Merge Linux 2.6.23

26 files changed, 464 insertions, 203 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 181ae708602..38033db8d8e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -273,7 +273,7 @@ int __cpuinit cpu_up(unsigned int cpu)
 	return err;
 }
 
-#ifdef CONFIG_SUSPEND_SMP
+#ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_t frozen_cpus;
 
 int disable_nonboot_cpus(void)
@@ -334,4 +334,4 @@ void enable_nonboot_cpus(void)
 out:
 	mutex_unlock(&cpu_add_remove_lock);
 }
-#endif
+#endif /* CONFIG_PM_SLEEP_SMP */
diff --git a/kernel/exit.c b/kernel/exit.c
index 9578c1ae19c..993369ee94d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -24,7 +24,6 @@
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/profile.h>
-#include <linux/signalfd.h>
 #include <linux/mount.h>
 #include <linux/proc_fs.h>
 #include <linux/kthread.h>
@@ -86,14 +85,6 @@ static void __exit_signal(struct task_struct *tsk)
 	sighand = rcu_dereference(tsk->sighand);
 	spin_lock(&sighand->siglock);
 
-	/*
-	 * Notify that this sighand has been detached. This must
-	 * be called with the tsk->sighand lock held. Also, this
-	 * access tsk->sighand internally, so it must be called
-	 * before tsk->sighand is reset.
-	 */
-	signalfd_detach_locked(tsk);
-
 	posix_cpu_timers_exit(tsk);
 	if (atomic_dec_and_test(&sig->count))
 		posix_cpu_timers_exit_group(tsk);
@@ -975,6 +966,7 @@ fastcall NORET_TYPE void do_exit(long code)
 	if (unlikely(tsk->audit_context))
 		audit_free(tsk);
 
+	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
 
 	exit_mm(tsk);
@@ -996,7 +988,6 @@ fastcall NORET_TYPE void do_exit(long code)
 	if (tsk->binfmt)
 		module_put(tsk->binfmt->module);
 
-	tsk->exit_code = code;
 	proc_exit_connector(tsk);
 	exit_task_namespaces(tsk);
 	exit_notify(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 7332e236d36..33f12f48684 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1438,7 +1438,7 @@ static void sighand_ctor(void *data, struct kmem_cache *cachep,
 	struct sighand_struct *sighand = data;
 
 	spin_lock_init(&sighand->siglock);
-	INIT_LIST_HEAD(&sighand->signalfd_list);
+	init_waitqueue_head(&sighand->signalfd_wqh);
 }
 
 void __init proc_caches_init(void)
diff --git a/kernel/futex.c b/kernel/futex.c
index e8935b195e8..fcc94e7b408 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1943,9 +1943,10 @@ static inline int fetch_robust_entry(struct robust_list __user **entry,
 void exit_robust_list(struct task_struct *curr)
 {
 	struct robust_list_head __user *head = curr->robust_list;
-	struct robust_list __user *entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
+	struct robust_list __user *entry, *next_entry, *pending;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
 	unsigned long futex_offset;
+	int rc;
 
 	/*
 	 * Fetch the list head (which was registered earlier, via
@@ -1965,12 +1966,14 @@ void exit_robust_list(struct task_struct *curr)
 	if (fetch_robust_entry(&pending, &head->list_op_pending, &pip))
 		return;
 
-	if (pending)
-		handle_futex_death((void __user *)pending + futex_offset,
-				   curr, pip);
-
+	next_entry = NULL;	/* avoid warning with gcc */
 	while (entry != &head->list) {
 		/*
+		 * Fetch the next entry in the list before calling
+		 * handle_futex_death:
+		 */
+		rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi);
+		/*
 		 * A pending lock might already be on the list, so
 		 * don't process it twice:
 		 */
@@ -1978,11 +1981,10 @@ void exit_robust_list(struct task_struct *curr)
 			if (handle_futex_death((void __user *)entry + futex_offset,
 						curr, pi))
 				return;
-		/*
-		 * Fetch the next entry in the list:
-		 */
-		if (fetch_robust_entry(&entry, &entry->next, &pi))
+		if (rc)
 			return;
+		entry = next_entry;
+		pi = next_pi;
 		/*
 		 * Avoid excessively long or circular lists:
 		 */
@@ -1991,6 +1993,10 @@ void exit_robust_list(struct task_struct *curr)
 
 		cond_resched();
 	}
+
+	if (pending)
+		handle_futex_death((void __user *)pending + futex_offset,
+				   curr, pip);
 }
 
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index f7921360efa..2c2e2954b71 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -38,10 +38,11 @@ fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
 void compat_exit_robust_list(struct task_struct *curr)
 {
 	struct compat_robust_list_head __user *head = curr->compat_robust_list;
-	struct robust_list __user *entry, *pending;
-	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
-	compat_uptr_t uentry, upending;
+	struct robust_list __user *entry, *next_entry, *pending;
+	unsigned int limit = ROBUST_LIST_LIMIT, pi, next_pi, pip;
+	compat_uptr_t uentry, next_uentry, upending;
 	compat_long_t futex_offset;
+	int rc;
 
 	/*
 	 * Fetch the list head (which was registered earlier, via
@@ -61,10 +62,15 @@ void compat_exit_robust_list(struct task_struct *curr)
 	if (fetch_robust_entry(&upending, &pending,
 			       &head->list_op_pending, &pip))
 		return;
-	if (upending)
-		handle_futex_death((void __user *)pending + futex_offset, curr, pip);
 
-	while (compat_ptr(uentry) != &head->list) {
+	next_entry = NULL;	/* avoid warning with gcc */
+	while (entry != (struct robust_list __user *) &head->list) {
+		/*
+		 * Fetch the next entry in the list before calling
+		 * handle_futex_death:
+		 */
+		rc = fetch_robust_entry(&next_uentry, &next_entry,
+			(compat_uptr_t __user *)&entry->next, &next_pi);
 		/*
 		 * A pending lock might already be on the list, so
 		 * dont process it twice:
@@ -74,12 +80,11 @@ void compat_exit_robust_list(struct task_struct *curr)
 						curr, pi))
 				return;
 
