Merge commit 'v2.6.32' into next

15 files changed, 894 insertions, 125 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index b8d4cd8ac0b..d7c13d249b2 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -94,6 +94,7 @@ obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_SLOW_WORK) += slow-work.o
+obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 114e704760f..bd7273e6282 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -121,7 +121,9 @@ static void poll_all_shared_irqs(void)
 		if (!(status & IRQ_SPURIOUS_DISABLED))
 			continue;
 
+		local_irq_disable();
 		try_one_irq(i, desc);
+		local_irq_enable();
 	}
 }
 
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 5fe709982ca..ab7ae57773e 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -150,29 +150,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 EXPORT_SYMBOL(kthread_create);
 
 /**
- * kthread_bind - bind a just-created kthread to a cpu.
- * @k: thread created by kthread_create().
- * @cpu: cpu (might not be online, must be possible) for @k to run on.
- *
- * Description: This function is equivalent to set_cpus_allowed(),
- * except that @cpu doesn't need to be online, and the thread must be
- * stopped (i.e., just returned from kthread_create()).
- */
-void kthread_bind(struct task_struct *k, unsigned int cpu)
-{
-	/* Must have done schedule() in kthread() before we set_task_cpu */
-	if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
-		WARN_ON(1);
-		return;
-	}
-	set_task_cpu(k, cpu);
-	k->cpus_allowed = cpumask_of_cpu(cpu);
-	k->rt.nr_cpus_allowed = 1;
-	k->flags |= PF_THREAD_BOUND;
-}
-EXPORT_SYMBOL(kthread_bind);
-
-/**
  * kthread_stop - stop a thread created by kthread_create().
  * @k: thread created by kthread_create().
  *
diff --git a/kernel/module.c b/kernel/module.c
index 8b7d8805819..5842a71cf05 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1187,7 +1187,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
 
 	/* Count loaded sections and allocate structures */
 	for (i = 0; i < nsect; i++)
-		if (sechdrs[i].sh_flags & SHF_ALLOC)
+		if (sechdrs[i].sh_flags & SHF_ALLOC
+		    && sechdrs[i].sh_size)
 			nloaded++;
 	size[0] = ALIGN(sizeof(*sect_attrs)
 			+ nloaded * sizeof(sect_attrs->attrs[0]),
@@ -1207,6 +1208,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
 	for (i = 0; i < nsect; i++) {
 		if (! (sechdrs[i].sh_flags & SHF_ALLOC))
 			continue;
+		if (!sechdrs[i].sh_size)
+			continue;
 		sattr->address = sechdrs[i].sh_addr;
 		sattr->name = kstrdup(secstrings + sechdrs[i].sh_name,
 					GFP_KERNEL);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 0536125b049..f3077c0ab18 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -59,7 +59,7 @@
 		NUM_RCU_LVL_2, \
 		NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
 	}, \
-	.signaled = RCU_SIGNAL_INIT, \
+	.signaled = RCU_GP_IDLE, \
 	.gpnum = -300, \
 	.completed = -300, \
 	.onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
@@ -657,14 +657,17 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	 * irqs disabled.
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
-		spin_lock(&rnp->lock);	/* irqs already disabled. */
+		spin_lock(&rnp->lock);		/* irqs already disabled. */
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		rnp->gpnum = rsp->gpnum;
-		spin_unlock(&rnp->lock);	/* irqs already disabled. */
+		spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	}
 
+	rnp = rcu_get_root(rsp);
+	spin_lock(&rnp->lock);			/* irqs already disabled. */
 	rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
+	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 	spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
@@ -706,6 +709,7 @@ static void cpu_quiet_msk_finish(struct rcu_state *rsp, unsigned long flags)
 {
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	rsp->completed = rsp->gpnum;
+	rsp->signaled = RCU_GP_IDLE;
 	rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
 	rcu_start_gp(rsp, flags);  /* releases root node's rnp->lock. */
 }
@@ -1162,9 +1166,10 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 	}
 	spin_unlock(&rnp->lock);
 	switch (signaled) {
+	case RCU_GP_IDLE:
 	case RCU_GP_INIT:
 
-		break; /* grace period still initializing, ignore. */
+		break; /* grace period idle or initializing, ignore. */
 
 	case RCU_SAVE_DYNTICK:
 
@@ -1178,7 +1183,8 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 
 		/* Update state, record completion counter. */
 		spin_lock(&rnp->lock);
-		if (lastcomp == rsp->completed) {
+		if (lastcomp == rsp->completed &&
+		    rsp->signaled == RCU_SAVE_DYNTICK) {
 			rsp->signaled = RCU_FORCE_QS;
 			dyntick_record_completed(rsp, lastcomp);
 		}
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 1823c6e2060..1899023b096 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -201,9 +201,10 @@ struct rcu_data {
 };
 
