Merge branch 'linux-3.0.y' into HEAD

Conflicts:
	drivers/net/tun.c

9 files changed, 97 insertions, 65 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9c9b754..b2e84bd 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -123,6 +123,19 @@ static inline struct cpuset *task_cs(struct task_struct *task)
 			    struct cpuset, css);
 }
 
+#ifdef CONFIG_NUMA
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+	return task->mempolicy;
+}
+#else
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+	return false;
+}
+#endif
+
+
 /* bits in struct cpuset flags field */
 typedef enum {
 	CS_CPU_EXCLUSIVE,
@@ -949,7 +962,8 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 static void cpuset_change_task_nodemask(struct task_struct *tsk,
 					nodemask_t *newmems)
 {
-repeat:
+	bool need_loop;
+
 	/*
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
@@ -960,46 +974,27 @@ repeat:
 		return;
 
 	task_lock(tsk);
-	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
-	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
-
-
 	/*
-	 * ensure checking ->mems_allowed_change_disable after setting all new
-	 * allowed nodes.
-	 *
-	 * the read-side task can see an nodemask with new allowed nodes and
-	 * old allowed nodes. and if it allocates page when cpuset clears newly
-	 * disallowed ones continuous, it can see the new allowed bits.
-	 *
-	 * And if setting all new allowed nodes is after the checking, setting
-	 * all new allowed nodes and clearing newly disallowed ones will be done
-	 * continuous, and the read-side task may find no node to alloc page.
+	 * Determine if a loop is necessary if another thread is doing
+	 * get_mems_allowed().  If at least one node remains unchanged and
+	 * tsk does not have a mempolicy, then an empty nodemask will not be
+	 * possible when mems_allowed is larger than a word.
 	 */
-	smp_mb();
+	need_loop = task_has_mempolicy(tsk) ||
+			!nodes_intersects(*newmems, tsk->mems_allowed);
 
-	/*
-	 * Allocation of memory is very fast, we needn't sleep when waiting
-	 * for the read-side.
-	 */
-	while (ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
-		task_unlock(tsk);
-		if (!task_curr(tsk))
-			yield();
-		goto repeat;
-	}
+	if (need_loop)
+		write_seqcount_begin(&tsk->mems_allowed_seq);
 
-	/*
-	 * ensure checking ->mems_allowed_change_disable before clearing all new
-	 * disallowed nodes.
-	 *
-	 * if clearing newly disallowed bits before the checking, the read-side
-	 * task may find no node to alloc page.
-	 */
-	smp_mb();
+	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
+	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
 
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
 	tsk->mems_allowed = *newmems;
+
+	if (need_loop)
+		write_seqcount_end(&tsk->mems_allowed_seq);
+
 	task_unlock(tsk);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index fa6030d..158ca4f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1001,6 +1001,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 #ifdef CONFIG_CGROUPS
 	init_rwsem(&sig->threadgroup_fork_lock);
 #endif
+#ifdef CONFIG_CPUSETS
+	seqcount_init(&tsk->mems_allowed_seq);
+#endif
 
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
diff --git a/kernel/futex.c b/kernel/futex.c
index b2d51a7..e45efe7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2231,11 +2231,11 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb,
  * @uaddr2:	the pi futex we will take prior to returning to user-space
  *
  * The caller will wait on uaddr and will be requeued by futex_requeue() to
- * uaddr2 which must be PI aware.  Normal wakeup will wake on uaddr2 and
- * complete the acquisition of the rt_mutex prior to returning to userspace.
- * This ensures the rt_mutex maintains an owner when it has waiters; without
- * one, the pi logic wouldn't know which task to boost/deboost, if there was a
- * need to.
+ * uaddr2 which must be PI aware and unique from uaddr.  Normal wakeup will wake
+ * on uaddr2 and complete the acquisition of the rt_mutex prior to returning to
+ * userspace.  This ensures the rt_mutex maintains an owner when it has waiters;
+ * without one, the pi logic would not know which task to boost/deboost, if
+ * there was a need to.
  *
  * We call schedule in futex_wait_queue_me() when we enqueue and return there
  * via the following:
@@ -2272,6 +2272,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	struct futex_q q = futex_q_init;
 	int res, ret;
 
+	if (uaddr == uaddr2)
+		return -EINVAL;
+
 	if (!bitset)
 		return -EINVAL;
 
@@ -2343,7 +2346,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 * signal.  futex_unlock_pi() will not destroy the lock_ptr nor
 		 * the pi_state.
 		 */
-		WARN_ON(!&q.pi_state);
+		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
 		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
 		debug_rt_mutex_free_waiter(&rt_waiter);
@@ -2370,7 +2373,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * fault, unlock the rt_mutex and return the fault to userspace.
 	 */
 	if (ret == -EFAULT) {
-		if (rt_mutex_owner(pi_mutex) == current)
+		if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
 			rt_mutex_unlock(pi_mutex);
 	} else if (ret == -EINTR) {
 		/*
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 470d08c..10e0772 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -117,7 +117,7 @@ irqreturn_t
 handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 {
 	irqreturn_t retval = IRQ_NONE;
-	unsigned int random = 0, irq = desc->irq_data.irq;
+	unsigned int flags = 0, irq = desc->irq_data.irq;
 
 	do {
 		irqreturn_t res;
@@ -145,7 +145,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 
 			/* Fall through to add to randomness */
 		case IRQ_HANDLED:
-			random |= action->flags;
+			flags |= action->flags;
 			break;
 
 		default:
@@ -156,8 +156,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 		action = action->next;
 	} while (action);
 