-		/*
-		 * Fetch the next entry in the list:
-		 */
-		if (fetch_robust_entry(&uentry, &entry,
-				       (compat_uptr_t __user *)&entry->next, &pi))
+		if (rc)
 			return;
+		uentry = next_uentry;
+		entry = next_entry;
+		pi = next_pi;
 		/*
 		 * Avoid excessively long or circular lists:
 		 */
@@ -88,6 +93,9 @@ void compat_exit_robust_list(struct task_struct *curr)
 
 		cond_resched();
 	}
+	if (pending)
+		handle_futex_death((void __user *)pending + futex_offset,
+				   curr, pip);
 }
 
 asmlinkage long
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 853aefbd184..7230d914eaa 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -547,14 +547,11 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 		 * We do this before actually registering it, to make sure that
 		 * a 'real' IRQ doesn't run in parallel with our fake
 		 */
-		if (irqflags & IRQF_DISABLED) {
-			unsigned long flags;
+		unsigned long flags;
 
-			local_irq_save(flags);
-			handler(irq, dev_id);
-			local_irq_restore(flags);
-		} else
-			handler(irq, dev_id);
+		local_irq_save(flags);
+		handler(irq, dev_id);
+		local_irq_restore(flags);
 	}
 #endif
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 9809cc1f33d..c6a4f8aebeb 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -505,7 +505,7 @@ int call_usermodehelper_pipe(char *path, char **argv, char **envp,
 	if (ret < 0)
 		goto out;
 
-	return call_usermodehelper_exec(sub_info, 1);
+	return call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
 
   out:
 	call_usermodehelper_freeinfo(sub_info);
diff --git a/kernel/module.c b/kernel/module.c
index 33c04ad5117..db0ead0363e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -784,8 +784,7 @@ EXPORT_SYMBOL_GPL(symbol_put_addr);
 static ssize_t show_refcnt(struct module_attribute *mattr,
 			   struct module *mod, char *buffer)
 {
-	/* sysfs holds a reference */
-	return sprintf(buffer, "%u\n", module_refcount(mod)-1);
+	return sprintf(buffer, "%u\n", module_refcount(mod));
 }
 
 static struct module_attribute refcnt = {
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 412859f8d94..14b0e10dc95 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -72,15 +72,10 @@ config PM_TRACE
 	CAUTION: this option will cause your machine's real-time clock to be
 	set to an invalid time after a resume.
 
-config SUSPEND_SMP_POSSIBLE
-	bool
-	depends on (X86 && !X86_VOYAGER) || (PPC64 && (PPC_PSERIES || PPC_PMAC))
-	depends on SMP
-	default y
-
-config SUSPEND_SMP
+config PM_SLEEP_SMP
 	bool
-	depends on SUSPEND_SMP_POSSIBLE && PM_SLEEP
+	depends on SUSPEND_SMP_POSSIBLE || HIBERNATION_SMP_POSSIBLE
+	depends on PM_SLEEP
 	select HOTPLUG_CPU
 	default y
 
@@ -89,20 +84,46 @@ config PM_SLEEP
 	depends on SUSPEND || HIBERNATION
 	default y
 
+config SUSPEND_UP_POSSIBLE
+	bool
+	depends on (X86 && !X86_VOYAGER) || PPC || ARM || BLACKFIN || MIPS \
+		   || SUPERH || FRV
+	depends on !SMP
+	default y
+
+config SUSPEND_SMP_POSSIBLE
+	bool
+	depends on (X86 && !X86_VOYAGER) \
+		   || (PPC && (PPC_PSERIES || PPC_PMAC)) || ARM
+	depends on SMP
+	default y
+
 config SUSPEND
 	bool "Suspend to RAM and standby"
 	depends on PM
-	depends on !SMP || SUSPEND_SMP_POSSIBLE
+	depends on SUSPEND_UP_POSSIBLE || SUSPEND_SMP_POSSIBLE
 	default y
 	---help---
 	  Allow the system to enter sleep states in which main memory is
 	  powered and thus its contents are preserved, such as the
 	  suspend-to-RAM state (i.e. the ACPI S3 state).
 
+config HIBERNATION_UP_POSSIBLE
+	bool
+	depends on X86 || PPC64_SWSUSP || PPC32
+	depends on !SMP
+	default y
+
+config HIBERNATION_SMP_POSSIBLE
+	bool
+	depends on (X86 && !X86_VOYAGER) || PPC64_SWSUSP
+	depends on SMP
+	default y
+
 config HIBERNATION
 	bool "Hibernation (aka 'suspend to disk')"
 	depends on PM && SWAP
-	depends on ((X86 || PPC64_SWSUSP || FRV || PPC32) && !SMP) || SUSPEND_SMP_POSSIBLE
+	depends on HIBERNATION_UP_POSSIBLE || HIBERNATION_SMP_POSSIBLE
 	---help---
 	  Enable the suspend to disk (STD) functionality, which is usually
 	  called "hibernation" in user interfaces.  STD checkpoints the
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 82a558b655d..3eca7a55f2e 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -233,6 +233,7 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
 
 	/* Architecture-specific hardware disable .. */
 	ptrace_disable(child);
+	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
 
 	write_lock_irq(&tasklist_lock);
 	/* protect against de_thread()->release_task() */
diff --git a/kernel/sched.c b/kernel/sched.c
index 45e17b83b7f..6107a0cd632 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -262,7 +262,8 @@ struct rq {
 	s64 clock_max_delta;
 
 	unsigned int clock_warps, clock_overflows;
-	unsigned int clock_unstable_events;
+	u64 idle_clock;
+	unsigned int clock_deep_idle_events;
 	u64 tick_timestamp;
 
 	atomic_t nr_iowait;
@@ -556,18 +557,40 @@ static inline struct rq *this_rq_lock(void)
 }
 
 /*
- * CPU frequency is/was unstable - start new by setting prev_clock_raw:
+ * We are going deep-idle (irqs are disabled):
  */
-void sched_clock_unstable_event(void)
+void sched_clock_idle_sleep_event(void)
 {
-	unsigned long flags;
-	struct rq *rq;
+	struct rq *rq = cpu_rq(smp_processor_id());
 