 /* Values for signaled field in struct rcu_state. */
-#define RCU_GP_INIT		0	/* Grace period being initialized. */
-#define RCU_SAVE_DYNTICK	1	/* Need to scan dyntick state. */
-#define RCU_FORCE_QS		2	/* Need to force quiescent state. */
+#define RCU_GP_IDLE		0	/* No grace period in progress. */
+#define RCU_GP_INIT		1	/* Grace period being initialized. */
+#define RCU_SAVE_DYNTICK	2	/* Need to scan dyntick state. */
+#define RCU_FORCE_QS		3	/* Need to force quiescent state. */
 #ifdef CONFIG_NO_HZ
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
 #else /* #ifdef CONFIG_NO_HZ */
diff --git a/kernel/sched.c b/kernel/sched.c
index a455dca884a..3c11ae0a948 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -309,6 +309,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
 #ifdef CONFIG_SMP
 static int root_task_group_empty(void)
 {
@@ -316,7 +318,6 @@ static int root_task_group_empty(void)
 }
 #endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
 #else /* !CONFIG_USER_SCHED */
@@ -1992,6 +1993,38 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	/* Must have done schedule() in kthread() before we set_task_cpu */
+	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+		WARN_ON(1);
+		return;
+	}
+
+	spin_lock_irqsave(&rq->lock, flags);
+	set_task_cpu(p, cpu);
+	p->cpus_allowed = cpumask_of_cpu(cpu);
+	p->rt.nr_cpus_allowed = 1;
+	p->flags |= PF_THREAD_BOUND;
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+EXPORT_SYMBOL(kthread_bind);
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -2004,7 +2037,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 	/*
 	 * Buddy candidates are cache hot:
 	 */
-	if (sched_feat(CACHE_HOT_BUDDY) &&
+	if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
 			(&p->se == cfs_rq_of(&p->se)->next ||
 			 &p->se == cfs_rq_of(&p->se)->last))
 		return 1;
@@ -9532,13 +9565,13 @@ void __init sched_init(void)
 	current->sched_class = &fair_sched_class;
 
 	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
-	alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
-	alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+	zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
 	alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
 #endif
-	alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+	zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
 	perf_event_init();
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c32c3e643da..37087a7fac2 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -822,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		 * re-elected due to buddy favours.
 		 */
 		clear_buddies(cfs_rq, curr);
+		return;
+	}
+
+	/*
+	 * Ensure that a task that missed wakeup preemption by a
+	 * narrow margin doesn't have to wait for a full slice.
+	 * This also mitigates buddy induced latencies under load.
+	 */
+	if (!sched_feat(WAKEUP_PREEMPT))
+		return;
+
+	if (delta_exec < sysctl_sched_min_granularity)
+		return;
+
+	if (cfs_rq->nr_running > 1) {
+		struct sched_entity *se = __pick_next_entity(cfs_rq);
+		s64 delta = curr->vruntime - se->vruntime;
+
+		if (delta > ideal_runtime)
+			resched_task(rq_of(cfs_rq)->curr);
 	}
 }
 
@@ -861,21 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *se = __pick_next_entity(cfs_rq);
-	struct sched_entity *buddy;
+	struct sched_entity *left = se;
 
-	if (cfs_rq->next) {
-		buddy = cfs_rq->next;
-		cfs_rq->next = NULL;
-		if (wakeup_preempt_entity(buddy, se) < 1)
-			return buddy;
-	}
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+		se = cfs_rq->next;
 
-	if (cfs_rq->last) {
-		buddy = cfs_rq->last;
-		cfs_rq->last = NULL;
-		if (wakeup_preempt_entity(buddy, se) < 1)
-			return buddy;
-	}
+	/*
+	 * Prefer last buddy, try to return the CPU to a preempted task.
+	 */
+	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+		se = cfs_rq->last;
+
+	clear_buddies(cfs_rq, se);
 
 	return se;
 }
@@ -1577,6 +1594,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	int sync = wake_flags & WF_SYNC;
+	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
 	update_curr(cfs_rq);
 
@@ -1591,18 +1609,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (unlikely(se == pse))
 		return;
 
-	/*
-	 * Only set the backward buddy when the current task is still on the
-	 * rq. This can happen when a wakeup gets interleaved with schedule on
-	 * the ->pre_schedule() or idle_balance() point, either of which can
-	 * drop the rq lock.
-	 *
-	 * Also, during early boot the idle thread is in the fair class, for
-	 * obvious reasons its a bad idea to schedule back to the idle thread.
-	 */
-	if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
-		set_last_buddy(se);
-	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
+	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
 		set_next_buddy(pse);
 
 	/*
@@ -1648,8 +1655,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 
 	BUG_ON(!pse);
 
