Merge branch 'sched-core-for-linus' of...

Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (31 commits)
  sched: fix warning in fs/proc/base.c
  schedstat: consolidate per-task cpu runtime stats
  sched: use RCU variant of list traversal in for_each_leaf_rt_rq()
  sched, cpuacct: export percpu cpuacct cgroup stats
  sched, cpuacct: refactoring cpuusage_read / cpuusage_write
  sched: optimize update_curr()
  sched: fix wakeup preemption clock
  sched: add missing arch_update_cpu_topology() call
  sched: let arch_update_cpu_topology indicate if topology changed
  sched: idle_balance() does not call load_balance_newidle()
  sched: fix sd_parent_degenerate on non-numa smp machine
  sched: add uid information to sched_debug for CONFIG_USER_SCHED
  sched: move double_unlock_balance() higher
  sched: update comment for move_task_off_dead_cpu
  sched: fix inconsistency when redistribute per-cpu tg->cfs_rq shares
  sched/rt: removed unneeded defintion
  sched: add hierarchical accounting to cpu accounting controller
  sched: include group statistics in /proc/sched_debug
  sched: rename SCHED_NO_NO_OMIT_FRAME_POINTER => SCHED_OMIT_FRAME_POINTER
  sched: clean up SCHED_CPUMASK_ALLOC
  ...

Documentation/controllers/cpuacct.txt

+CPU Accounting Controller
+-------------------------
+
+The CPU accounting controller is used to group tasks using cgroups and
+account the CPU usage of these groups of tasks.
+
+The CPU accounting controller supports multi-hierarchy groups. An accounting
+group accumulates the CPU usage of all of its child groups and the tasks
+directly present in its group.
+
+Accounting groups can be created by first mounting the cgroup filesystem.
+
+# mkdir /cgroups
+# mount -t cgroup -ocpuacct none /cgroups
+
+With the above step, the initial or the parent accounting group
+becomes visible at /cgroups. At bootup, this group includes all the
+tasks in the system. /cgroups/tasks lists the tasks in this cgroup.
+/cgroups/cpuacct.usage gives the CPU time (in nanoseconds) obtained by
+this group which is essentially the CPU time obtained by all the tasks
+in the system.
+
+New accounting groups can be created under the parent group /cgroups.
+
+# cd /cgroups
+# mkdir g1
+# echo $$ > g1
+
+The above steps create a new group g1 and move the current shell
+process (bash) into it. CPU time consumed by this bash and its children
+can be obtained from g1/cpuacct.usage and the same is accumulated in
+/cgroups/cpuacct.usage also.

Documentation/scheduler/sched-arch.txt

@@ -8,7 +8,7 @@ Context switch
 By default, the switch_to arch function is called with the runqueue
 locked. This is usually not a problem unless switch_to may need to
 take the runqueue lock. This is usually due to a wake up operation in
-the context switch. See include/asm-ia64/system.h for an example.
+the context switch. See arch/ia64/include/asm/system.h for an example.
 
 To request the scheduler call switch_to with the runqueue unlocked,
 you must `#define __ARCH_WANT_UNLOCKED_CTXSW` in a header file
@@ -23,7 +23,7 @@ disabled. Interrupts may be enabled over the call if it is likely to
 introduce a significant interrupt latency by adding the line
 `#define __ARCH_WANT_INTERRUPTS_ON_CTXSW` in the same place as for
 unlocked context switches. This define also implies
-`__ARCH_WANT_UNLOCKED_CTXSW`. See include/asm-arm/system.h for an
+`__ARCH_WANT_UNLOCKED_CTXSW`. See arch/arm/include/asm/system.h for an
 example.
 
 

arch/ia64/Kconfig

@@ -99,7 +99,7 @@ config GENERIC_IOMAP
 	bool
 	default y
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
 

arch/m32r/Kconfig

@@ -273,7 +273,7 @@ config GENERIC_CALIBRATE_DELAY
 	bool
 	default y
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
         bool
         default y
 

arch/mips/Kconfig

@@ -653,7 +653,7 @@ config GENERIC_CMOS_UPDATE
 	bool
 	default y
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
 

arch/powerpc/Kconfig

@@ -141,7 +141,7 @@ config GENERIC_NVRAM
 	bool
 	default y if PPC32
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
 

arch/s390/kernel/topology.c

@@ -212,7 +212,7 @@ static void update_cpu_core_map(void)
 		cpu_core_map[cpu] = cpu_coregroup_map(cpu);
 }
 