-	rq = task_rq_lock(current, &flags);
-	rq->prev_clock_raw = sched_clock();
-	rq->clock_unstable_events++;
-	task_rq_unlock(rq, &flags);
+	spin_lock(&rq->lock);
+	__update_rq_clock(rq);
+	spin_unlock(&rq->lock);
+	rq->clock_deep_idle_events++;
+}
+EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
+
+/*
+ * We just idled delta nanoseconds (called with irqs disabled):
+ */
+void sched_clock_idle_wakeup_event(u64 delta_ns)
+{
+	struct rq *rq = cpu_rq(smp_processor_id());
+	u64 now = sched_clock();
+
+	rq->idle_clock += delta_ns;
+	/*
+	 * Override the previous timestamp and ignore all
+	 * sched_clock() deltas that occured while we idled,
+	 * and use the PM-provided delta_ns to advance the
+	 * rq clock:
+	 */
+	spin_lock(&rq->lock);
+	rq->prev_clock_raw = now;
+	rq->clock += delta_ns;
+	spin_unlock(&rq->lock);
 }
+EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
 /*
  * resched_task - mark a task 'to be rescheduled now'.
@@ -645,7 +668,7 @@ static u64 div64_likely32(u64 divident, unsigned long divisor)
 /*
  * Shift right and round:
  */
-#define RSR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
+#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))
 
 static unsigned long
 calc_delta_mine(unsigned long delta_exec, unsigned long weight,
@@ -661,10 +684,10 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 	 * Check whether we'd overflow the 64-bit multiplication:
 	 */
 	if (unlikely(tmp > WMULT_CONST))
-		tmp = RSR(RSR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
+		tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
 			WMULT_SHIFT/2);
 	else
-		tmp = RSR(tmp * lw->inv_weight, WMULT_SHIFT);
+		tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);
 
 	return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
 }
@@ -835,7 +858,6 @@ static void dec_nr_running(struct task_struct *p, struct rq *rq)
 
 static void set_load_weight(struct task_struct *p)
 {
-	task_rq(p)->cfs.wait_runtime -= p->se.wait_runtime;
 	p->se.wait_runtime = 0;
 
 	if (task_has_rt_policy(p)) {
@@ -1564,6 +1586,7 @@ static void __sched_fork(struct task_struct *p)
 	p->se.wait_start_fair		= 0;
 	p->se.exec_start		= 0;
 	p->se.sum_exec_runtime		= 0;
+	p->se.prev_sum_exec_runtime	= 0;
 	p->se.delta_exec		= 0;
 	p->se.delta_fair_run		= 0;
 	p->se.delta_fair_sleep		= 0;
@@ -1659,6 +1682,11 @@ void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 
 	p->prio = effective_prio(p);
 
+	if (rt_prio(p->prio))
+		p->sched_class = &rt_sched_class;
+	else
+		p->sched_class = &fair_sched_class;
+
 	if (!p->sched_class->task_new || !sysctl_sched_child_runs_first ||
 			(clone_flags & CLONE_VM) || task_cpu(p) != this_cpu ||
 			!current->se.on_rq) {
@@ -2157,12 +2185,6 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	if (task_running(rq, p))
 		return 0;
 
-	/*
-	 * Aggressive migration if too many balance attempts have failed:
-	 */
-	if (sd->nr_balance_failed > sd->cache_nice_tries)
-		return 1;
-
 	return 1;
 }
 
@@ -2494,7 +2516,7 @@ group_next:
 	 * a think about bumping its value to force at least one task to be
 	 * moved
 	 */
-	if (*imbalance + SCHED_LOAD_SCALE_FUZZ < busiest_load_per_task/2) {
+	if (*imbalance < busiest_load_per_task) {
 		unsigned long tmp, pwr_now, pwr_move;
 		unsigned int imbn;
 
@@ -2546,10 +2568,8 @@ small_imbalance:
 		pwr_move /= SCHED_LOAD_SCALE;
 
 		/* Move if we gain throughput */
-		if (pwr_move <= pwr_now)
-			goto out_balanced;
-
-		*imbalance = busiest_load_per_task;
+		if (pwr_move > pwr_now)
+			*imbalance = busiest_load_per_task;
 	}
 
 	return busiest;
@@ -3020,6 +3040,7 @@ static inline void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	struct sched_domain *sd;
 	/* Earliest time when we have to do rebalance again */
 	unsigned long next_balance = jiffies + 60*HZ;
+	int update_next_balance = 0;
 
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
@@ -3056,8 +3077,10 @@ static inline void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		if (sd->flags & SD_SERIALIZE)
 			spin_unlock(&balancing);
 out:
-		if (time_after(next_balance, sd->last_balance + interval))
+		if (time_after(next_balance, sd->last_balance + interval)) {
 			next_balance = sd->last_balance + interval;
+			update_next_balance = 1;
+		}
 
 		/*
 		 * Stop the load balance at this level. There is another
@@ -3067,7 +3090,14 @@ out:
 		if (!balance)
 			break;
 	}
-	rq->next_balance = next_balance;
+
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the cpu is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		rq->next_balance = next_balance;
 }
 
 /*
@@ -4525,10 +4555,7 @@ asmlinkage long sys_sched_yield(void)
 	struct rq *rq = this_rq_lock();
 
 	schedstat_inc(rq, yld_cnt);
-	if (unlikely(rq->nr_running == 1))
-		schedstat_inc(rq, yld_act_empty);
-	else
-		current->sched_class->yield_task(rq, current);
+	current->sched_class->yield_task(rq, current);
 
 	/*
 	 * Since we are going to call schedule() anyway, there's
@@ -4884,14 +4911,18 @@ cpumask_t nohz_cpu_mask = CPU_MASK_NONE;
 static inline void sched_init_granularity(void)
 {
 	unsigned int factor = 1 + ilog2(num_online_cpus());
-	const unsigned long gran_limit = 100000000;
+	const unsigned long limit = 100000000;
+
+	sysctl_sched_min_granularity *= factor;
+	if (sysctl_sched_min_granularity > limit)
+		sysctl_sched_min_granularity = limit;
 
-	sysctl_sched_granularity *= factor;
-	if (sysctl_sched_granularity > gran_limit)
-		sysctl_sched_granularity = gran_limit;
+	sysctl_sched_latency *= factor;
+	if (sysctl_sched_latency > limit)
+		sysctl_sched_latency = limit;
 
