4 files changed, 333 insertions, 11 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index b8d4cd8ac0b..776ffed1556 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-$(CONFIG_SLOW_WORK_PROC) += slow-work-proc.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
diff --git a/kernel/slow-work-proc.c b/kernel/slow-work-proc.c
new file mode 100644
index 00000000000..3988032571f
--- /dev/null
+++ b/kernel/slow-work-proc.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 /proc
+ */
+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 "/proc/slow_work_rq" 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 f67e1daae93..b763bc2d267 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -16,13 +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 */
-
-#define SLOW_WORK_THREAD_LIMIT	255	/* abs maximum number of slow-work threads */
+#include <linux/proc_fs.h>
+#include "slow-work.h"
 
 static void slow_work_cull_timeout(unsigned long);
 static void slow_work_oom_timeout(unsigned long);
@@ -117,6 +112,15 @@ static DEFINE_MUTEX(slow_work_unreg_sync_lock);
 #endif
 
 /*
+ * Data for tracking currently executing items for indication through /proc
+ */
+#ifdef CONFIG_SLOW_WORK_PROC
+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.
@@ -124,9 +128,9 @@ static DEFINE_MUTEX(slow_work_unreg_sync_lock);
  * 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 thread controls.  A variable used to signal to the threads that they
@@ -182,7 +186,7 @@ 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(int id)
+static noinline bool slow_work_execute(int id)
 {
 #ifdef CONFIG_MODULES
 	struct module *module;
@@ -227,6 +231,10 @@ static bool slow_work_execute(int id)
 	if (work)
 		slow_work_thread_processing[id] = work->owner;
 #endif
+	if (work) {
+		slow_work_mark_time(work);
+		slow_work_begin_exec(id, work);
+	}
 
 	spin_unlock_irq(&slow_work_queue_lock);
 
@@ -247,6 +255,8 @@ static bool slow_work_execute(int id)
 	/* 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
@@ -285,6 +295,7 @@ 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
@@ -368,6 +379,7 @@ int slow_work_enqueue(struct slow_work *work)
 			ret = slow_work_get_ref(work);
 			if (ret < 0)
 				goto failed;
+			slow_work_mark_time(work);
 			if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
 				list_add_tail(&work->link, &vslow_work_queue);
 			else
@@ -489,6 +501,7 @@ static void delayed_slow_work_timer(unsigned long data)
 			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
 			put = true;
 		} else {
+			slow_work_mark_time(work);
 			if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
 				list_add_tail(&work->link, &vslow_work_queue);
 			else
@@ -627,6 +640,7 @@ static int slow_work_thread(void *_data)
 	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);
@@ -669,6 +683,7 @@ static int slow_work_thread(void *_data)
 	}
 
 	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);
 
@@ -722,6 +737,9 @@ static void slow_work_new_thread_execute(struct slow_work *work)
 static const struct slow_work_ops slow_work_new_thread_ops = {
 	.owner		= THIS_MODULE,
 	.execute	= slow_work_new_thread_execute,
+#ifdef CONFIG_SLOW_WORK_PROC
+	.desc		= slow_work_new_thread_desc,
+#endif
 };
 
 /*
@@ -949,6 +967,10 @@ 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_PROC
+	proc_create("slow_work_rq", S_IFREG | 0400, 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..3c2f007f3ad
--- /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_PROC
+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-proc.c
+ */
+#ifdef CONFIG_SLOW_WORK_PROC
+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
+}