From f11b00f3bd89c91c684d56b2082d1b0241ff20ae Mon Sep 17 00:00:00 2001
From: Adrian Bunk <bunk@kernel.org>
Date: Tue, 29 Apr 2008 00:58:56 -0700
Subject: fs/fs-writeback.c: make 2 functions static

Make the following needlessly global functions static:

- writeback_acquire()
- writeback_release()

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/backing-dev.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux/backing-dev.h')

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 48a62baace58..b66fa2bdfd9c 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -156,9 +156,7 @@ static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi)
 extern struct backing_dev_info default_backing_dev_info;
 void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page);
 
-int writeback_acquire(struct backing_dev_info *bdi);
 int writeback_in_progress(struct backing_dev_info *bdi);
-void writeback_release(struct backing_dev_info *bdi);
 
 static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
 {
-- 
cgit v1.3


From cf0ca9fe5dd9e3693d935757a7b2fc50fc576554 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 30 Apr 2008 00:54:32 -0700
Subject: mm: bdi: export BDI attributes in sysfs

Provide a place in sysfs (/sys/class/bdi) for the backing_dev_info object.
This allows us to see and set the various BDI specific variables.

In particular this properly exposes the read-ahead window for all relevant
users and /sys/block/<block>/queue/read_ahead_kb should be deprecated.

With patient help from Kay Sievers and Greg KH

[mszeredi@suse.cz]

 - split off NFS and FUSE changes into separate patches
 - document new sysfs attributes under Documentation/ABI
 - do bdi_class_init as a core_initcall, otherwise the "default" BDI
   won't be initialized
 - remove bdi_init_fmt macro, it's not used very much

[akpm@linux-foundation.org: fix ia64 warning]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Acked-by: Greg KH <greg@kroah.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/ABI/testing/sysfs-class-bdi |  46 ++++++++++++
 block/genhd.c                             |   8 ++
 include/linux/backing-dev.h               |   9 +++
 include/linux/writeback.h                 |   3 +
 lib/percpu_counter.c                      |   1 +
 mm/backing-dev.c                          | 119 ++++++++++++++++++++++++++++++
 mm/page-writeback.c                       |   2 +-
 mm/readahead.c                            |   8 +-
 8 files changed, 194 insertions(+), 2 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-class-bdi

(limited to 'include/linux/backing-dev.h')

diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
new file mode 100644
index 000000000000..b800cdda40bb
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -0,0 +1,46 @@
+What:		/sys/class/bdi/<bdi>/
+Date:		January 2008
+Contact:	Peter Zijlstra <a.p.zijlstra@chello.nl>
+Description:
+
+Provide a place in sysfs for the backing_dev_info object.
+This allows us to see and set the various BDI specific variables.
+
+The <bdi> identifier can be either of the following:
+
+MAJOR:MINOR
+
+	Device number for block devices, or value of st_dev on
+	non-block filesystems which provide their own BDI, such as NFS
+	and FUSE.
+
+default
+
+	The default backing dev, used for non-block device backed
+	filesystems which do not provide their own BDI.
+
+Files under /sys/class/bdi/<bdi>/
+---------------------------------
+
+read_ahead_kb (read-write)
+
+	Size of the read-ahead window in kilobytes
+
+reclaimable_kb (read-only)
+
+	Reclaimable (dirty or unstable) memory destined for writeback
+	to this device
+
+writeback_kb (read-only)
+
+	Memory currently under writeback to this device
+
+dirty_kb (read-only)
+
+	Global threshold for reclaimable + writeback memory
+
+bdi_dirty_kb (read-only)
+
+	Current threshold on this BDI for reclaimable + writeback
+	memory
+
diff --git a/block/genhd.c b/block/genhd.c
index 00da5219ee37..fda9c7a63c29 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -182,11 +182,17 @@ static int exact_lock(dev_t devt, void *data)
  */
 void add_disk(struct gendisk *disk)
 {
+	struct backing_dev_info *bdi;
+
 	disk->flags |= GENHD_FL_UP;
 	blk_register_region(MKDEV(disk->major, disk->first_minor),
 			    disk->minors, NULL, exact_match, exact_lock, disk);
 	register_disk(disk);
 	blk_register_queue(disk);
+
+	bdi = &disk->queue->backing_dev_info;
+	bdi_register_dev(bdi, MKDEV(disk->major, disk->first_minor));
+	sysfs_create_link(&disk->dev.kobj, &bdi->dev->kobj, "bdi");
 }
 