-	sysctl_sched_runtime_limit = sysctl_sched_granularity * 4;
-	sysctl_sched_wakeup_granularity = sysctl_sched_granularity / 2;
+	sysctl_sched_runtime_limit = sysctl_sched_latency;
+	sysctl_sched_wakeup_granularity = sysctl_sched_min_granularity / 2;
 }
 
 #ifdef CONFIG_SMP
@@ -5234,15 +5265,16 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 static struct ctl_table sd_ctl_dir[] = {
 	{
 		.procname	= "sched_domain",
-		.mode		= 0755,
+		.mode		= 0555,
 	},
 	{0,},
 };
 
 static struct ctl_table sd_ctl_root[] = {
 	{
+		.ctl_name	= CTL_KERN,
 		.procname	= "kernel",
-		.mode		= 0755,
+		.mode		= 0555,
 		.child		= sd_ctl_dir,
 	},
 	{0,},
@@ -5318,7 +5350,7 @@ static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
 	for_each_domain(cpu, sd) {
 		snprintf(buf, 32, "domain%d", i);
 		entry->procname = kstrdup(buf, GFP_KERNEL);
-		entry->mode = 0755;
+		entry->mode = 0555;
 		entry->child = sd_alloc_ctl_domain_table(sd);
 		entry++;
 		i++;
@@ -5338,7 +5370,7 @@ static void init_sched_domain_sysctl(void)
 	for (i = 0; i < cpu_num; i++, entry++) {
 		snprintf(buf, 32, "cpu%d", i);
 		entry->procname = kstrdup(buf, GFP_KERNEL);
-		entry->mode = 0755;
+		entry->mode = 0555;
 		entry->child = sd_alloc_ctl_cpu_table(i);
 	}
 	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 87e524762b8..c3ee38bd342 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -154,10 +154,11 @@ static void print_cpu(struct seq_file *m, int cpu)
 	P(next_balance);
 	P(curr->pid);
 	P(clock);
+	P(idle_clock);
 	P(prev_clock_raw);
 	P(clock_warps);
 	P(clock_overflows);
-	P(clock_unstable_events);
+	P(clock_deep_idle_events);
 	P(clock_max_delta);
 	P(cpu_load[0]);
 	P(cpu_load[1]);
@@ -282,4 +283,5 @@ void proc_sched_set_task(struct task_struct *p)
 	p->se.wait_runtime_overruns = p->se.wait_runtime_underruns = 0;
 #endif
 	p->se.sum_exec_runtime = 0;
+	p->se.prev_sum_exec_runtime	= 0;
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index fedbb51bba9..67c67a87146 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -15,34 +15,50 @@
  *
  *  Scaled math optimizations by Thomas Gleixner
  *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
+ *
+ *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
  */
 
 /*
- * Preemption granularity:
- * (default: 2 msec, units: nanoseconds)
+ * Targeted preemption latency for CPU-bound tasks:
+ * (default: 20ms, units: nanoseconds)
  *
- * NOTE: this granularity value is not the same as the concept of
- * 'timeslice length' - timeslices in CFS will typically be somewhat
- * larger than this value. (to see the precise effective timeslice
- * length of your workload, run vmstat and monitor the context-switches
- * field)
+ * NOTE: this latency value is not the same as the concept of
+ * 'timeslice length' - timeslices in CFS are of variable length.
+ * (to see the precise effective timeslice length of your workload,
+ *  run vmstat and monitor the context-switches field)
  *
  * On SMP systems the value of this is multiplied by the log2 of the
  * number of CPUs. (i.e. factor 2x on 2-way systems, 3x on 4-way
  * systems, 4x on 8-way systems, 5x on 16-way systems, etc.)
+ * Targeted preemption latency for CPU-bound tasks:
+ */
+unsigned int sysctl_sched_latency __read_mostly = 20000000ULL;
+
+/*
+ * Minimal preemption granularity for CPU-bound tasks:
+ * (default: 2 msec, units: nanoseconds)
  */
-unsigned int sysctl_sched_granularity __read_mostly = 2000000000ULL/HZ;
+unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;
+
+/*
+ * sys_sched_yield() compat mode
+ *
+ * This option switches the agressive yield implementation of the
+ * old scheduler back on.
+ */
+unsigned int __read_mostly sysctl_sched_compat_yield;
 
 /*
  * SCHED_BATCH wake-up granularity.
- * (default: 10 msec, units: nanoseconds)
+ * (default: 25 msec, units: nanoseconds)
  *
  * This option delays the preemption effects of decoupled workloads
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-unsigned int sysctl_sched_batch_wakeup_granularity __read_mostly =
-							10000000000ULL/HZ;
+unsigned int sysctl_sched_batch_wakeup_granularity __read_mostly = 25000000UL;
 
 /*
  * SCHED_OTHER wake-up granularity.
@@ -52,12 +68,12 @@ unsigned int sysctl_sched_batch_wakeup_granularity __read_mostly =
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-unsigned int sysctl_sched_wakeup_granularity __read_mostly = 1000000000ULL/HZ;
+unsigned int sysctl_sched_wakeup_granularity __read_mostly = 1000000UL;
 
 unsigned int sysctl_sched_stat_granularity __read_mostly;
 
 /*
- * Initialized in sched_init_granularity():
+ * Initialized in sched_init_granularity() [to 5 times the base granularity]:
  */
 unsigned int sysctl_sched_runtime_limit __read_mostly;
 
@@ -186,6 +202,8 @@ __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	update_load_add(&cfs_rq->load, se->load.weight);
 	cfs_rq->nr_running++;
 	se->on_rq = 1;
+
+	schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
 }
 
 static inline void
@@ -197,6 +215,8 @@ __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	update_load_sub(&cfs_rq->load, se->load.weight);
 	cfs_rq->nr_running--;
 	se->on_rq = 0;
+
+	schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
 }
 
 static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
@@ -214,6 +234,49 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
  */
 
