphore	lock;
+	unsigned long		id;
+	int			nice;
+};
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg);
+
+#else /* !CONFIG_SCHED_AUTOGROUP */
+
+static inline void autogroup_init(struct task_struct *init_task) {  }
+static inline void autogroup_free(struct task_group *tg) { }
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+	return tg;
+}
+
+#ifdef CONFIG_SCHED_DEBUG
+static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
+{
+	return 0;
+}
+#endif
+
+#endif /* CONFIG_SCHED_AUTOGROUP */

kernel/sched_debug.c

@@ -54,8 +54,7 @@ static unsigned long nsec_low(unsigned long long nsec)
 #define SPLIT_NS(x) nsec_high(x), nsec_low(x)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void print_cfs_group_stats(struct seq_file *m, int cpu,
+static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
-		struct task_group *tg)
 {
 	struct sched_entity *se = tg->se[cpu];
 	if (!se)
@@ -110,16 +109,6 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
 #endif
 
-#ifdef CONFIG_CGROUP_SCHED
-	{
-		char path[64];
-
-		rcu_read_lock();
-		cgroup_path(task_group(p)->css.cgroup, path, sizeof(path));
-		rcu_read_unlock();
-		SEQ_printf(m, " %s", path);
-	}
-#endif
 	SEQ_printf(m, "\n");
 }
 
@@ -147,19 +136,6 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	read_unlock_irqrestore(&tasklist_lock, flags);
 }
 
-#if defined(CONFIG_CGROUP_SCHED) && \
-	(defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED))
-static void task_group_path(struct task_group *tg, char *buf, int buflen)
-{
-	/* may be NULL if the underlying cgroup isn't fully-created yet */
-	if (!tg->css.cgroup) {
-		buf[0] = '\0';
-		return;
-	}
-	cgroup_path(tg->css.cgroup, buf, buflen);
-}
-#endif
-
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
 	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
@@ -168,16 +144,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	struct sched_entity *last;
 	unsigned long flags;
 
-#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
-	char path[128];
-	struct task_group *tg = cfs_rq->tg;
-
-	task_group_path(tg, path, sizeof(path));
-
-	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
-#else
 	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
-#endif
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
 			SPLIT_NS(cfs_rq->exec_clock));
 
@@ -215,7 +182,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %ld\n", "load_contrib",
 			cfs_rq->load_contribution);
 	SEQ_printf(m, "  .%-30s: %d\n", "load_tg",
-			atomic_read(&tg->load_weight));
+			atomic_read(&cfs_rq->tg->load_weight));
 #endif
 
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
@@ -224,17 +191,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 
 void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 {
-#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
-	char path[128];
-	struct task_group *tg = rt_rq->tg;
-
-	task_group_path(tg, path, sizeof(path));
-
-	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
-#else
 	SEQ_printf(m, "\nrt_rq[%d]:\n", cpu);
-#endif
-
 
 #define P(x) \
 	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rt_rq->x))

kernel/sys.c

@@ -1080,8 +1080,10 @@ SYSCALL_DEFINE0(setsid)
 	err = session;
 out:
 	write_unlock_irq(&tasklist_lock);
-	if (err > 0)
+	if (err > 0) {
 		proc_sid_connector(group_leader);
+		sched_autogroup_create_attach(group_leader);
+	}
 	return err;
 }
 

kernel/sysctl.c

@@ -370,6 +370,17 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_SCHED_AUTOGROUP
+	{
+		.procname	= "sched_autogroup_enabled",
+		.data		= &sysctl_sched_autogroup_enabled,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname	= "prove_locking",