 EXPORT_SYMBOL(add_disk);
@@ -194,6 +200,8 @@ EXPORT_SYMBOL(del_gendisk);	/* in partitions/check.c */
 
 void unlink_gendisk(struct gendisk *disk)
 {
+	sysfs_remove_link(&disk->dev.kobj, "bdi");
+	bdi_unregister(&disk->queue->backing_dev_info);
 	blk_unregister_queue(disk);
 	blk_unregister_region(MKDEV(disk->major, disk->first_minor),
 			      disk->minors);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index b66fa2bdfd9c..6d513666d45c 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -11,9 +11,11 @@
 #include <linux/percpu_counter.h>
 #include <linux/log2.h>
 #include <linux/proportions.h>
+#include <linux/kernel.h>
 #include <asm/atomic.h>
 
 struct page;
+struct device;
 
 /*
  * Bits in backing_dev_info.state
@@ -48,11 +50,18 @@ struct backing_dev_info {
 
 	struct prop_local_percpu completions;
 	int dirty_exceeded;
+
+	struct device *dev;
 };
 
 int bdi_init(struct backing_dev_info *bdi);
 void bdi_destroy(struct backing_dev_info *bdi);
 
+int bdi_register(struct backing_dev_info *bdi, struct device *parent,
+		const char *fmt, ...);
+int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
+void bdi_unregister(struct backing_dev_info *bdi);
+
 static inline void __add_bdi_stat(struct backing_dev_info *bdi,
 		enum bdi_stat_item item, s64 amount)
 {
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index b7b3362f7717..f462439cc288 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -114,6 +114,9 @@ struct file;
 int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *,
 				      void __user *, size_t *, loff_t *);
 
+void get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
+		 struct backing_dev_info *bdi);
+
 void page_writeback_init(void);
 void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 					unsigned long nr_pages_dirtied);
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 393a0e915c23..119174494cb5 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -102,6 +102,7 @@ void percpu_counter_destroy(struct percpu_counter *fbc)
 		return;
 
 	free_percpu(fbc->counters);
+	fbc->counters = NULL;
 #ifdef CONFIG_HOTPLUG_CPU
 	mutex_lock(&percpu_counters_lock);
 	list_del(&fbc->list);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index e8644b1e5527..847eabe4824c 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -4,12 +4,129 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/module.h>
+#include <linux/writeback.h>
+#include <linux/device.h>
+
+
+static struct class *bdi_class;
+
+static ssize_t read_ahead_kb_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	char *end;
+	unsigned long read_ahead_kb;
+	ssize_t ret = -EINVAL;
+
+	read_ahead_kb = simple_strtoul(buf, &end, 10);
+	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
+		bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10);
+		ret = count;
+	}
+	return ret;
+}
+
+#define K(pages) ((pages) << (PAGE_SHIFT - 10))
+
+#define BDI_SHOW(name, expr)						\
+static ssize_t name##_show(struct device *dev,				\
+			   struct device_attribute *attr, char *page)	\
+{									\
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);		\
+									\
+	return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr);	\
+}
+
+BDI_SHOW(read_ahead_kb, K(bdi->ra_pages))
+
+BDI_SHOW(reclaimable_kb, K(bdi_stat(bdi, BDI_RECLAIMABLE)))
+BDI_SHOW(writeback_kb, K(bdi_stat(bdi, BDI_WRITEBACK)))
+
+static inline unsigned long get_dirty(struct backing_dev_info *bdi, int i)
+{
+	unsigned long thresh[3];
+
+	get_dirty_limits(&thresh[0], &thresh[1], &thresh[2], bdi);
+
+	return thresh[i];
+}
+
+BDI_SHOW(dirty_kb, K(get_dirty(bdi, 1)))
+BDI_SHOW(bdi_dirty_kb, K(get_dirty(bdi, 2)))
+
+#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
+
+static struct device_attribute bdi_dev_attrs[] = {
+	__ATTR_RW(read_ahead_kb),
+	__ATTR_RO(reclaimable_kb),
+	__ATTR_RO(writeback_kb),
+	__ATTR_RO(dirty_kb),
+	__ATTR_RO(bdi_dirty_kb),
+	__ATTR_NULL,
+};
+
+static __init int bdi_class_init(void)
+{
+	bdi_class = class_create(THIS_MODULE, "bdi");
+	bdi_class->dev_attrs = bdi_dev_attrs;
+	return 0;
+}
+
+core_initcall(bdi_class_init);
+
+int bdi_register(struct backing_dev_info *bdi, struct device *parent,
+		const char *fmt, ...)
+{
+	char *name;
+	va_list args;
+	int ret = 0;
+	struct device *dev;
+
+	va_start(args, fmt);
+	name = kvasprintf(GFP_KERNEL, fmt, args);
+	va_end(args);
+
+	if (!name)
+		return -ENOMEM;
+
+	dev = device_create(bdi_class, parent, MKDEV(0, 0), name);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto exit;
+	}
+
+	bdi->dev = dev;
+	dev_set_drvdata(bdi->dev, bdi);
+
+exit:
+	kfree(name);
+	return ret;
+}
+EXPORT_SYMBOL(bdi_register);
+
+int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
+{
+	return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev));
+}
+EXPORT_SYMBOL(bdi_register_dev);
+
+void bdi_unregister(struct backing_dev_info *bdi)
+{
+	if (bdi->dev) {
+		device_unregister(bdi->dev);
+		bdi->dev = NULL;
+	}
+}
+EXPORT_SYMBOL(bdi_unregister);
 
 int bdi_init(struct backing_dev_info *bdi)
 {
 	int i;
 	int err;
 