-	if (wakeup_preempt_entity(se, pse) == 1)
+	if (wakeup_preempt_entity(se, pse) == 1) {
 		resched_task(curr);
+		/*
+		 * Only set the backward buddy when the current task is still
+		 * on the rq. This can happen when a wakeup gets interleaved
+		 * with schedule on the ->pre_schedule() or idle_balance()
+		 * point, either of which can * drop the rq lock.
+		 *
+		 * Also, during early boot the idle thread is in the fair class,
+		 * for obvious reasons its a bad idea to schedule back to it.
+		 */
+		if (unlikely(!se->on_rq || curr == rq->idle))
+			return;
+		if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
+			set_last_buddy(se);
+	}
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
diff --git a/kernel/slow-work-debugfs.c b/kernel/slow-work-debugfs.c
new file mode 100644
index 00000000000..e45c4364529
--- /dev/null
+++ b/kernel/slow-work-debugfs.c
@@ -0,0 +1,227 @@
+/* Slow work debugging
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/slow-work.h>
+#include <linux/fs.h>
+#include <linux/time.h>
+#include <linux/seq_file.h>
+#include "slow-work.h"
+
+#define ITERATOR_SHIFT		(BITS_PER_LONG - 4)
+#define ITERATOR_SELECTOR	(0xfUL << ITERATOR_SHIFT)
+#define ITERATOR_COUNTER	(~ITERATOR_SELECTOR)
+
+void slow_work_new_thread_desc(struct slow_work *work, struct seq_file *m)
+{
+	seq_puts(m, "Slow-work: New thread");
+}
+
+/*
+ * Render the time mark field on a work item into a 5-char time with units plus
+ * a space
+ */
+static void slow_work_print_mark(struct seq_file *m, struct slow_work *work)
+{
+	struct timespec now, diff;
+
+	now = CURRENT_TIME;
+	diff = timespec_sub(now, work->mark);
+
+	if (diff.tv_sec < 0)
+		seq_puts(m, "  -ve ");
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000)
+		seq_printf(m, "%3luns ", diff.tv_nsec);
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000)
+		seq_printf(m, "%3luus ", diff.tv_nsec / 1000);
+	else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000000)
+		seq_printf(m, "%3lums ", diff.tv_nsec / 1000000);
+	else if (diff.tv_sec <= 1)
+		seq_puts(m, "   1s ");
+	else if (diff.tv_sec < 60)
+		seq_printf(m, "%4lus ", diff.tv_sec);
+	else if (diff.tv_sec < 60 * 60)
+		seq_printf(m, "%4lum ", diff.tv_sec / 60);
+	else if (diff.tv_sec < 60 * 60 * 24)
+		seq_printf(m, "%4luh ", diff.tv_sec / 3600);
+	else
+		seq_puts(m, "exces ");
+}
+
+/*
+ * Describe a slow work item for debugfs
+ */
+static int slow_work_runqueue_show(struct seq_file *m, void *v)
+{
+	struct slow_work *work;
+	struct list_head *p = v;
+	unsigned long id;
+
+	switch ((unsigned long) v) {
+	case 1:
+		seq_puts(m, "THR PID   ITEM ADDR        FL MARK  DESC\n");
+		return 0;
+	case 2:
+		seq_puts(m, "=== ===== ================ == ===== ==========\n");
+		return 0;
+
+	case 3 ... 3 + SLOW_WORK_THREAD_LIMIT - 1:
+		id = (unsigned long) v - 3;
+
+		read_lock(&slow_work_execs_lock);
+		work = slow_work_execs[id];
+		if (work) {
+			smp_read_barrier_depends();
+
+			seq_printf(m, "%3lu %5d %16p %2lx ",
+				   id, slow_work_pids[id], work, work->flags);
+			slow_work_print_mark(m, work);
+
+			if (work->ops->desc)
+				work->ops->desc(work, m);
+			seq_putc(m, '\n');
+		}
+		read_unlock(&slow_work_execs_lock);
+		return 0;
+
+	default:
+		work = list_entry(p, struct slow_work, link);
+		seq_printf(m, "%3s     - %16p %2lx ",
+			   work->flags & SLOW_WORK_VERY_SLOW ? "vsq" : "sq",
+			   work, work->flags);
+		slow_work_print_mark(m, work);
+
+		if (work->ops->desc)
+			work->ops->desc(work, m);
+		seq_putc(m, '\n');
+		return 0;
+	}
+}
+
+/*
+ * map the iterator to a work item
+ */
+static void *slow_work_runqueue_index(struct seq_file *m, loff_t *_pos)
+{
+	struct list_head *p;
+	unsigned long count, id;
+
+	switch (*_pos >> ITERATOR_SHIFT) {
+	case 0x0:
+		if (*_pos == 0)
+			*_pos = 1;
+		if (*_pos < 3)
+			return (void *)(unsigned long) *_pos;
+		if (*_pos < 3 + SLOW_WORK_THREAD_LIMIT)
+			for (id = *_pos - 3;
+			     id < SLOW_WORK_THREAD_LIMIT;
+			     id++, (*_pos)++)
+				if (slow_work_execs[id])
+					return (void *)(unsigned long) *_pos;
+		*_pos = 0x1UL << ITERATOR_SHIFT;
+
+	case 0x1:
+		count = *_pos & ITERATOR_COUNTER;
+		list_for_each(p, &slow_work_queue) {
+			if (count == 0)
+				return p;
+			count--;
+		}
+		*_pos = 0x2UL << ITERATOR_SHIFT;
+
+	case 0x2:
+		count = *_pos & ITERATOR_COUNTER;
+		list_for_each(p, &vslow_work_queue) {
+			if (count == 0)
+				return p;
+			count--;
+		}
+		*_pos = 0x3UL << ITERATOR_SHIFT;
+
+	default:
+		return NULL;
+	}
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *slow_work_runqueue_start(struct seq_file *m, loff_t *_pos)
+{
+	spin_lock_irq(&slow_work_queue_lock);
+	return slow_work_runqueue_index(m, _pos);
+}
+
+/*
+ * move to the next line
+ */
+static void *slow_work_runqueue_next(struct seq_file *m, void *v, loff_t *_pos)
+{
+	struct list_head *p = v;
+	unsigned long selector = *_pos >> ITERATOR_SHIFT;
+
+	(*_pos)++;
+	switch (selector) {
+	case 0x0:
+		return slow_work_runqueue_index(m, _pos);
+
+	case 0x1:
+		if (*_pos >> ITERATOR_SHIFT == 0x1) {
+			p = p->next;
+			if (p != &slow_work_queue)
+				return p;
+		}
+		*_pos = 0x2UL << ITERATOR_SHIFT;
+		p = &vslow_work_queue;
+
+	case 0x2:
+		if (*_pos >> ITERATOR_SHIFT == 0x2) {
+			p = p->next;
+			if (p != &vslow_work_queue)
+				return p;
+		}
+		*_pos = 0x3UL << ITERATOR_SHIFT;
+
+	default:
+		return NULL;
+	}
+}
+
+/*
+ * clean up after reading
+ */
+static void slow_work_runqueue_stop(struct seq_file *m, void *v)
+{
+	spin_unlock_irq(&slow_work_queue_lock);
+}
+
+static const struct seq_operations slow_work_runqueue_ops = {
+	.start		= slow_work_runqueue_start,
+	.stop		= slow_work_runqueue_stop,
+	.next		= slow_work_runqueue_next,
+	.show		= slow_work_runqueue_show,
+};
+
+/*
+ * open "/sys/kernel/debug/slow_work/runqueue" to list queue contents
+ */
+static int slow_work_runqueue_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &slow_work_runqueue_ops);
+}
+
+const struct file_operations slow_work_runqueue_fops = {
+	.owner		= THIS_MODULE,
+	.open		= slow_work_runqueue_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 0d31135efbf..00889bd3c59 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -16,11 +16,8 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/wait.h>
-
-#define SLOW_WORK_CULL_TIMEOUT (5 * HZ)	/* cull threads 5s after running out of
-					 * things to do */
-#define SLOW_WORK_OOM_TIMEOUT (5 * HZ)	/* can't start new threads for 5s after
-					 * OOM */
+#include <linux/debugfs.h>
+#include "slow-work.h"
 
 static void slow_work_cull_timeout(unsigned long);
 static void slow_work_oom_timeout(unsigned long);
@@ -46,7 +43,7 @@ static unsigned vslow_work_proportion = 50; /* % of threads that may process
 