 /*
+ * Calculate the preemption granularity needed to schedule every
+ * runnable task once per sysctl_sched_latency amount of time.
+ * (down to a sensible low limit on granularity)
+ *
+ * For example, if there are 2 tasks running and latency is 10 msecs,
+ * we switch tasks every 5 msecs. If we have 3 tasks running, we have
+ * to switch tasks every 3.33 msecs to get a 10 msecs observed latency
+ * for each task. We do finer and finer scheduling up to until we
+ * reach the minimum granularity value.
+ *
+ * To achieve this we use the following dynamic-granularity rule:
+ *
+ *    gran = lat/nr - lat/nr/nr
+ *
+ * This comes out of the following equations:
+ *
+ *    kA1 + gran = kB1
+ *    kB2 + gran = kA2
+ *    kA2 = kA1
+ *    kB2 = kB1 - d + d/nr
+ *    lat = d * nr
+ *
+ * Where 'k' is key, 'A' is task A (waiting), 'B' is task B (running),
+ * '1' is start of time, '2' is end of time, 'd' is delay between
+ * 1 and 2 (during which task B was running), 'nr' is number of tasks
+ * running, 'lat' is the the period of each task. ('lat' is the
+ * sched_latency that we aim for.)
+ */
+static long
+sched_granularity(struct cfs_rq *cfs_rq)
+{
+	unsigned int gran = sysctl_sched_latency;
+	unsigned int nr = cfs_rq->nr_running;
+
+	if (nr > 1) {
+		gran = gran/nr - gran/nr/nr;
+		gran = max(gran, sysctl_sched_min_granularity);
+	}
+
+	return gran;
+}
+
+/*
  * We rescale the rescheduling granularity of tasks according to their
  * nice level, but only linearly, not exponentially:
  */
@@ -240,7 +303,7 @@ niced_granularity(struct sched_entity *curr, unsigned long granularity)
 	/*
 	 * It will always fit into 'long':
 	 */
-	return (long) (tmp >> WMULT_SHIFT);
+	return (long) (tmp >> (WMULT_SHIFT-NICE_0_SHIFT));
 }
 
 static inline void
@@ -303,10 +366,10 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 	delta_fair = calc_delta_fair(delta_exec, lw);
 	delta_mine = calc_delta_mine(delta_exec, curr->load.weight, lw);
 
-	if (cfs_rq->sleeper_bonus > sysctl_sched_granularity) {
-		delta = min(cfs_rq->sleeper_bonus, (u64)delta_exec);
-		delta = calc_delta_mine(delta, curr->load.weight, lw);
-		delta = min((u64)delta, cfs_rq->sleeper_bonus);
+	if (cfs_rq->sleeper_bonus > sysctl_sched_min_granularity) {
+		delta = min((u64)delta_mine, cfs_rq->sleeper_bonus);
+		delta = min(delta, (unsigned long)(
+			(long)sysctl_sched_runtime_limit - curr->wait_runtime));
 		cfs_rq->sleeper_bonus -= delta;
 		delta_mine -= delta;
 	}
@@ -438,6 +501,9 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	unsigned long delta_fair;
 
+	if (unlikely(!se->wait_start_fair))
+		return;
+
 	delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
 			(u64)(cfs_rq->fair_clock - se->wait_start_fair));
 
@@ -494,6 +560,13 @@ static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	unsigned long load = cfs_rq->load.weight, delta_fair;
 	long prev_runtime;
 
+	/*
+	 * Do not boost sleepers if there's too much bonus 'in flight'
+	 * already:
+	 */
+	if (unlikely(cfs_rq->sleeper_bonus > sysctl_sched_runtime_limit))
+		return;
+
 	if (sysctl_sched_features & SCHED_FEAT_SLEEPER_LOAD_AVG)
 		load = rq_of(cfs_rq)->cpu_load[2];
 
@@ -519,10 +592,6 @@ static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * Track the amount of bonus we've given to sleepers:
 	 */
 	cfs_rq->sleeper_bonus += delta_fair;
-	if (unlikely(cfs_rq->sleeper_bonus > sysctl_sched_runtime_limit))
-		cfs_rq->sleeper_bonus = sysctl_sched_runtime_limit;
-
-	schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
 }
 
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -570,6 +639,16 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 		se->block_start = 0;
 		se->sum_sleep_runtime += delta;
+
+		/*
+		 * Blocking time is in units of nanosecs, so shift by 20 to
+		 * get a milliseconds-range estimation of the amount of
+		 * time that the task spent sleeping:
+		 */
+		if (unlikely(prof_on == SLEEP_PROFILING)) {
+			profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
+				     delta >> 20);
+		}
 	}
 #endif
 }
@@ -604,7 +683,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 			if (tsk->state & TASK_UNINTERRUPTIBLE)
 				se->block_start = rq_of(cfs_rq)->clock;
 		}
-		cfs_rq->wait_runtime -= se->wait_runtime;
 #endif
 	}
 	__dequeue_entity(cfs_rq, se);
@@ -618,11 +696,31 @@ __check_preempt_curr_fair(struct cfs_rq *cfs_rq, struct sched_entity *se,
 			  struct sched_entity *curr, unsigned long granularity)
 {
 	s64 __delta = curr->fair_key - se->fair_key;
+	unsigned long ideal_runtime, delta_exec;
+
+	/*
+	 * ideal_runtime is compared against sum_exec_runtime, which is
+	 * walltime, hence do not scale.
+	 */
+	ideal_runtime = max(sysctl_sched_latency / cfs_rq->nr_running,
+			(unsigned long)sysctl_sched_min_granularity);
+
+	/*
+	 * If we executed more than what the latency constraint suggests,
+	 * reduce the rescheduling granularity. This way the total latency
+	 * of how much a task is not scheduled converges to
+	 * sysctl_sched_latency:
+	 */
+	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
+	if (delta_exec > ideal_runtime)
+		granularity = 0;
 
 	/*
 	 * Take scheduling granularity into account - do not
 	 * preempt the current task unless the best task has
 	 * a larger than sched_granularity fairness advantage:
+	 *
+	 * scale granularity as key space is in fair_clock.
 	 */
 	if (__delta > niced_granularity(curr, granularity))
 		resched_task(rq_of(cfs_rq)->curr);
@@ -641,6 +739,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	update_stats_wait_end(cfs_rq, se);
 	update_stats_curr_start(cfs_rq, se);
 	set_cfs_rq_curr(cfs_rq, se);
+	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
@@ -686,7 +785,8 @@ static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 	if (next == curr)
 		return;
 
-	__check_preempt_curr_fair(cfs_rq, next, curr, sysctl_sched_granularity);
+	__check_preempt_curr_fair(cfs_rq, next, curr,
+			sched_granularity(cfs_rq));
 }
 