+	bdi->dev = NULL;
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
 		err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0);
 		if (err)
@@ -33,6 +150,8 @@ void bdi_destroy(struct backing_dev_info *bdi)
 {
 	int i;
 
+	bdi_unregister(bdi);
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5e00f1772c20..e5b6b1190a95 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -300,7 +300,7 @@ static unsigned long determine_dirtyable_memory(void)
 	return x + 1;	/* Ensure that we never return 0 */
 }
 
-static void
+void
 get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
 		 struct backing_dev_info *bdi)
 {
diff --git a/mm/readahead.c b/mm/readahead.c
index 8762e8988972..d8723a5f6496 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -235,7 +235,13 @@ unsigned long max_sane_readahead(unsigned long nr)
 
 static int __init readahead_init(void)
 {
-	return bdi_init(&default_backing_dev_info);
+	int err;
+
+	err = bdi_init(&default_backing_dev_info);
+	if (!err)
+		bdi_register(&default_backing_dev_info, NULL, "default");
+
+	return err;
 }
 subsys_initcall(readahead_init);
 
-- 
cgit v1.3


From 189d3c4a94ef19fca2a71a6a336e9fda900e25e7 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 30 Apr 2008 00:54:35 -0700
Subject: mm: bdi: allow setting a minimum for the bdi dirty limit

Under normal circumstances each device is given a part of the total write-back
cache that relates to its current avg writeout speed in relation to the other
devices.

min_ratio - allows one to assign a minimum portion of the write-back cache to
a particular device.  This is useful in situations where you might want to
provide a minimum QoS.  (One request for this feature came from flash based
storage people who wanted to avoid writing out at all costs - they of course
needed some pdflush hacks as well)

max_ratio - allows one to assign a maximum portion of the dirty limit to a
particular device.  This is useful in situations where you want to avoid one
device taking all or most of the write-back cache.  Eg.  an NFS mount that is
prone to get stuck, or a FUSE mount which you don't trust to play fair.

Add "min_ratio" to /sys/class/bdi.  This indicates the minimum percentage of
the global dirty threshold allocated to this bdi.

[mszeredi@suse.cz]

 - fix parsing in min_ratio_store()
 - document new sysfs attribute

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/ABI/testing/sysfs-class-bdi |  6 ++++++
 include/linux/backing-dev.h               |  4 ++++
 mm/backing-dev.c                          | 21 +++++++++++++++++++++
 mm/page-writeback.c                       | 27 ++++++++++++++++++++++++++-
 4 files changed, 57 insertions(+), 1 deletion(-)

(limited to 'include/linux/backing-dev.h')

diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
index b800cdda40bb..b9e8a9368dc6 100644
--- a/Documentation/ABI/testing/sysfs-class-bdi
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -44,3 +44,9 @@ bdi_dirty_kb (read-only)
 	Current threshold on this BDI for reclaimable + writeback
 	memory
 
+min_ratio (read-write)
+
+	Minimal percentage of global dirty threshold allocated to this
+	bdi.  If the value written to this file would make the the sum
+	of all min_ratio values exceed 100, then EINVAL is returned.
+	The default is zero
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 6d513666d45c..9a8965518d1d 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -51,6 +51,8 @@ struct backing_dev_info {
 	struct prop_local_percpu completions;
 	int dirty_exceeded;
 
+	unsigned int min_ratio;
+
 	struct device *dev;
 };
 
@@ -137,6 +139,8 @@ static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi)
 #endif
 }
 
+int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio);
+
 /*
  * Flags in backing_dev_info::capability
  * - The first two flags control whether dirty pages will contribute to the
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 847eabe4824c..4967fb176e53 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -55,6 +55,24 @@ static inline unsigned long get_dirty(struct backing_dev_info *bdi, int i)
 BDI_SHOW(dirty_kb, K(get_dirty(bdi, 1)))
 BDI_SHOW(bdi_dirty_kb, K(get_dirty(bdi, 2)))
 