 #ifdef CONFIG_SYSCTL
 static const int slow_work_min_min_threads = 2;
-static int slow_work_max_max_threads = 255;
+static int slow_work_max_max_threads = SLOW_WORK_THREAD_LIMIT;
 static const int slow_work_min_vslow = 1;
 static const int slow_work_max_vslow = 99;
 
@@ -98,6 +95,56 @@ static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0);
 static struct slow_work slow_work_new_thread; /* new thread starter */
 
 /*
+ * slow work ID allocation (use slow_work_queue_lock)
+ */
+static DECLARE_BITMAP(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+
+/*
+ * Unregistration tracking to prevent put_ref() from disappearing during module
+ * unload
+ */
+#ifdef CONFIG_MODULES
+static struct module *slow_work_thread_processing[SLOW_WORK_THREAD_LIMIT];
+static struct module *slow_work_unreg_module;
+static struct slow_work *slow_work_unreg_work_item;
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_unreg_wq);
+static DEFINE_MUTEX(slow_work_unreg_sync_lock);
+
+static void slow_work_set_thread_processing(int id, struct slow_work *work)
+{
+	if (work)
+		slow_work_thread_processing[id] = work->owner;
+}
+static void slow_work_done_thread_processing(int id, struct slow_work *work)
+{
+	struct module *module = slow_work_thread_processing[id];
+
+	slow_work_thread_processing[id] = NULL;
+	smp_mb();
+	if (slow_work_unreg_work_item == work ||
+	    slow_work_unreg_module == module)
+		wake_up_all(&slow_work_unreg_wq);
+}
+static void slow_work_clear_thread_processing(int id)
+{
+	slow_work_thread_processing[id] = NULL;
+}
+#else
+static void slow_work_set_thread_processing(int id, struct slow_work *work) {}
+static void slow_work_done_thread_processing(int id, struct slow_work *work) {}
+static void slow_work_clear_thread_processing(int id) {}
+#endif
+
+/*
+ * Data for tracking currently executing items for indication through /proc
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+struct slow_work *slow_work_execs[SLOW_WORK_THREAD_LIMIT];
+pid_t slow_work_pids[SLOW_WORK_THREAD_LIMIT];
+DEFINE_RWLOCK(slow_work_execs_lock);
+#endif
+
+/*
  * The queues of work items and the lock governing access to them.  These are
  * shared between all the CPUs.  It doesn't make sense to have per-CPU queues
  * as the number of threads bears no relation to the number of CPUs.
@@ -105,9 +152,18 @@ static struct slow_work slow_work_new_thread; /* new thread starter */
  * There are two queues of work items: one for slow work items, and one for
  * very slow work items.
  */
-static LIST_HEAD(slow_work_queue);
-static LIST_HEAD(vslow_work_queue);
-static DEFINE_SPINLOCK(slow_work_queue_lock);
+LIST_HEAD(slow_work_queue);
+LIST_HEAD(vslow_work_queue);
+DEFINE_SPINLOCK(slow_work_queue_lock);
+
+/*
+ * The following are two wait queues that get pinged when a work item is placed
+ * on an empty queue.  These allow work items that are hogging a thread by
+ * sleeping in a way that could be deferred to yield their thread and enqueue
+ * themselves.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_queue_waits_for_occupation);
+static DECLARE_WAIT_QUEUE_HEAD(vslow_work_queue_waits_for_occupation);
 
 /*
  * The thread controls.  A variable used to signal to the threads that they
@@ -126,6 +182,20 @@ static DECLARE_COMPLETION(slow_work_last_thread_exited);
 static int slow_work_user_count;
 static DEFINE_MUTEX(slow_work_user_lock);
 
+static inline int slow_work_get_ref(struct slow_work *work)
+{
+	if (work->ops->get_ref)
+		return work->ops->get_ref(work);
+
+	return 0;
+}
+
+static inline void slow_work_put_ref(struct slow_work *work)
+{
+	if (work->ops->put_ref)
+		work->ops->put_ref(work);
+}
+
 /*
  * Calculate the maximum number of active threads in the pool that are
  * permitted to process very slow work items.
@@ -149,7 +219,7 @@ static unsigned slow_work_calc_vsmax(void)
  * Attempt to execute stuff queued on a slow thread.  Return true if we managed
  * it, false if there was nothing to do.
  */
-static bool slow_work_execute(void)
+static noinline bool slow_work_execute(int id)
 {
 	struct slow_work *work = NULL;
 	unsigned vsmax;
@@ -186,6 +256,13 @@ static bool slow_work_execute(void)
 	} else {
 		very_slow = false; /* avoid the compiler warning */
 	}
+
+	slow_work_set_thread_processing(id, work);
+	if (work) {
+		slow_work_mark_time(work);
+		slow_work_begin_exec(id, work);
+	}
+
 	spin_unlock_irq(&slow_work_queue_lock);
 
 	if (!work)
@@ -194,12 +271,19 @@ static bool slow_work_execute(void)
 	if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags))
 		BUG();
 
-	work->ops->execute(work);
+	/* don't execute if the work is in the process of being cancelled */
+	if (!test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		work->ops->execute(work);
 
 	if (very_slow)
 		atomic_dec(&vslow_work_executing_count);
 	clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags);
 