 /**************************************************
@@ -815,19 +915,62 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 }
 
 /*
- * sched_yield() support is very simple - we dequeue and enqueue
+ * sched_yield() support is very simple - we dequeue and enqueue.
+ *
+ * If compat_yield is turned on then we requeue to the end of the tree.
  */
 static void yield_task_fair(struct rq *rq, struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
+	struct sched_entity *rightmost, *se = &p->se;
+	struct rb_node *parent;
 
-	__update_rq_clock(rq);
 	/*
-	 * Dequeue and enqueue the task to update its
-	 * position within the tree:
+	 * Are we the only task in the tree?
+	 */
+	if (unlikely(cfs_rq->nr_running == 1))
+		return;
+
+	if (likely(!sysctl_sched_compat_yield)) {
+		__update_rq_clock(rq);
+		/*
+		 * Dequeue and enqueue the task to update its
+		 * position within the tree:
+		 */
+		dequeue_entity(cfs_rq, &p->se, 0);
+		enqueue_entity(cfs_rq, &p->se, 0);
+
+		return;
+	}
+	/*
+	 * Find the rightmost entry in the rbtree:
+	 */
+	do {
+		parent = *link;
+		link = &parent->rb_right;
+	} while (*link);
+
+	rightmost = rb_entry(parent, struct sched_entity, run_node);
+	/*
+	 * Already in the rightmost position?
+	 */
+	if (unlikely(rightmost == se))
+		return;
+
+	/*
+	 * Minimally necessary key value to be last in the tree:
 	 */
-	dequeue_entity(cfs_rq, &p->se, 0);
-	enqueue_entity(cfs_rq, &p->se, 0);
+	se->fair_key = rightmost->fair_key + 1;
+
+	if (cfs_rq->rb_leftmost == &se->run_node)
+		cfs_rq->rb_leftmost = rb_next(&se->run_node);
+	/*
+	 * Relink the task to the rightmost position:
+	 */
+	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
+	rb_link_node(&se->run_node, parent, link);
+	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
 /*
@@ -1020,31 +1163,32 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr)
 static void task_new_fair(struct rq *rq, struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
-	struct sched_entity *se = &p->se;
+	struct sched_entity *se = &p->se, *curr = cfs_rq_curr(cfs_rq);
 
 	sched_info_queued(p);
 
+	update_curr(cfs_rq);
 	update_stats_enqueue(cfs_rq, se);
 	/*
 	 * Child runs first: we let it run before the parent
 	 * until it reschedules once. We set up the key so that
 	 * it will preempt the parent:
 	 */
-	p->se.fair_key = current->se.fair_key -
-		niced_granularity(&rq->curr->se, sysctl_sched_granularity) - 1;
+	se->fair_key = curr->fair_key -
+		niced_granularity(curr, sched_granularity(cfs_rq)) - 1;
 	/*
 	 * The first wait is dominated by the child-runs-first logic,
 	 * so do not credit it with that waiting time yet:
 	 */
 	if (sysctl_sched_features & SCHED_FEAT_SKIP_INITIAL)
-		p->se.wait_start_fair = 0;
+		se->wait_start_fair = 0;
 
 	/*
 	 * The statistical average of wait_runtime is about
 	 * -granularity/2, so initialize the task with that:
 	 */
 	if (sysctl_sched_features & SCHED_FEAT_START_DEBIT)
-		p->se.wait_runtime = -(sysctl_sched_granularity / 2);
+		se->wait_runtime = -(sched_granularity(cfs_rq) / 2);
 
 	__enqueue_entity(cfs_rq, se);
 }
@@ -1057,7 +1201,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
  */
 static void set_curr_task_fair(struct rq *rq)
 {
-	struct sched_entity *se = &rq->curr.se;
+	struct sched_entity *se = &rq->curr->se;
 
 	for_each_sched_entity(se)
 		set_next_entity(cfs_rq_of(se), se);
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index dcdcad632fd..4b87476a02d 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -207,10 +207,15 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p)
 		return;
 
 	p->time_slice = static_prio_timeslice(p->static_prio);
-	set_tsk_need_resched(p);
 
-	/* put it at the end of the queue: */
-	requeue_task_rt(rq, p);
+	/*
+	 * Requeue to the end of queue if we are not the only element
+	 * on the queue:
+	 */
+	if (p->run_list.prev != p->run_list.next) {
+		requeue_task_rt(rq, p);
+		set_tsk_need_resched(p);
+	}
 }
 
 static struct sched_class rt_sched_class __read_mostly = {
diff --git a/kernel/signal.c b/kernel/signal.c
index ad63109e413..79295238109 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -378,8 +378,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 	/* We only dequeue private signals from ourselves, we don't let
 	 * signalfd steal them
 	 */
-	if (likely(tsk == current))
-		signr = __dequeue_signal(&tsk->pending, mask, info);
+	signr = __dequeue_signal(&tsk->pending, mask, info);
 	if (!signr) {
 		signr = __dequeue_signal(&tsk->signal->shared_pending,
 					 mask, info);
@@ -407,8 +406,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 			}
 		}
 	}
-	if (likely(tsk == current))
-		recalc_sigpending();
+	recalc_sigpending();
 	if (signr && unlikely(sig_kernel_stop(signr))) {
 		/*
 		 * Set a marker that we have dequeued a stop signal.  Our
@@ -425,7 +423,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
 		if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
 			tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
 	}
-	if (signr && likely(tsk == current) &&
+	if (signr &&
 	     ((info->si_code & __SI_MASK) == __SI_TIMER) &&
 	     info->si_sys_private){
 		/*
@@ -533,18 +531,18 @@ static int check_kill_permission(int sig, struct siginfo *info,
 	if (!valid_signal(sig))
 		return error;
 