+static ssize_t min_ratio_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	char *end;
+	unsigned int ratio;
+	ssize_t ret = -EINVAL;
+
+	ratio = simple_strtoul(buf, &end, 10);
+	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
+		ret = bdi_set_min_ratio(bdi, ratio);
+		if (!ret)
+			ret = count;
+	}
+	return ret;
+}
+BDI_SHOW(min_ratio, bdi->min_ratio)
+
 #define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
 
 static struct device_attribute bdi_dev_attrs[] = {
@@ -63,6 +81,7 @@ static struct device_attribute bdi_dev_attrs[] = {
 	__ATTR_RO(writeback_kb),
 	__ATTR_RO(dirty_kb),
 	__ATTR_RO(bdi_dirty_kb),
+	__ATTR_RW(min_ratio),
 	__ATTR_NULL,
 };
 
@@ -127,6 +146,8 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	bdi->dev = NULL;
 
+	bdi->min_ratio = 0;
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
 		err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0);
 		if (err)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e5b6b1190a95..4ac077f4269c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -242,6 +242,29 @@ static void task_dirty_limit(struct task_struct *tsk, long *pdirty)
 	*pdirty = dirty;
 }
 
+/*
+ *
+ */
+static DEFINE_SPINLOCK(bdi_lock);
+static unsigned int bdi_min_ratio;
+
+int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
+{
+	int ret = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bdi_lock, flags);
+	min_ratio -= bdi->min_ratio;
+	if (bdi_min_ratio + min_ratio < 100) {
+		bdi_min_ratio += min_ratio;
+		bdi->min_ratio += min_ratio;
+	} else
+		ret = -EINVAL;
+	spin_unlock_irqrestore(&bdi_lock, flags);
+
+	return ret;
+}
+
 /*
  * Work out the current dirty-memory clamping and background writeout
  * thresholds.
@@ -330,7 +353,7 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
 	*pdirty = dirty;
 
 	if (bdi) {
-		u64 bdi_dirty = dirty;
+		u64 bdi_dirty;
 		long numerator, denominator;
 
 		/*
@@ -338,8 +361,10 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
 		 */
 		bdi_writeout_fraction(bdi, &numerator, &denominator);
 
+		bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
 		bdi_dirty *= numerator;
 		do_div(bdi_dirty, denominator);
+		bdi_dirty += (dirty * bdi->min_ratio) / 100;
 
 		*pbdi_dirty = bdi_dirty;
 		clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
-- 
cgit v1.3


From a42dde04152750426cc620fd277e80fffae2f65a Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 30 Apr 2008 00:54:36 -0700
Subject: mm: bdi: allow setting a maximum for the bdi dirty limit

Add "max_ratio" to /sys/class/bdi.  This indicates the maximum percentage of
the global dirty threshold allocated to this bdi.

[mszeredi@suse.cz]

 - fix parsing in max_ratio_store().
 - export bdi_set_max_ratio() to modules
 - limit bdi_dirty with bdi->max_ratio
 - document new sysfs attribute

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/ABI/testing/sysfs-class-bdi |  9 ++++++-
 include/linux/backing-dev.h               |  2 ++
 include/linux/proportions.h               | 13 ++++++++++
 lib/proportions.c                         | 38 +++++++++++++++++++++++-----
 mm/backing-dev.c                          | 21 ++++++++++++++++
 mm/page-writeback.c                       | 41 ++++++++++++++++++++++++++-----
 6 files changed, 111 insertions(+), 13 deletions(-)

(limited to 'include/linux/backing-dev.h')

diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
index b9e8a9368dc6..c55e811ca180 100644
--- a/Documentation/ABI/testing/sysfs-class-bdi
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -49,4 +49,11 @@ min_ratio (read-write)
 	Minimal percentage of global dirty threshold allocated to this
 	bdi.  If the value written to this file would make the the sum
 	of all min_ratio values exceed 100, then EINVAL is returned.
-	The default is zero
+	If min_ratio would become larger than the current max_ratio,
+	then also EINVAL is returned.  The default is zero
+
+max_ratio (read-write)
+
+	Maximal percentage of global dirty threshold allocated to this
+	bdi.  If max_ratio would become smaller than the current
+	min_ratio, then EINVAL is returned.  The default is 100
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 9a8965518d1d..ad3271d1e90a 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -52,6 +52,7 @@ struct backing_dev_info {
 	int dirty_exceeded;
 
 	unsigned int min_ratio;
+	unsigned int max_ratio, max_prop_frac;
 
 	struct device *dev;
 };
@@ -140,6 +141,7 @@ static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi)
 }
 
 int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio);
+int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 
 /*
  * Flags in backing_dev_info::capability
diff --git a/include/linux/proportions.h b/include/linux/proportions.h
index 2c3b3cad92be..5afc1b23346d 100644
--- a/include/linux/proportions.h
+++ b/include/linux/proportions.h
@@ -77,6 +77,19 @@ void prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl)
 	local_irq_restore(flags);
 }
 