+	/* wake up anyone waiting for this work to be complete */
+	wake_up_bit(&work->flags, SLOW_WORK_EXECUTING);
+
+	slow_work_end_exec(id, work);
+
 	/* if someone tried to enqueue the item whilst we were executing it,
 	 * then it'll be left unenqueued to avoid multiple threads trying to
 	 * execute it simultaneously
@@ -219,7 +303,10 @@ static bool slow_work_execute(void)
 		spin_unlock_irq(&slow_work_queue_lock);
 	}
 
-	work->ops->put_ref(work);
+	/* sort out the race between module unloading and put_ref() */
+	slow_work_put_ref(work);
+	slow_work_done_thread_processing(id, work);
+
 	return true;
 
 auto_requeue:
@@ -227,15 +314,61 @@ auto_requeue:
 	 * - we transfer our ref on the item back to the appropriate queue
 	 * - don't wake another thread up as we're awake already
 	 */
+	slow_work_mark_time(work);
 	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
 		list_add_tail(&work->link, &vslow_work_queue);
 	else
 		list_add_tail(&work->link, &slow_work_queue);
 	spin_unlock_irq(&slow_work_queue_lock);
+	slow_work_clear_thread_processing(id);
 	return true;
 }
 
 /**
+ * slow_work_sleep_till_thread_needed - Sleep till thread needed by other work
+ * work: The work item under execution that wants to sleep
+ * _timeout: Scheduler sleep timeout
+ *
+ * Allow a requeueable work item to sleep on a slow-work processor thread until
+ * that thread is needed to do some other work or the sleep is interrupted by
+ * some other event.
+ *
+ * The caller must set up a wake up event before calling this and must have set
+ * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own
+ * condition before calling this function as no test is made here.
+ *
+ * False is returned if there is nothing on the queue; true is returned if the
+ * work item should be requeued
+ */
+bool slow_work_sleep_till_thread_needed(struct slow_work *work,
+					signed long *_timeout)
+{
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
+
+	DEFINE_WAIT(wait);
+
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+		wfo_wq = &vslow_work_queue_waits_for_occupation;
+		queue = &vslow_work_queue;
+	} else {
+		wfo_wq = &slow_work_queue_waits_for_occupation;
+		queue = &slow_work_queue;
+	}
+
+	if (!list_empty(queue))
+		return true;
+
+	add_wait_queue_exclusive(wfo_wq, &wait);
+	if (list_empty(queue))
+		*_timeout = schedule_timeout(*_timeout);
+	finish_wait(wfo_wq, &wait);
+
+	return !list_empty(queue);
+}
+EXPORT_SYMBOL(slow_work_sleep_till_thread_needed);
+
+/**
  * slow_work_enqueue - Schedule a slow work item for processing
  * @work: The work item to queue
  *
@@ -260,16 +393,22 @@ auto_requeue:
  * allowed to pick items to execute.  This ensures that very slow items won't
  * overly block ones that are just ordinarily slow.
  *
- * Returns 0 if successful, -EAGAIN if not.
+ * Returns 0 if successful, -EAGAIN if not (or -ECANCELED if cancelled work is
+ * attempted queued)
  */
 int slow_work_enqueue(struct slow_work *work)
 {
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
 	unsigned long flags;
+	int ret;
+
+	if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		return -ECANCELED;
 
 	BUG_ON(slow_work_user_count <= 0);
 	BUG_ON(!work);
 	BUG_ON(!work->ops);
-	BUG_ON(!work->ops->get_ref);
 
 	/* when honouring an enqueue request, we only promise that we will run
 	 * the work function in the future; we do not promise to run it once
@@ -280,8 +419,19 @@ int slow_work_enqueue(struct slow_work *work)
 	 * maintaining our promise
 	 */
 	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+			wfo_wq = &vslow_work_queue_waits_for_occupation;
+			queue = &vslow_work_queue;
+		} else {
+			wfo_wq = &slow_work_queue_waits_for_occupation;
+			queue = &slow_work_queue;
+		}
+
 		spin_lock_irqsave(&slow_work_queue_lock, flags);
 
+		if (unlikely(test_bit(SLOW_WORK_CANCELLING, &work->flags)))
+			goto cancelled;
+
 		/* we promise that we will not attempt to execute the work
 		 * function in more than one thread simultaneously
 		 *
@@ -299,25 +449,221 @@ int slow_work_enqueue(struct slow_work *work)
 		if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
 			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
 		} else {
-			if (work->ops->get_ref(work) < 0)
-				goto cant_get_ref;
-			if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
-				list_add_tail(&work->link, &vslow_work_queue);
-			else
-				list_add_tail(&work->link, &slow_work_queue);
+			ret = slow_work_get_ref(work);
+			if (ret < 0)
+				goto failed;
+			slow_work_mark_time(work);
+			list_add_tail(&work->link, queue);
 			wake_up(&slow_work_thread_wq);
+
+			/* if someone who could be requeued is sleeping on a
+			 * thread, then ask them to yield their thread */
+			if (work->link.prev == queue)
+				wake_up(wfo_wq);
 		}
 
 		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
 	}
 	return 0;
 
-cant_get_ref:
+cancelled:
+	ret = -ECANCELED;
+failed:
 	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
-	return -EAGAIN;
+	return ret;
 }
 EXPORT_SYMBOL(slow_work_enqueue);
 