-	if (random & IRQF_SAMPLE_RANDOM)
-		add_interrupt_randomness(irq);
+	add_interrupt_randomness(irq, flags);
 
 	if (!noirqdebug)
 		note_interrupt(irq, desc, retval);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index df8136f..fa4a70e 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -886,22 +886,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	if (desc->irq_data.chip == &no_irq_chip)
 		return -ENOSYS;
-	/*
-	 * Some drivers like serial.c use request_irq() heavily,
-	 * so we have to be careful not to interfere with a
-	 * running system.
-	 */
-	if (new->flags & IRQF_SAMPLE_RANDOM) {
-		/*
-		 * This function might sleep, we want to call it first,
-		 * outside of the atomic block.
-		 * Yes, this might clear the entropy pool if the wrong
-		 * driver is attempted to be loaded, without actually
-		 * installing a new handler, but is this really a problem,
-		 * only the sysadmin is able to do this.
-		 */
-		rand_initialize_irq(irq);
-	}
 
 	/*
 	 * Check whether the interrupt nests into another interrupt
@@ -1325,7 +1309,6 @@ EXPORT_SYMBOL(free_irq);
  *	Flags:
  *
  *	IRQF_SHARED		Interrupt is shared
- *	IRQF_SAMPLE_RANDOM	The interrupt can be used for entropy
  *	IRQF_TRIGGER_*		Specify active edge(s) or level
  *
  */
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 8884c27..32f1590 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -344,6 +344,7 @@ int hibernation_snapshot(int platform_mode)
 		goto Complete_devices;
 
 	suspend_console();
+	ftrace_stop();
 	pm_restrict_gfp_mask();
 	error = dpm_suspend(PMSG_FREEZE);
 	if (error)
@@ -369,6 +370,7 @@ int hibernation_snapshot(int platform_mode)
 	if (error || !in_suspend)
 		pm_restore_gfp_mask();
 
+	ftrace_start();
 	resume_console();
 
  Complete_devices:
@@ -471,6 +473,7 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	suspend_console();
+	ftrace_stop();
 	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
@@ -478,6 +481,7 @@ int hibernation_restore(int platform_mode)
 		dpm_resume_end(PMSG_RECOVER);
 	}
 	pm_restore_gfp_mask();
+	ftrace_start();
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -504,6 +508,7 @@ int hibernation_platform_enter(void)
 
 	entering_platform_hibernation = true;
 	suspend_console();
+	ftrace_stop();
 	error = dpm_suspend_start(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -547,6 +552,7 @@ int hibernation_platform_enter(void)
  Resume_devices:
 	entering_platform_hibernation = false;
 	dpm_resume_end(PMSG_RESTORE);
+	ftrace_start();
 	resume_console();
 
  Close:
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index a8bf2e6..44c78d5 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
+#include <linux/ftrace.h>
 #include <trace/events/power.h>
 
 #include "power.h"
@@ -213,6 +214,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
+	ftrace_stop();
 	suspend_test_start();
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
@@ -229,6 +231,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	dpm_resume_end(PMSG_RESUME);
 	suspend_test_finish("resume devices");
+	ftrace_start();
 	resume_console();
  Close:
 	if (suspend_ops->end)
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index f1eb182..61fc450 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -375,7 +375,9 @@ int second_overflow(unsigned long secs)
 			time_state = TIME_DEL;
 		break;
 	case TIME_INS:
-		if (secs % 86400 == 0) {
+		if (!(time_status & STA_INS))
+			time_state = TIME_OK;
+		else if (secs % 86400 == 0) {
 			leap = -1;
 			time_state = TIME_OOP;
 			time_tai++;
@@ -384,7 +386,9 @@ int second_overflow(unsigned long secs)
 		}
 		break;
 	case TIME_DEL:
-		if ((secs + 1) % 86400 == 0) {
+		if (!(time_status & STA_DEL))
+			time_state = TIME_OK;
+		else if ((secs + 1) % 86400 == 0) {
 			leap = 1;
 			time_tai--;
 			time_state = TIME_WAIT;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ee1845b..e88c924 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3561,6 +3561,41 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 	return notifier_from_errno(0);
 }
 
+/*
+ * Workqueues should be brought up before normal priority CPU notifiers.
+ * This will be registered high priority CPU notifier.
+ */
+static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb,
+					       unsigned long action,
+					       void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_CANCELED:
+	case CPU_DOWN_FAILED:
+	case CPU_ONLINE:
+		return workqueue_cpu_callback(nfb, action, hcpu);
+	}
+	return NOTIFY_OK;
+}
+
+/*
+ * Workqueues should be brought down after normal priority CPU notifiers.
+ * This will be registered as low priority CPU notifier.
+ */
+static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
+						 unsigned long action,
+						 void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_DOWN_PREPARE:
+	case CPU_DYING:
+	case CPU_POST_DEAD:
+		return workqueue_cpu_callback(nfb, action, hcpu);
+	}
+	return NOTIFY_OK;
+}
+
 #ifdef CONFIG_SMP
 
 struct work_for_cpu {
@@ -3754,7 +3789,8 @@ static int __init init_workqueues(void)
 	unsigned int cpu;
 	int i;
 
-	cpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE);
+	cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP);
+	cpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN);
 
 	/* initialize gcwqs */
 	for_each_gcwq_cpu(cpu) {