+/*
+ * Limit the time part in order to ensure there are some bits left for the
+ * cycle counter and fraction multiply.
+ */
+#define PROP_MAX_SHIFT (3*BITS_PER_LONG/4)
+
+#define PROP_FRAC_SHIFT		(BITS_PER_LONG - PROP_MAX_SHIFT - 1)
+#define PROP_FRAC_BASE		(1UL << PROP_FRAC_SHIFT)
+
+void __prop_inc_percpu_max(struct prop_descriptor *pd,
+			   struct prop_local_percpu *pl, long frac);
+
+
 /*
  * ----- SINGLE ------
  */
diff --git a/lib/proportions.c b/lib/proportions.c
index 9508d9a7af3e..4f387a643d72 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -73,12 +73,6 @@
 #include <linux/proportions.h>
 #include <linux/rcupdate.h>
 
-/*
- * Limit the time part in order to ensure there are some bits left for the
- * cycle counter.
- */
-#define PROP_MAX_SHIFT (3*BITS_PER_LONG/4)
-
 int prop_descriptor_init(struct prop_descriptor *pd, int shift)
 {
 	int err;
@@ -267,6 +261,38 @@ void __prop_inc_percpu(struct prop_descriptor *pd, struct prop_local_percpu *pl)
 	prop_put_global(pd, pg);
 }
 
+/*
+ * identical to __prop_inc_percpu, except that it limits this pl's fraction to
+ * @frac/PROP_FRAC_BASE by ignoring events when this limit has been exceeded.
+ */
+void __prop_inc_percpu_max(struct prop_descriptor *pd,
+			   struct prop_local_percpu *pl, long frac)
+{
+	struct prop_global *pg = prop_get_global(pd);
+
+	prop_norm_percpu(pg, pl);
+
+	if (unlikely(frac != PROP_FRAC_BASE)) {
+		unsigned long period_2 = 1UL << (pg->shift - 1);
+		unsigned long counter_mask = period_2 - 1;
+		unsigned long global_count;
+		long numerator, denominator;
+
+		numerator = percpu_counter_read_positive(&pl->events);
+		global_count = percpu_counter_read(&pg->events);
+		denominator = period_2 + (global_count & counter_mask);
+
+		if (numerator > ((denominator * frac) >> PROP_FRAC_SHIFT))
+			goto out_put;
+	}
+
+	percpu_counter_add(&pl->events, 1);
+	percpu_counter_add(&pg->events, 1);
+
+out_put:
+	prop_put_global(pd, pg);
+}
+
 /*
  * Obtain a fraction of this proportion
  *
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 4967fb176e53..08361b6aad50 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -73,6 +73,24 @@ static ssize_t min_ratio_store(struct device *dev,
 }
 BDI_SHOW(min_ratio, bdi->min_ratio)
 
+static ssize_t max_ratio_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	char *end;
+	unsigned int ratio;
+	ssize_t ret = -EINVAL;
+
+	ratio = simple_strtoul(buf, &end, 10);
+	if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
+		ret = bdi_set_max_ratio(bdi, ratio);
+		if (!ret)
+			ret = count;
+	}
+	return ret;
+}
+BDI_SHOW(max_ratio, bdi->max_ratio)
+
 #define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
 
 static struct device_attribute bdi_dev_attrs[] = {
@@ -82,6 +100,7 @@ static struct device_attribute bdi_dev_attrs[] = {
 	__ATTR_RO(dirty_kb),
 	__ATTR_RO(bdi_dirty_kb),
 	__ATTR_RW(min_ratio),
+	__ATTR_RW(max_ratio),
 	__ATTR_NULL,
 };
 
@@ -147,6 +166,8 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->dev = NULL;
 
 	bdi->min_ratio = 0;
+	bdi->max_ratio = 100;
+	bdi->max_prop_frac = PROP_FRAC_BASE;
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
 		err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4ac077f4269c..2a9942f5387c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -164,7 +164,8 @@ int dirty_ratio_handler(struct ctl_table *table, int write,
  */
 static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
 {
-	__prop_inc_percpu(&vm_completions, &bdi->completions);
+	__prop_inc_percpu_max(&vm_completions, &bdi->completions,
+			      bdi->max_prop_frac);
 }
 
 static inline void task_dirty_inc(struct task_struct *tsk)
@@ -254,16 +255,42 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
 	unsigned long flags;
 