-void arch_update_cpu_topology(void)
+int arch_update_cpu_topology(void)
 {
 	struct tl_info *info = tl_info;
 	struct sys_device *sysdev;
@@ -221,7 +221,7 @@ void arch_update_cpu_topology(void)
 	if (!machine_has_topology) {
 		update_cpu_core_map();
 		topology_update_polarization_simple();
-		return;
+		return 0;
 	}
 	stsi(info, 15, 1, 2);
 	tl_to_cores(info);
@@ -230,6 +230,7 @@ void arch_update_cpu_topology(void)
 		sysdev = get_cpu_sysdev(cpu);
 		kobject_uevent(&sysdev->kobj, KOBJ_CHANGE);
 	}
+	return 1;
 }
 
 static void topology_work_fn(struct work_struct *work)

arch/x86/Kconfig

@@ -368,10 +368,10 @@ config X86_RDC321X
 	  as R-8610-(G).
 	  If you don't have one of these chips, you should say N here.
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	def_bool y
 	prompt "Single-depth WCHAN output"
-	depends on X86_32
+	depends on X86
 	help
 	  Calculate simpler /proc/<PID>/wchan values. If this option
 	  is disabled then wchan values will recurse back to the

fs/proc/base.c

@@ -347,8 +347,8 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer)
 static int proc_pid_schedstat(struct task_struct *task, char *buffer)
 {
 	return sprintf(buffer, "%llu %llu %lu\n",
-			task->sched_info.cpu_time,
-			task->sched_info.run_delay,
+			(unsigned long long)task->se.sum_exec_runtime,
+			(unsigned long long)task->sched_info.run_delay,
 			task->sched_info.pcount);
 }
 #endif

include/asm-m32r/system.h

@@ -23,7 +23,7 @@
  */
 
 #if defined(CONFIG_FRAME_POINTER) || \
-	!defined(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER)
+	!defined(CONFIG_SCHED_OMIT_FRAME_POINTER)
 #define M32R_PUSH_FP "	push fp\n"
 #define M32R_POP_FP  "	pop  fp\n"
 #else

include/linux/sched.h

@@ -260,8 +260,6 @@ static inline int select_nohz_load_balancer(int cpu)
 }
 #endif
 
-extern unsigned long rt_needs_cpu(int cpu);
-
 /*
  * Only dump TASK_* tasks. (0 for all tasks)
  */
@@ -669,8 +667,7 @@ struct reclaim_state;
 struct sched_info {
 	/* cumulative counters */
 	unsigned long pcount;	      /* # of times run on this cpu */
-	unsigned long long cpu_time,  /* time spent on the cpu */
-			   run_delay; /* time spent waiting on a runqueue */
+	unsigned long long run_delay; /* time spent waiting on a runqueue */
 
 	/* timestamps */
 	unsigned long long last_arrival,/* when we last ran on a cpu */
@@ -2210,6 +2207,7 @@ extern void normalize_rt_tasks(void);
 extern struct task_group init_task_group;
 #ifdef CONFIG_USER_SCHED
 extern struct task_group root_task_group;
+extern void set_tg_uid(struct user_struct *user);
 #endif
 
 extern struct task_group *sched_create_group(struct task_group *parent);

include/linux/topology.h

@@ -49,7 +49,7 @@
 	for_each_online_node(node)			\
 		if (nr_cpus_node(node))
 
-void arch_update_cpu_topology(void);
+int arch_update_cpu_topology(void);
 
 /* Conform to ACPI 2.0 SLIT distance definitions */
 #define LOCAL_DISTANCE		10

kernel/Makefile

@@ -19,7 +19,6 @@ CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
-CFLAGS_REMOVE_sched.o = -pg
 endif
 
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -90,7 +89,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 
-ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
+ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
 # needed for x86 only.  Why this used to be enabled for all architectures is beyond
 # me.  I suspect most platforms don't need this, but until we know that for sure

kernel/delayacct.c

@@ -127,7 +127,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	 */
 	t1 = tsk->sched_info.pcount;
 	t2 = tsk->sched_info.run_delay;
-	t3 = tsk->sched_info.cpu_time;
+	t3 = tsk->se.sum_exec_runtime;
 
 	d->cpu_count += t1;
 

kernel/sched_debug.c

@@ -53,6 +53,40 @@ 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,
+		struct task_group *tg)
+{
+	struct sched_entity *se = tg->se[cpu];
+	if (!se)
+		return;
+
+#define P(F) \
+	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)F)
+#define PN(F) \
+	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
+
+	PN(se->exec_start);
+	PN(se->vruntime);
+	PN(se->sum_exec_runtime);
+#ifdef CONFIG_SCHEDSTATS
+	PN(se->wait_start);
+	PN(se->sleep_start);
+	PN(se->block_start);
+	PN(se->sleep_max);
+	PN(se->block_max);
+	PN(se->exec_max);
+	PN(se->slice_max);
+	PN(se->wait_max);
+	PN(se->wait_sum);
+	P(se->wait_count);
+#endif
+	P(se->load.weight);
+#undef PN
+#undef P
+}
+#endif
+
 static void
 print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 {
@@ -121,20 +155,19 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 
 #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
 	char path[128] = "";
-	struct cgroup *cgroup = NULL;
 	struct task_group *tg = cfs_rq->tg;
 