-	error = audit_signal_info(sig, t); /* Let audit system see the signal */
-	if (error)
-		return error;
-
-	error = -EPERM;
-	if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)))
-	    && ((sig != SIGCONT) ||
-		(process_session(current) != process_session(t)))
-	    && (current->euid ^ t->suid) && (current->euid ^ t->uid)
-	    && (current->uid ^ t->suid) && (current->uid ^ t->uid)
-	    && !capable(CAP_KILL))
+	if (info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info))) {
+		error = audit_signal_info(sig, t); /* Let audit system see the signal */
+		if (error)
+			return error;
+		error = -EPERM;
+		if (((sig != SIGCONT) ||
+			(process_session(current) != process_session(t)))
+		    && (current->euid ^ t->suid) && (current->euid ^ t->uid)
+		    && (current->uid ^ t->suid) && (current->uid ^ t->uid)
+		    && !capable(CAP_KILL))
 		return error;
+	}
 
 	return security_task_kill(t, info, sig, 0);
 }
@@ -1300,20 +1298,19 @@ struct sigqueue *sigqueue_alloc(void)
 void sigqueue_free(struct sigqueue *q)
 {
 	unsigned long flags;
+	spinlock_t *lock = &current->sighand->siglock;
+
 	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
 	/*
 	 * If the signal is still pending remove it from the
-	 * pending queue.
+	 * pending queue. We must hold ->siglock while testing
+	 * q->list to serialize with collect_signal().
 	 */
-	if (unlikely(!list_empty(&q->list))) {
-		spinlock_t *lock = &current->sighand->siglock;
-		read_lock(&tasklist_lock);
-		spin_lock_irqsave(lock, flags);
-		if (!list_empty(&q->list))
-			list_del_init(&q->list);
-		spin_unlock_irqrestore(lock, flags);
-		read_unlock(&tasklist_lock);
-	}
+	spin_lock_irqsave(lock, flags);
+	if (!list_empty(&q->list))
+		list_del_init(&q->list);
+	spin_unlock_irqrestore(lock, flags);
+
 	q->flags &= ~SIGQUEUE_PREALLOC;
 	__sigqueue_free(q);
 }
diff --git a/kernel/sys.c b/kernel/sys.c
index 449b81b98b3..8ae2e636eb1 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -32,6 +32,7 @@
 #include <linux/getcpu.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/seccomp.h>
+#include <linux/cpu.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -878,6 +879,7 @@ void kernel_power_off(void)
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
+	disable_nonboot_cpus();
 	sysdev_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	machine_power_off();
@@ -1442,7 +1444,6 @@ asmlinkage long sys_times(struct tms __user * tbuf)
  * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
  * LBT 04.03.94
  */
-
 asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
 {
 	struct task_struct *p;
@@ -1470,7 +1471,7 @@ asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
 	if (!thread_group_leader(p))
 		goto out;
 
-	if (p->real_parent == group_leader) {
+	if (p->real_parent->tgid == group_leader->tgid) {
 		err = -EPERM;
 		if (task_session(p) != task_session(group_leader))
 			goto out;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9029690f4fa..53a456ebf6d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -222,8 +222,19 @@ static ctl_table kern_table[] = {
 #ifdef CONFIG_SCHED_DEBUG
 	{
 		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "sched_granularity_ns",
-		.data		= &sysctl_sched_granularity,
+		.procname	= "sched_min_granularity_ns",
+		.data		= &sysctl_sched_min_granularity,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &min_sched_granularity_ns,
+		.extra2		= &max_sched_granularity_ns,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_latency_ns",
+		.data		= &sysctl_sched_latency,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec_minmax,
@@ -283,6 +294,23 @@ static ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_features",
+		.data		= &sysctl_sched_features,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_compat_yield",
+		.data		= &sysctl_sched_compat_yield,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.ctl_name	= CTL_UNNUMBERED,
@@ -304,15 +332,6 @@ static ctl_table kern_table[] = {
 	},
 #endif
 	{
-		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "sched_features",
-		.data		= &sysctl_sched_features,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-#endif
-	{
 		.ctl_name	= KERN_PANIC,
 		.procname	= "panic",
 		.data		= &panic_timeout,
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index cd91237dbfe..de6a2d6b3eb 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -226,7 +226,7 @@ static void sync_cmos_clock(unsigned long dummy)
 
 static void notify_cmos_timer(void)
 {
-	if (no_sync_cmos_clock)
+	if (!no_sync_cmos_clock)
 		mod_timer(&sync_cmos_timer, jiffies + 1);
 }
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index db8e0f3d409..0962e057766 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -383,11 +383,7 @@ static int tick_broadcast_set_event(ktime_t expires, int force)
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
 	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-
-	if(!cpus_empty(tick_broadcast_oneshot_mask))
-		tick_broadcast_set_event(ktime_get(), 1);
-
-	return cpu_isset(smp_processor_id(), tick_broadcast_oneshot_mask);
+	return 0;
 }
 
 /*
@@ -549,20 +545,17 @@ void tick_broadcast_switch_to_oneshot(void)
  */
 void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 {
-	struct clock_event_device *bc;
 	unsigned long flags;
 	unsigned int cpu = *cpup;
 
 	spin_lock_irqsave(&tick_broadcast_lock, flags);
 
-	bc = tick_broadcast_device.evtdev;
+	/*
+	 * Clear the broadcast mask flag for the dead cpu, but do not
+	 * stop the broadcast device!
+	 */
 	cpu_clear(cpu, tick_broadcast_oneshot_mask);
 
-	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) {
-		if (bc && cpus_empty(tick_broadcast_oneshot_mask))
-			clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
-	}
-
 	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b416995b975..8c3fef1db09 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -160,6 +160,18 @@ void tick_nohz_stop_sched_tick(void)
 	cpu = smp_processor_id();
 	ts = &per_cpu(tick_cpu_sched, cpu);
 
+	/*
+	 * If this cpu is offline and it is the one which updates
+	 * jiffies, then give up the assignment and let it be taken by
+	 * the cpu which runs the tick timer next. If we don't drop
+	 * this here the jiffies might be stale and do_timer() never
+	 * invoked.
+	 */
+	if (unlikely(!cpu_online(cpu))) {
+		if (cpu == tick_do_timer_cpu)
+			tick_do_timer_cpu = -1;
+	}
+
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
 		goto end;
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index acc417b5a9b..4ad79f6bdec 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -217,6 +217,7 @@ static void change_clocksource(void)
 }
 #else
 static inline void change_clocksource(void) { }
+static inline s64 __get_nsec_offset(void) { return 0; }
 #endif
 