 	spin_lock_irqsave(&bdi_lock, flags);
-	min_ratio -= bdi->min_ratio;
-	if (bdi_min_ratio + min_ratio < 100) {
-		bdi_min_ratio += min_ratio;
-		bdi->min_ratio += min_ratio;
-	} else
+	if (min_ratio > bdi->max_ratio) {
 		ret = -EINVAL;
+	} else {
+		min_ratio -= bdi->min_ratio;
+		if (bdi_min_ratio + min_ratio < 100) {
+			bdi_min_ratio += min_ratio;
+			bdi->min_ratio += min_ratio;
+		} else {
+			ret = -EINVAL;
+		}
+	}
+	spin_unlock_irqrestore(&bdi_lock, flags);
+
+	return ret;
+}
+
+int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	if (max_ratio > 100)
+		return -EINVAL;
+
+	spin_lock_irqsave(&bdi_lock, flags);
+	if (bdi->min_ratio > max_ratio) {
+		ret = -EINVAL;
+	} else {
+		bdi->max_ratio = max_ratio;
+		bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
+	}
 	spin_unlock_irqrestore(&bdi_lock, flags);
 
 	return ret;
 }
+EXPORT_SYMBOL(bdi_set_max_ratio);
 
 /*
  * Work out the current dirty-memory clamping and background writeout
@@ -365,6 +392,8 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
 		bdi_dirty *= numerator;
 		do_div(bdi_dirty, denominator);
 		bdi_dirty += (dirty * bdi->min_ratio) / 100;
+		if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
+			bdi_dirty = dirty * bdi->max_ratio / 100;
 
 		*pbdi_dirty = bdi_dirty;
 		clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
-- 
cgit v1.3


From 76f1418b485da2707531178e517bbb5cf06b3c76 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Wed, 30 Apr 2008 00:54:36 -0700
Subject: mm: bdi: move statistics to debugfs

Move BDI statistics to debugfs:

   /sys/kernel/debug/bdi/<bdi>/stats

Use postcore_initcall() to initialize the sysfs class and debugfs,
because debugfs is initialized in core_initcall().

Update descriptions in ABI documentation.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/ABI/testing/sysfs-class-bdi | 43 +++++---------
 include/linux/backing-dev.h               |  6 ++
 mm/backing-dev.c                          | 98 ++++++++++++++++++++++++-------
 3 files changed, 99 insertions(+), 48 deletions(-)

(limited to 'include/linux/backing-dev.h')

diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
index c55e811ca180..5ac1e01bbd48 100644
--- a/Documentation/ABI/testing/sysfs-class-bdi
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -3,8 +3,8 @@ Date:		January 2008
 Contact:	Peter Zijlstra <a.p.zijlstra@chello.nl>
 Description:
 
-Provide a place in sysfs for the backing_dev_info object.
-This allows us to see and set the various BDI specific variables.
+Provide a place in sysfs for the backing_dev_info object.  This allows
+setting and retrieving various BDI specific variables.
 
 The <bdi> identifier can be either of the following:
 
@@ -26,34 +26,21 @@ read_ahead_kb (read-write)
 
 	Size of the read-ahead window in kilobytes
 
-reclaimable_kb (read-only)
-
-	Reclaimable (dirty or unstable) memory destined for writeback
-	to this device
-
-writeback_kb (read-only)
-
-	Memory currently under writeback to this device
-
-dirty_kb (read-only)
-
-	Global threshold for reclaimable + writeback memory
-
-bdi_dirty_kb (read-only)
-
-	Current threshold on this BDI for reclaimable + writeback
-	memory
-
 min_ratio (read-write)
 
-	Minimal percentage of global dirty threshold allocated to this
-	bdi.  If the value written to this file would make the the sum
-	of all min_ratio values exceed 100, then EINVAL is returned.
-	If min_ratio would become larger than the current max_ratio,
-	then also EINVAL is returned.  The default is zero
+	Under normal circumstances each device is given a part of the
+	total write-back cache that relates to its current average
+	writeout speed in relation to the other devices.
+
+	The 'min_ratio' parameter allows assigning a minimum
+	percentage of the write-back cache to a particular device.
+	For example, this is useful for providing a minimum QoS.
 
 max_ratio (read-write)
 
-	Maximal percentage of global dirty threshold allocated to this
-	bdi.  If max_ratio would become smaller than the current
-	min_ratio, then EINVAL is returned.  The default is 100
+	Allows limiting a particular device to use not more than the
+	given percentage of the write-back cache.  This is useful in
+	situations where we want to avoid one device taking all or
+	most of the write-back cache.  For example in case of an NFS
+	mount that is prone to get stuck, or a FUSE mount which cannot
+	be trusted to play fair.
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index ad3271d1e90a..c49a2d045e11 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -16,6 +16,7 @@
 
 struct page;
 struct device;
+struct dentry;
 
 /*
  * Bits in backing_dev_info.state
@@ -55,6 +56,11 @@ struct backing_dev_info {
 	unsigned int max_ratio, max_prop_frac;
 
 	struct device *dev;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *debug_dir;
+	struct dentry *debug_stats;
+#endif
 };
 
 int bdi_init(struct backing_dev_info *bdi);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 08361b6aad50..7c4f9e097095 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -10,6 +10,80 @@
 
 static struct class *bdi_class;
 
