Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  llist: Add back llist_add_batch() and llist_del_first() prototypes
  sched: Don't use tasklist_lock for debug prints
  sched: Warn on rt throttling
  sched: Unify the ->cpus_allowed mask copy
  sched: Wrap scheduler p->cpus_allowed access
  sched: Request for idle balance during nohz idle load balance
  sched: Use resched IPI to kick off the nohz idle balance
  sched: Fix idle_cpu()
  llist: Remove cpu_relax() usage in cmpxchg loops
  sched: Convert to struct llist
  llist: Add llist_next()
  irq_work: Use llist in the struct irq_work logic
  llist: Return whether list is empty before adding in llist_add()
  llist: Move cpu_relax() to after the cmpxchg()
  llist: Remove the platform-dependent NMI checks
  llist: Make some llist functions inline
  sched, tracing: Show PREEMPT_ACTIVE state in trace_sched_switch
  sched: Remove redundant test in check_preempt_tick()
  sched: Add documentation for bandwidth control
  sched: Return unused runtime on group dequeue
  ...

Documentation/scheduler/sched-bwc.txt

@@ -0,0 +1,122 @@
+CFS Bandwidth Control
+=====================
+
+[ This document only discusses CPU bandwidth control for SCHED_NORMAL.
+  The SCHED_RT case is covered in Documentation/scheduler/sched-rt-group.txt ]
+
+CFS bandwidth control is a CONFIG_FAIR_GROUP_SCHED extension which allows the
+specification of the maximum CPU bandwidth available to a group or hierarchy.
+
+The bandwidth allowed for a group is specified using a quota and period. Within
+each given "period" (microseconds), a group is allowed to consume only up to
+"quota" microseconds of CPU time.  When the CPU bandwidth consumption of a
+group exceeds this limit (for that period), the tasks belonging to its
+hierarchy will be throttled and are not allowed to run again until the next
+period.
+
+A group's unused runtime is globally tracked, being refreshed with quota units
+above at each period boundary.  As threads consume this bandwidth it is
+transferred to cpu-local "silos" on a demand basis.  The amount transferred
+within each of these updates is tunable and described as the "slice".
+
+Management
+----------
+Quota and period are managed within the cpu subsystem via cgroupfs.
+
+cpu.cfs_quota_us: the total available run-time within a period (in microseconds)
+cpu.cfs_period_us: the length of a period (in microseconds)
+cpu.stat: exports throttling statistics [explained further below]
+
+The default values are:
+	cpu.cfs_period_us=100ms
+	cpu.cfs_quota=-1
+
+A value of -1 for cpu.cfs_quota_us indicates that the group does not have any
+bandwidth restriction in place, such a group is described as an unconstrained
+bandwidth group.  This represents the traditional work-conserving behavior for
+CFS.
+
+Writing any (valid) positive value(s) will enact the specified bandwidth limit.
+The minimum quota allowed for the quota or period is 1ms.  There is also an
+upper bound on the period length of 1s.  Additional restrictions exist when
+bandwidth limits are used in a hierarchical fashion, these are explained in
+more detail below.
+
+Writing any negative value to cpu.cfs_quota_us will remove the bandwidth limit
+and return the group to an unconstrained state once more.
+
+Any updates to a group's bandwidth specification will result in it becoming
+unthrottled if it is in a constrained state.
+
+System wide settings
+--------------------
+For efficiency run-time is transferred between the global pool and CPU local
+"silos" in a batch fashion.  This greatly reduces global accounting pressure
+on large systems.  The amount transferred each time such an update is required
+is described as the "slice".
+
+This is tunable via procfs:
+	/proc/sys/kernel/sched_cfs_bandwidth_slice_us (default=5ms)
+
+Larger slice values will reduce transfer overheads, while smaller values allow
+for more fine-grained consumption.
+
+Statistics
+----------
+A group's bandwidth statistics are exported via 3 fields in cpu.stat.
+
+cpu.stat:
+- nr_periods: Number of enforcement intervals that have elapsed.
+- nr_throttled: Number of times the group has been throttled/limited.
+- throttled_time: The total time duration (in nanoseconds) for which entities
+  of the group have been throttled.
+
+This interface is read-only.
+
+Hierarchical considerations
+---------------------------
+The interface enforces that an individual entity's bandwidth is always
+attainable, that is: max(c_i) <= C. However, over-subscription in the
+aggregate case is explicitly allowed to enable work-conserving semantics
+within a hierarchy.
+  e.g. \Sum (c_i) may exceed C
+[ Where C is the parent's bandwidth, and c_i its children ]
+
+
+There are two ways in which a group may become throttled:
+	a. it fully consumes its own quota within a period
+	b. a parent's quota is fully consumed within its period
+
+In case b) above, even though the child may have runtime remaining it will not
+be allowed to until the parent's runtime is refreshed.
+
+Examples
+--------
+1. Limit a group to 1 CPU worth of runtime.
+
+	If period is 250ms and quota is also 250ms, the group will get
+	1 CPU worth of runtime every 250ms.
+
+	# echo 250000 > cpu.cfs_quota_us /* quota = 250ms */
+	# echo 250000 > cpu.cfs_period_us /* period = 250ms */
+
+2. Limit a group to 2 CPUs worth of runtime on a multi-CPU machine.
+
+	With 500ms period and 1000ms quota, the group can get 2 CPUs worth of
+	runtime every 500ms.
+
+	# echo 1000000 > cpu.cfs_quota_us /* quota = 1000ms */
+	# echo 500000 > cpu.cfs_period_us /* period = 500ms */
+
+	The larger period here allows for increased burst capacity.
+
+3. Limit a group to 20% of 1 CPU.
+
+	With 50ms period, 10ms quota will be equivalent to 20% of 1 CPU.
+
+	# echo 10000 > cpu.cfs_quota_us /* quota = 10ms */
+	# echo 50000 > cpu.cfs_period_us /* period = 50ms */
+
+	By using a small period here we are ensuring a consistent latency
+	response at the expense of burst capacity.
+