+static int slow_work_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
+/**
+ * slow_work_cancel - Cancel a slow work item
+ * @work: The work item to cancel
+ *
+ * This function will cancel a previously enqueued work item. If we cannot
+ * cancel the work item, it is guarenteed to have run when this function
+ * returns.
+ */
+void slow_work_cancel(struct slow_work *work)
+{
+	bool wait = true, put = false;
+
+	set_bit(SLOW_WORK_CANCELLING, &work->flags);
+	smp_mb();
+
+	/* if the work item is a delayed work item with an active timer, we
+	 * need to wait for the timer to finish _before_ getting the spinlock,
+	 * lest we deadlock against the timer routine
+	 *
+	 * the timer routine will leave DELAYED set if it notices the
+	 * CANCELLING flag in time
+	 */
+	if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+		struct delayed_slow_work *dwork =
+			container_of(work, struct delayed_slow_work, work);
+		del_timer_sync(&dwork->timer);
+	}
+
+	spin_lock_irq(&slow_work_queue_lock);
+
+	if (test_bit(SLOW_WORK_DELAYED, &work->flags)) {
+		/* the timer routine aborted or never happened, so we are left
+		 * holding the timer's reference on the item and should just
+		 * drop the pending flag and wait for any ongoing execution to
+		 * finish */
+		struct delayed_slow_work *dwork =
+			container_of(work, struct delayed_slow_work, work);
+
+		BUG_ON(timer_pending(&dwork->timer));
+		BUG_ON(!list_empty(&work->link));
+
+		clear_bit(SLOW_WORK_DELAYED, &work->flags);
+		put = true;
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+	} else if (test_bit(SLOW_WORK_PENDING, &work->flags) &&
+		   !list_empty(&work->link)) {
+		/* the link in the pending queue holds a reference on the item
+		 * that we will need to release */
+		list_del_init(&work->link);
+		wait = false;
+		put = true;
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+
+	} else if (test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) {
+		/* the executor is holding our only reference on the item, so
+		 * we merely need to wait for it to finish executing */
+		clear_bit(SLOW_WORK_PENDING, &work->flags);
+	}
+
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	/* the EXECUTING flag is set by the executor whilst the spinlock is set
+	 * and before the item is dequeued - so assuming the above doesn't
+	 * actually dequeue it, simply waiting for the EXECUTING flag to be
+	 * released here should be sufficient */
+	if (wait)
+		wait_on_bit(&work->flags, SLOW_WORK_EXECUTING, slow_work_wait,
+			    TASK_UNINTERRUPTIBLE);
+
+	clear_bit(SLOW_WORK_CANCELLING, &work->flags);
+	if (put)
+		slow_work_put_ref(work);
+}
+EXPORT_SYMBOL(slow_work_cancel);
+
+/*
+ * Handle expiry of the delay timer, indicating that a delayed slow work item
+ * should now be queued if not cancelled
+ */
+static void delayed_slow_work_timer(unsigned long data)
+{
+	wait_queue_head_t *wfo_wq;
+	struct list_head *queue;
+	struct slow_work *work = (struct slow_work *) data;
+	unsigned long flags;
+	bool queued = false, put = false, first = false;
+
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) {
+		wfo_wq = &vslow_work_queue_waits_for_occupation;
+		queue = &vslow_work_queue;
+	} else {
+		wfo_wq = &slow_work_queue_waits_for_occupation;
+		queue = &slow_work_queue;
+	}
+
+	spin_lock_irqsave(&slow_work_queue_lock, flags);
+	if (likely(!test_bit(SLOW_WORK_CANCELLING, &work->flags))) {
+		clear_bit(SLOW_WORK_DELAYED, &work->flags);
+
+		if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
+			/* we discard the reference the timer was holding in
+			 * favour of the one the executor holds */
+			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
+			put = true;
+		} else {
+			slow_work_mark_time(work);
+			list_add_tail(&work->link, queue);
+			queued = true;
+			if (work->link.prev == queue)
+				first = true;
+		}
+	}
+
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	if (put)
+		slow_work_put_ref(work);
+	if (first)
+		wake_up(wfo_wq);
+	if (queued)
+		wake_up(&slow_work_thread_wq);
+}
+
+/**
+ * delayed_slow_work_enqueue - Schedule a delayed slow work item for processing
+ * @dwork: The delayed work item to queue
+ * @delay: When to start executing the work, in jiffies from now
+ *
+ * This is similar to slow_work_enqueue(), but it adds a delay before the work
+ * is actually queued for processing.
+ *
+ * The item can have delayed processing requested on it whilst it is being
+ * executed.  The delay will begin immediately, and if it expires before the
+ * item finishes executing, the item will be placed back on the queue when it
+ * has done executing.
+ */
+int delayed_slow_work_enqueue(struct delayed_slow_work *dwork,
+			      unsigned long delay)
+{
+	struct slow_work *work = &dwork->work;
+	unsigned long flags;
+	int ret;
+
+	if (delay == 0)
+		return slow_work_enqueue(&dwork->work);
+
+	BUG_ON(slow_work_user_count <= 0);
+	BUG_ON(!work);
+	BUG_ON(!work->ops);
+
+	if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+		return -ECANCELED;
+
+	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+		if (test_bit(SLOW_WORK_CANCELLING, &work->flags))
+			goto cancelled;
+
+		/* the timer holds a reference whilst it is pending */
+		ret = work->ops->get_ref(work);
+		if (ret < 0)
+			goto cant_get_ref;
+
+		if (test_and_set_bit(SLOW_WORK_DELAYED, &work->flags))
+			BUG();
+		dwork->timer.expires = jiffies + delay;
+		dwork->timer.data = (unsigned long) work;
+		dwork->timer.function = delayed_slow_work_timer;
+		add_timer(&dwork->timer);
+
+		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	}
+
+	return 0;
+
+cancelled:
+	ret = -ECANCELED;
+cant_get_ref:
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(delayed_slow_work_enqueue);
+
 /*
  * Schedule a cull of the thread pool at some time in the near future
  */
@@ -368,13 +714,23 @@ static inline bool slow_work_available(int vsmax)
  */
 static int slow_work_thread(void *_data)
 {
-	int vsmax;
+	int vsmax, id;
 