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+static struct dentry *bdi_debug_root;
+
+static void bdi_debug_init(void)
+{
+	bdi_debug_root = debugfs_create_dir("bdi", NULL);
+}
+
+static int bdi_debug_stats_show(struct seq_file *m, void *v)
+{
+	struct backing_dev_info *bdi = m->private;
+	long background_thresh;
+	long dirty_thresh;
+	long bdi_thresh;
+
+	get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
+
+#define K(x) ((x) << (PAGE_SHIFT - 10))
+	seq_printf(m,
+		   "BdiWriteback:     %8lu kB\n"
+		   "BdiReclaimable:   %8lu kB\n"
+		   "BdiDirtyThresh:   %8lu kB\n"
+		   "DirtyThresh:      %8lu kB\n"
+		   "BackgroundThresh: %8lu kB\n",
+		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
+		   (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
+		   K(bdi_thresh),
+		   K(dirty_thresh),
+		   K(background_thresh));
+#undef K
+
+	return 0;
+}
+
+static int bdi_debug_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, bdi_debug_stats_show, inode->i_private);
+}
+
+static const struct file_operations bdi_debug_stats_fops = {
+	.open		= bdi_debug_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void bdi_debug_register(struct backing_dev_info *bdi, const char *name)
+{
+	bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root);
+	bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir,
+					       bdi, &bdi_debug_stats_fops);
+}
+
+static void bdi_debug_unregister(struct backing_dev_info *bdi)
+{
+	debugfs_remove(bdi->debug_stats);
+	debugfs_remove(bdi->debug_dir);
+}
+#else
+static inline void bdi_debug_init(void)
+{
+}
+static inline void bdi_debug_register(struct backing_dev_info *bdi,
+				      const char *name)
+{
+}
+static inline void bdi_debug_unregister(struct backing_dev_info *bdi)
+{
+}
+#endif
+
 static ssize_t read_ahead_kb_store(struct device *dev,
 				  struct device_attribute *attr,
 				  const char *buf, size_t count)
@@ -40,21 +114,6 @@ static ssize_t name##_show(struct device *dev,				\
 
 BDI_SHOW(read_ahead_kb, K(bdi->ra_pages))
 
-BDI_SHOW(reclaimable_kb, K(bdi_stat(bdi, BDI_RECLAIMABLE)))
-BDI_SHOW(writeback_kb, K(bdi_stat(bdi, BDI_WRITEBACK)))
-
-static inline unsigned long get_dirty(struct backing_dev_info *bdi, int i)
-{
-	unsigned long thresh[3];
-
-	get_dirty_limits(&thresh[0], &thresh[1], &thresh[2], bdi);
-
-	return thresh[i];
-}
-
-BDI_SHOW(dirty_kb, K(get_dirty(bdi, 1)))
-BDI_SHOW(bdi_dirty_kb, K(get_dirty(bdi, 2)))
-
 static ssize_t min_ratio_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
@@ -95,10 +154,6 @@ BDI_SHOW(max_ratio, bdi->max_ratio)
 
 static struct device_attribute bdi_dev_attrs[] = {
 	__ATTR_RW(read_ahead_kb),
-	__ATTR_RO(reclaimable_kb),
-	__ATTR_RO(writeback_kb),
-	__ATTR_RO(dirty_kb),
-	__ATTR_RO(bdi_dirty_kb),
 	__ATTR_RW(min_ratio),
 	__ATTR_RW(max_ratio),
 	__ATTR_NULL,
@@ -108,10 +163,11 @@ static __init int bdi_class_init(void)
 {
 	bdi_class = class_create(THIS_MODULE, "bdi");
 	bdi_class->dev_attrs = bdi_dev_attrs;
+	bdi_debug_init();
 	return 0;
 }
 
-core_initcall(bdi_class_init);
+postcore_initcall(bdi_class_init);
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...)
@@ -136,6 +192,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 
 	bdi->dev = dev;
 	dev_set_drvdata(bdi->dev, bdi);
+	bdi_debug_register(bdi, name);
 
 exit:
 	kfree(name);
@@ -152,6 +209,7 @@ EXPORT_SYMBOL(bdi_register_dev);
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		bdi_debug_unregister(bdi);
 		device_unregister(bdi->dev);
 		bdi->dev = NULL;
 	}
-- 
cgit v1.3


From e4ad08fe64afca4ef79ecc4c624e6e871688da0d Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Wed, 30 Apr 2008 00:54:37 -0700
Subject: mm: bdi: add separate writeback accounting capability

Add a new BDI capability flag: BDI_CAP_NO_ACCT_WB.  If this flag is
set, then don't update the per-bdi writeback stats from
test_set_page_writeback() and test_clear_page_writeback().