drivers/acpi/apei/Kconfig

@@ -14,7 +14,6 @@ config ACPI_APEI_GHES
 	depends on ACPI_APEI && X86
 	select ACPI_HED
 	select IRQ_WORK
-	select LLIST
 	select GENERIC_ALLOCATOR
 	help
 	  Generic Hardware Error Source provides a way to report

include/linux/irq_work.h

@@ -1,20 +1,23 @@
 #ifndef _LINUX_IRQ_WORK_H
 #define _LINUX_IRQ_WORK_H
 
+#include <linux/llist.h>
+
 struct irq_work {
-	struct irq_work *next;
+	unsigned long flags;
+	struct llist_node llnode;
 	void (*func)(struct irq_work *);
 };
 
 static inline
-void init_irq_work(struct irq_work *entry, void (*func)(struct irq_work *))
+void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *))
 {
-	entry->next = NULL;
-	entry->func = func;
+	work->flags = 0;
+	work->func = func;
 }
 
-bool irq_work_queue(struct irq_work *entry);
+bool irq_work_queue(struct irq_work *work);
 void irq_work_run(void);
-void irq_work_sync(struct irq_work *entry);
+void irq_work_sync(struct irq_work *work);
 
 #endif /* _LINUX_IRQ_WORK_H */

include/linux/llist.h

@@ -35,10 +35,30 @@
  *
  * The basic atomic operation of this list is cmpxchg on long.  On
  * architectures that don't have NMI-safe cmpxchg implementation, the
- * list can NOT be used in NMI handler.  So code uses the list in NMI
- * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
+ * list can NOT be used in NMI handlers.  So code that uses the list in
+ * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
+ *
+ * Copyright 2010,2011 Intel Corp.
+ *   Author: Huang Ying <[email protected]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation;
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/kernel.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+
 struct llist_head {
 	struct llist_node *first;
 };
@@ -113,14 +133,55 @@ static inline void init_llist_head(struct llist_head *list)
  * test whether the list is empty without deleting something from the
  * list.
  */
-static inline int llist_empty(const struct llist_head *head)
+static inline bool llist_empty(const struct llist_head *head)
 {
 	return ACCESS_ONCE(head->first) == NULL;
 }
 