-	if (tg)
-		cgroup = tg->css.cgroup;
-
-	if (cgroup)
-		cgroup_path(cgroup, path, sizeof(path));
+	cgroup_path(tg->css.cgroup, path, sizeof(path));
 
 	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
+#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
+	{
+		uid_t uid = cfs_rq->tg->uid;
+		SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid);
+	}
 #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));
 
@@ -168,6 +201,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 #ifdef CONFIG_SMP
 	SEQ_printf(m, "  .%-30s: %lu\n", "shares", cfs_rq->shares);
 #endif
+	print_cfs_group_stats(m, cpu, cfs_rq->tg);
 #endif
 }
 
@@ -175,14 +209,9 @@ 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 cgroup *cgroup = NULL;
 	struct task_group *tg = rt_rq->tg;
 
-	if (tg)
-		cgroup = tg->css.cgroup;
-
-	if (cgroup)
-		cgroup_path(cgroup, path, sizeof(path));
+	cgroup_path(tg->css.cgroup, path, sizeof(path));
 
 	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
 #else
@@ -272,7 +301,7 @@ static int sched_debug_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Sched Debug Version: v0.07, %s %.*s\n",
+	SEQ_printf(m, "Sched Debug Version: v0.08, %s %.*s\n",
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);

kernel/sched_fair.c

@@ -492,6 +492,8 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	 * overflow on 32 bits):
 	 */
 	delta_exec = (unsigned long)(now - curr->exec_start);
+	if (!delta_exec)
+		return;
 
 	__update_curr(cfs_rq, curr, delta_exec);
 	curr->exec_start = now;
@@ -1345,12 +1347,11 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_entity *se = &curr->se, *pse = &p->se;
+	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 
-	if (unlikely(rt_prio(p->prio))) {
-		struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+	update_curr(cfs_rq);
 
-		update_rq_clock(rq);
-		update_curr(cfs_rq);
+	if (unlikely(rt_prio(p->prio))) {
 		resched_task(curr);
 		return;
 	}

kernel/sched_rt.c

@@ -77,7 +77,7 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 }
 
 #define for_each_leaf_rt_rq(rt_rq, rq) \
-	list_for_each_entry(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
+	list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
 
 static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
 {
@@ -537,13 +537,13 @@ static void update_curr_rt(struct rq *rq)
 	for_each_sched_rt_entity(rt_se) {
 		rt_rq = rt_rq_of_se(rt_se);
 
-		spin_lock(&rt_rq->rt_runtime_lock);
 		if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
+			spin_lock(&rt_rq->rt_runtime_lock);
 			rt_rq->rt_time += delta_exec;
 			if (sched_rt_runtime_exceeded(rt_rq))
 				resched_task(curr);
+			spin_unlock(&rt_rq->rt_runtime_lock);
 		}
-		spin_unlock(&rt_rq->rt_runtime_lock);
 	}
 }
 
@@ -909,9 +909,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 /* Only try algorithms three times */
 #define RT_MAX_TRIES 3
 
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
-static void double_unlock_balance(struct rq *this_rq, struct rq *busiest);
-
 static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)

kernel/sched_stats.h

@@ -31,7 +31,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 		    rq->yld_act_empty, rq->yld_exp_empty, rq->yld_count,
 		    rq->sched_switch, rq->sched_count, rq->sched_goidle,
 		    rq->ttwu_count, rq->ttwu_local,
-		    rq->rq_sched_info.cpu_time,
+		    rq->rq_cpu_time,
 		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
 
 		seq_printf(seq, "\n");
@@ -123,7 +123,7 @@ static inline void
 rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 {
 	if (rq)
-		rq->rq_sched_info.cpu_time += delta;
+		rq->rq_cpu_time += delta;
 }
 
 static inline void
@@ -236,7 +236,6 @@ static inline void sched_info_depart(struct task_struct *t)
 	unsigned long long delta = task_rq(t)->clock -
 					t->sched_info.last_arrival;
 
-	t->sched_info.cpu_time += delta;
 	rq_sched_info_depart(task_rq(t), delta);
 
 	if (t->state == TASK_RUNNING)

kernel/user.c

@@ -104,6 +104,8 @@ static int sched_create_user(struct user_struct *up)
 	if (IS_ERR(up->tg))
 		rc = -ENOMEM;
 
+	set_tg_uid(up);
+
 	return rc;
 }