 /**
@@ -280,6 +281,8 @@ void __init timekeeping_init(void)
 static int timekeeping_suspended;
 /* time in seconds when suspend began */
 static unsigned long timekeeping_suspend_time;
+/* xtime offset when we went into suspend */
+static s64 timekeeping_suspend_nsecs;
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
@@ -305,6 +308,8 @@ static int timekeeping_resume(struct sys_device *dev)
 		wall_to_monotonic.tv_sec -= sleep_length;
 		total_sleep_time += sleep_length;
 	}
+	/* Make sure that we have the correct xtime reference */
+	timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
 	/* re-base the last cycle value */
 	clock->cycle_last = clocksource_read(clock);
 	clock->error = 0;
@@ -325,9 +330,12 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
 {
 	unsigned long flags;
 
+	timekeeping_suspend_time = read_persistent_clock();
+
 	write_seqlock_irqsave(&xtime_lock, flags);
+	/* Get the current xtime offset */
+	timekeeping_suspend_nsecs = __get_nsec_offset();
 	timekeeping_suspended = 1;
-	timekeeping_suspend_time = read_persistent_clock();
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
 	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index 3c38fb5eae1..c36bb7ed030 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -327,8 +327,9 @@ static int tstats_show(struct seq_file *m, void *v)
 		ms = 1;
 
 	if (events && period.tv_sec)
-		seq_printf(m, "%ld total events, %ld.%ld events/sec\n", events,
-			   events / period.tv_sec, events * 1000 / ms);
+		seq_printf(m, "%ld total events, %ld.%03ld events/sec\n",
+			   events, events * 1000 / ms,
+			   (events * 1000000 / ms) % 1000);
 	else
 		seq_printf(m, "%ld total events\n", events);
 
diff --git a/kernel/user.c b/kernel/user.c
index e7d11cef699..9ca2848fc35 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -55,25 +55,22 @@ struct user_struct root_user = {
 /*
  * These routines must be called with the uidhash spinlock held!
  */
-static inline void uid_hash_insert(struct user_struct *up, struct list_head *hashent)
+static inline void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
 {
-	list_add(&up->uidhash_list, hashent);
+	hlist_add_head(&up->uidhash_node, hashent);
 }
 
 static inline void uid_hash_remove(struct user_struct *up)
 {
-	list_del(&up->uidhash_list);
+	hlist_del_init(&up->uidhash_node);
 }
 
-static inline struct user_struct *uid_hash_find(uid_t uid, struct list_head *hashent)
+static inline struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
 {
-	struct list_head *up;
-
-	list_for_each(up, hashent) {
-		struct user_struct *user;
-
-		user = list_entry(up, struct user_struct, uidhash_list);
+	struct user_struct *user;
+	struct hlist_node *h;
 
+	hlist_for_each_entry(user, h, hashent, uidhash_node) {
 		if(user->uid == uid) {
 			atomic_inc(&user->__count);
 			return user;
@@ -122,7 +119,7 @@ void free_uid(struct user_struct *up)
 
 struct user_struct * alloc_uid(struct user_namespace *ns, uid_t uid)
 {
-	struct list_head *hashent = uidhashentry(ns, uid);
+	struct hlist_head *hashent = uidhashentry(ns, uid);
 	struct user_struct *up;
 
 	spin_lock_irq(&uidhash_lock);
@@ -202,6 +199,30 @@ void switch_uid(struct user_struct *new_user)
 	suid_keys(current);
 }
 
+void release_uids(struct user_namespace *ns)
+{
+	int i;
+	unsigned long flags;
+	struct hlist_head *head;
+	struct hlist_node *nd;
+
+	spin_lock_irqsave(&uidhash_lock, flags);
+	/*
+	 * collapse the chains so that the user_struct-s will
+	 * be still alive, but not in hashes. subsequent free_uid()
+	 * will free them.
+	 */
+	for (i = 0; i < UIDHASH_SZ; i++) {
+		head = ns->uidhash_table + i;
+		while (!hlist_empty(head)) {
+			nd = head->first;
+			hlist_del_init(nd);
+		}
+	}
+	spin_unlock_irqrestore(&uidhash_lock, flags);
+
+	free_uid(ns->root_user);
+}
 
 static int __init uid_cache_init(void)
 {
@@ -211,7 +232,7 @@ static int __init uid_cache_init(void)
 			0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
 	for(n = 0; n < UIDHASH_SZ; ++n)
-		INIT_LIST_HEAD(init_user_ns.uidhash_table + n);
+		INIT_HLIST_HEAD(init_user_ns.uidhash_table + n);
 
 	/* Insert the root user immediately (init already runs as root) */
 	spin_lock_irq(&uidhash_lock);
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index d055d987850..7af90fc4f0f 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -39,7 +39,7 @@ static struct user_namespace *clone_user_ns(struct user_namespace *old_ns)
 	kref_init(&ns->kref);
 
 	for (n = 0; n < UIDHASH_SZ; ++n)
-		INIT_LIST_HEAD(ns->uidhash_table + n);
+		INIT_HLIST_HEAD(ns->uidhash_table + n);
 
 	/* Insert new root user.  */
 	ns->root_user = alloc_uid(ns, 0);
@@ -81,6 +81,7 @@ void free_user_ns(struct kref *kref)
 	struct user_namespace *ns;
 
 	ns = container_of(kref, struct user_namespace, kref);
+	release_uids(ns);
 	kfree(ns);
 }
 
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 9d8180a0f0d..816d7b24fa0 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -28,7 +28,9 @@ static struct uts_namespace *clone_uts_ns(struct uts_namespace *old_ns)
 	if (!ns)
 		return ERR_PTR(-ENOMEM);
 
+	down_read(&uts_sem);
 	memcpy(&ns->name, &old_ns->name, sizeof(ns->name));
+	up_read(&uts_sem);
 	kref_init(&ns->kref);
 	return ns;
 }
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 58e5c152a6b..e080d1d744c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -635,7 +635,7 @@ int keventd_up(void)
 int current_is_keventd(void)
 {
 	struct cpu_workqueue_struct *cwq;
-	int cpu = smp_processor_id();	/* preempt-safe: keventd is per-cpu */
+	int cpu = raw_smp_processor_id(); /* preempt-safe: keventd is per-cpu */
 	int ret = 0;
 
 	BUG_ON(!keventd_wq);