 	DEFINE_WAIT(wait);
 
 	set_freezable();
 	set_user_nice(current, -5);
 
+	/* allocate ourselves an ID */
+	spin_lock_irq(&slow_work_queue_lock);
+	id = find_first_zero_bit(slow_work_ids, SLOW_WORK_THREAD_LIMIT);
+	BUG_ON(id < 0 || id >= SLOW_WORK_THREAD_LIMIT);
+	__set_bit(id, slow_work_ids);
+	slow_work_set_thread_pid(id, current->pid);
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	sprintf(current->comm, "kslowd%03u", id);
+
 	for (;;) {
 		vsmax = vslow_work_proportion;
 		vsmax *= atomic_read(&slow_work_thread_count);
@@ -395,7 +751,7 @@ static int slow_work_thread(void *_data)
 		vsmax *= atomic_read(&slow_work_thread_count);
 		vsmax /= 100;
 
-		if (slow_work_available(vsmax) && slow_work_execute()) {
+		if (slow_work_available(vsmax) && slow_work_execute(id)) {
 			cond_resched();
 			if (list_empty(&slow_work_queue) &&
 			    list_empty(&vslow_work_queue) &&
@@ -412,6 +768,11 @@ static int slow_work_thread(void *_data)
 			break;
 	}
 
+	spin_lock_irq(&slow_work_queue_lock);
+	slow_work_set_thread_pid(id, 0);
+	__clear_bit(id, slow_work_ids);
+	spin_unlock_irq(&slow_work_queue_lock);
+
 	if (atomic_dec_and_test(&slow_work_thread_count))
 		complete_and_exit(&slow_work_last_thread_exited, 0);
 	return 0;
@@ -427,21 +788,6 @@ static void slow_work_cull_timeout(unsigned long data)
 }
 
 /*
- * Get a reference on slow work thread starter
- */
-static int slow_work_new_thread_get_ref(struct slow_work *work)
-{
-	return 0;
-}
-
-/*
- * Drop a reference on slow work thread starter
- */
-static void slow_work_new_thread_put_ref(struct slow_work *work)
-{
-}
-
-/*
  * Start a new slow work thread
  */
 static void slow_work_new_thread_execute(struct slow_work *work)
@@ -475,9 +821,11 @@ static void slow_work_new_thread_execute(struct slow_work *work)
 }
 
 static const struct slow_work_ops slow_work_new_thread_ops = {
-	.get_ref	= slow_work_new_thread_get_ref,
-	.put_ref	= slow_work_new_thread_put_ref,
+	.owner		= THIS_MODULE,
 	.execute	= slow_work_new_thread_execute,
+#ifdef CONFIG_SLOW_WORK_DEBUG
+	.desc		= slow_work_new_thread_desc,
+#endif
 };
 
 /*
@@ -546,12 +894,13 @@ static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
 
 /**
  * slow_work_register_user - Register a user of the facility
+ * @module: The module about to make use of the facility
  *
  * Register a user of the facility, starting up the initial threads if there
  * aren't any other users at this point.  This will return 0 if successful, or
  * an error if not.
  */
-int slow_work_register_user(void)
+int slow_work_register_user(struct module *module)
 {
 	struct task_struct *p;
 	int loop;
@@ -598,14 +947,81 @@ error:
 }
 EXPORT_SYMBOL(slow_work_register_user);
 
+/*
+ * wait for all outstanding items from the calling module to complete
+ * - note that more items may be queued whilst we're waiting
+ */
+static void slow_work_wait_for_items(struct module *module)
+{
+#ifdef CONFIG_MODULES
+	DECLARE_WAITQUEUE(myself, current);
+	struct slow_work *work;
+	int loop;
+
+	mutex_lock(&slow_work_unreg_sync_lock);
+	add_wait_queue(&slow_work_unreg_wq, &myself);
+
+	for (;;) {
+		spin_lock_irq(&slow_work_queue_lock);
+
+		/* first of all, we wait for the last queued item in each list
+		 * to be processed */
+		list_for_each_entry_reverse(work, &vslow_work_queue, link) {
+			if (work->owner == module) {
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				slow_work_unreg_work_item = work;
+				goto do_wait;
+			}
+		}
+		list_for_each_entry_reverse(work, &slow_work_queue, link) {
+			if (work->owner == module) {
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				slow_work_unreg_work_item = work;
+				goto do_wait;
+			}
+		}
+
+		/* then we wait for the items being processed to finish */
+		slow_work_unreg_module = module;
+		smp_mb();
+		for (loop = 0; loop < SLOW_WORK_THREAD_LIMIT; loop++) {
+			if (slow_work_thread_processing[loop] == module)
+				goto do_wait;
+		}
+		spin_unlock_irq(&slow_work_queue_lock);
+		break; /* okay, we're done */
+
+	do_wait:
+		spin_unlock_irq(&slow_work_queue_lock);
+		schedule();
+		slow_work_unreg_work_item = NULL;
+		slow_work_unreg_module = NULL;
+	}
+
+	remove_wait_queue(&slow_work_unreg_wq, &myself);
+	mutex_unlock(&slow_work_unreg_sync_lock);
+#endif /* CONFIG_MODULES */
+}
+
 /**
  * slow_work_unregister_user - Unregister a user of the facility
+ * @module: The module whose items should be cleared
  *
  * Unregister a user of the facility, killing all the threads if this was the
  * last one.
+ *
+ * This waits for all the work items belonging to the nominated module to go
+ * away before proceeding.
  */
-void slow_work_unregister_user(void)
+void slow_work_unregister_user(struct module *module)
 {
+	/* first of all, wait for all outstanding items from the calling module
+	 * to complete */
+	if (module)
+		slow_work_wait_for_items(module);
+
+	/* then we can actually go about shutting down the facility if need
+	 * be */
 	mutex_lock(&slow_work_user_lock);
 