-void llist_add(struct llist_node *new, struct llist_head *head);
-void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
-		     struct llist_head *head);
-struct llist_node *llist_del_first(struct llist_head *head);
-struct llist_node *llist_del_all(struct llist_head *head);
+static inline struct llist_node *llist_next(struct llist_node *node)
+{
+	return node->next;
+}
+
+/**
+ * llist_add - add a new entry
+ * @new:	new entry to be added
+ * @head:	the head for your lock-less list
+ *
+ * Return whether list is empty before adding.
+ */
+static inline bool llist_add(struct llist_node *new, struct llist_head *head)
+{
+	struct llist_node *entry, *old_entry;
+
+	entry = head->first;
+	for (;;) {
+		old_entry = entry;
+		new->next = entry;
+		entry = cmpxchg(&head->first, old_entry, new);
+		if (entry == old_entry)
+			break;
+	}
+
+	return old_entry == NULL;
+}
+
+/**
+ * llist_del_all - delete all entries from lock-less list
+ * @head:	the head of lock-less list to delete all entries
+ *
+ * If list is empty, return NULL, otherwise, delete all entries and
+ * return the pointer to the first entry.  The order of entries
+ * deleted is from the newest to the oldest added one.
+ */
+static inline struct llist_node *llist_del_all(struct llist_head *head)
+{
+	return xchg(&head->first, NULL);
+}
+
+extern bool llist_add_batch(struct llist_node *new_first,
+			    struct llist_node *new_last,
+			    struct llist_head *head);
+extern struct llist_node *llist_del_first(struct llist_head *head);
+
 #endif /* LLIST_H */

include/linux/sched.h

@@ -90,6 +90,7 @@ struct sched_param {
 #include <linux/task_io_accounting.h>
 #include <linux/latencytop.h>
 #include <linux/cred.h>
+#include <linux/llist.h>
 
 #include <asm/processor.h>
 
@@ -1224,7 +1225,7 @@ struct task_struct {
 	unsigned int ptrace;
 
 #ifdef CONFIG_SMP
-	struct task_struct *wake_entry;
+	struct llist_node wake_entry;
 	int on_cpu;
 #endif
 	int on_rq;
@@ -2035,6 +2036,10 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { }
 static inline void sched_autogroup_exit(struct signal_struct *sig) { }
 #endif
 
+#ifdef CONFIG_CFS_BANDWIDTH
+extern unsigned int sysctl_sched_cfs_bandwidth_slice;
+#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);

include/trace/events/sched.h

@@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	 * For all intents and purposes a preempted task is a running task.
 	 */
 	if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)
-		state = TASK_RUNNING;
+		state = TASK_RUNNING | TASK_STATE_MAX;
 #endif
 
 	return state;
@@ -137,13 +137,14 @@ TRACE_EVENT(sched_switch,
 		__entry->next_prio	= next->prio;
 	),
 
-	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s ==> next_comm=%s next_pid=%d next_prio=%d",
+	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
-		__entry->prev_state ?
-		  __print_flags(__entry->prev_state, "|",
+		__entry->prev_state & (TASK_STATE_MAX-1) ?
+		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
 				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
 				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
 				{ 128, "W" }) : "R",
+		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
 

init/Kconfig

@@ -715,6 +715,18 @@ config FAIR_GROUP_SCHED
 	depends on CGROUP_SCHED
 	default CGROUP_SCHED
 
+config CFS_BANDWIDTH
+	bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
+	depends on EXPERIMENTAL
+	depends on FAIR_GROUP_SCHED
+	default n
+	help
+	  This option allows users to define CPU bandwidth rates (limits) for
+	  tasks running within the fair group scheduler.  Groups with no limit
+	  set are considered to be unconstrained and will run with no
+	  restriction.
+	  See tip/Documentation/scheduler/sched-bwc.txt for more information.
+
 config RT_GROUP_SCHED
 	bool "Group scheduling for SCHED_RR/FIFO"
 	depends on EXPERIMENTAL