 	BUG_ON(slow_work_user_count <= 0);
@@ -639,6 +1055,16 @@ static int __init init_slow_work(void)
 	if (slow_work_max_max_threads < nr_cpus * 2)
 		slow_work_max_max_threads = nr_cpus * 2;
 #endif
+#ifdef CONFIG_SLOW_WORK_DEBUG
+	{
+		struct dentry *dbdir;
+
+		dbdir = debugfs_create_dir("slow_work", NULL);
+		if (dbdir && !IS_ERR(dbdir))
+			debugfs_create_file("runqueue", S_IFREG | 0400, dbdir,
+					    NULL, &slow_work_runqueue_fops);
+	}
+#endif
 	return 0;
 }
 
diff --git a/kernel/slow-work.h b/kernel/slow-work.h
new file mode 100644
index 00000000000..321f3c59d73
--- /dev/null
+++ b/kernel/slow-work.h
@@ -0,0 +1,72 @@
+/* Slow work private definitions
+ *
+ * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define SLOW_WORK_CULL_TIMEOUT (5 * HZ)	/* cull threads 5s after running out of
+					 * things to do */
+#define SLOW_WORK_OOM_TIMEOUT (5 * HZ)	/* can't start new threads for 5s after
+					 * OOM */
+
+#define SLOW_WORK_THREAD_LIMIT	255	/* abs maximum number of slow-work threads */
+
+/*
+ * slow-work.c
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+extern struct slow_work *slow_work_execs[];
+extern pid_t slow_work_pids[];
+extern rwlock_t slow_work_execs_lock;
+#endif
+
+extern struct list_head slow_work_queue;
+extern struct list_head vslow_work_queue;
+extern spinlock_t slow_work_queue_lock;
+
+/*
+ * slow-work-debugfs.c
+ */
+#ifdef CONFIG_SLOW_WORK_DEBUG
+extern const struct file_operations slow_work_runqueue_fops;
+
+extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *);
+#endif
+
+/*
+ * Helper functions
+ */
+static inline void slow_work_set_thread_pid(int id, pid_t pid)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	slow_work_pids[id] = pid;
+#endif
+}
+
+static inline void slow_work_mark_time(struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	work->mark = CURRENT_TIME;
+#endif
+}
+
+static inline void slow_work_begin_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	slow_work_execs[id] = work;
+#endif
+}
+
+static inline void slow_work_end_exec(int id, struct slow_work *work)
+{
+#ifdef CONFIG_SLOW_WORK_PROC
+	write_lock(&slow_work_execs_lock);
+	slow_work_execs[id] = NULL;
+	write_unlock(&slow_work_execs_lock);
+#endif
+}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9c451a1930b..6dc4e5ef7a0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2222,15 +2222,15 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 		ret = ftrace_process_regex(parser->buffer,
 					   parser->idx, enable);
 		if (ret)
-			goto out;
+			goto out_unlock;
 
 		trace_parser_clear(parser);
 	}
 
 	ret = read;
-
+out_unlock:
 	mutex_unlock(&ftrace_regex_lock);
-out:
+
 	return ret;
 }
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3ffa502fb24..5dd017fea6f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1193,6 +1193,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
+	spin_lock_irq(&cpu_buffer->reader_lock);
 	rb_head_page_deactivate(cpu_buffer);
 
 	for (i = 0; i < nr_pages; i++) {
@@ -1207,6 +1208,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 		return;
 
 	rb_reset_cpu(cpu_buffer);
+	spin_unlock_irq(&cpu_buffer->reader_lock);
 
 	rb_check_pages(cpu_buffer);
 
diff --git a/kernel/user.c b/kernel/user.c
index 2c000e7132a..46d0165ca70 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -330,9 +330,9 @@ done:
  */
 static void free_user(struct user_struct *up, unsigned long flags)
 {
-	spin_unlock_irqrestore(&uidhash_lock, flags);
 	INIT_DELAYED_WORK(&up->work, cleanup_user_struct);
 	schedule_delayed_work(&up->work, msecs_to_jiffies(1000));
+	spin_unlock_irqrestore(&uidhash_lock, flags);
 }
 
 #else	/* CONFIG_USER_SCHED && CONFIG_SYSFS */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 12328147132..67e526b6ae8 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -692,31 +692,29 @@ int schedule_on_each_cpu(work_func_t func)
 	if (!works)
 		return -ENOMEM;
 
+	get_online_cpus();
+
 	/*
-	 * when running in keventd don't schedule a work item on itself.
-	 * Can just call directly because the work queue is already bound.
-	 * This also is faster.
-	 * Make this a generic parameter for other workqueues?
+	 * When running in keventd don't schedule a work item on
+	 * itself.  Can just call directly because the work queue is
+	 * already bound.  This also is faster.
 	 */
-	if (current_is_keventd()) {
+	if (current_is_keventd())
 		orig = raw_smp_processor_id();
-		INIT_WORK(per_cpu_ptr(works, orig), func);
-		func(per_cpu_ptr(works, orig));
-	}
 
-	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = per_cpu_ptr(works, cpu);
 
-		if (cpu == orig)
-			continue;
 		INIT_WORK(work, func);
-		schedule_work_on(cpu, work);
-	}
-	for_each_online_cpu(cpu) {
 		if (cpu != orig)
-			flush_work(per_cpu_ptr(works, cpu));
+			schedule_work_on(cpu, work);
 	}
+	if (orig >= 0)
+		func(per_cpu_ptr(works, orig));
+
+	for_each_online_cpu(cpu)
+		flush_work(per_cpu_ptr(works, cpu));
+
 	put_online_cpus();
 	free_percpu(works);
 	return 0;