Misc cleanups:

 - convert bdi_cap_writeback_dirty() and friends to static inline functions
 - create a flag that includes all three dirty/writeback related flags,
   since almst all users will want to have them toghether

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/configfs/inode.c         |  2 +-
 fs/hugetlbfs/inode.c        |  2 +-
 fs/ocfs2/dlm/dlmfs.c        |  2 +-
 fs/ramfs/inode.c            |  2 +-
 fs/sysfs/inode.c            |  2 +-
 include/linux/backing-dev.h | 77 +++++++++++++++++++++++++++++++++------------
 kernel/cgroup.c             |  2 +-
 mm/page-writeback.c         |  4 +--
 mm/shmem.c                  |  2 +-
 mm/swap_state.c             |  2 +-
 10 files changed, 67 insertions(+), 30 deletions(-)

(limited to 'include/linux/backing-dev.h')

diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 4c1ebff778ee..b9a1d810346d 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -47,7 +47,7 @@ static const struct address_space_operations configfs_aops = {
 
 static struct backing_dev_info configfs_backing_dev_info = {
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
 static const struct inode_operations configfs_inode_operations ={
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 9783723e8ffe..aeabf80f81a5 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -45,7 +45,7 @@ static const struct inode_operations hugetlbfs_inode_operations;
 
 static struct backing_dev_info hugetlbfs_backing_dev_info = {
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
 int sysctl_hugetlb_shm_group;
diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c
index 61a000f8524c..e48aba698b77 100644
--- a/fs/ocfs2/dlm/dlmfs.c
+++ b/fs/ocfs2/dlm/dlmfs.c
@@ -327,7 +327,7 @@ clear_fields:
 
 static struct backing_dev_info dlmfs_backing_dev_info = {
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
 static struct inode *dlmfs_get_root_inode(struct super_block *sb)
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 8428d5b2711d..b13123424e49 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -44,7 +44,7 @@ static const struct inode_operations ramfs_dir_inode_operations;
 
 static struct backing_dev_info ramfs_backing_dev_info = {
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK |
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK |
 			  BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
 			  BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP,
 };
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index d9262f74f94e..f8b82e73b3bf 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -30,7 +30,7 @@ static const struct address_space_operations sysfs_aops = {
 
 static struct backing_dev_info sysfs_backing_dev_info = {
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
 static const struct inode_operations sysfs_inode_operations ={
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c49a2d045e11..13ab79d99268 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -12,6 +12,7 @@
 #include <linux/log2.h>
 #include <linux/proportions.h>
 #include <linux/kernel.h>
+#include <linux/fs.h>
 #include <asm/atomic.h>
 
 struct page;
@@ -151,22 +152,43 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 
 /*
  * Flags in backing_dev_info::capability
- * - The first two flags control whether dirty pages will contribute to the
- *   VM's accounting and whether writepages() should be called for dirty pages
- *   (something that would not, for example, be appropriate for ramfs)
- * - These flags let !MMU mmap() govern direct device mapping vs immediate
- *   copying more easily for MAP_PRIVATE, especially for ROM filesystems
+ *
+ * The first three flags control whether dirty pages will contribute to the
+ * VM's accounting and whether writepages() should be called for dirty pages
+ * (something that would not, for example, be appropriate for ramfs)
+ *
+ * WARNING: these flags are closely related and should not normally be
+ * used separately.  The BDI_CAP_NO_ACCT_AND_WRITEBACK combines these
+ * three flags into a single convenience macro.
+ *
+ * BDI_CAP_NO_ACCT_DIRTY:  Dirty pages shouldn't contribute to accounting
+ * BDI_CAP_NO_WRITEBACK:   Don't write pages back
+ * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
+ *
+ * These flags let !MMU mmap() govern direct device mapping vs immediate
+ * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
+ *
+ * BDI_CAP_MAP_COPY:       Copy can be mapped (MAP_PRIVATE)
+ * BDI_CAP_MAP_DIRECT:     Can be mapped directly (MAP_SHARED)
+ * BDI_CAP_READ_MAP:       Can be mapped for reading
+ * BDI_CAP_WRITE_MAP:      Can be mapped for writing
+ * BDI_CAP_EXEC_MAP:       Can be mapped for execution
  */
-#define BDI_CAP_NO_ACCT_DIRTY	0x00000001	/* Dirty pages shouldn't contribute to accounting */
-#define BDI_CAP_NO_WRITEBACK	0x00000002	/* Don't write pages back */
-#define BDI_CAP_MAP_COPY	0x00000004	/* Copy can be mapped (MAP_PRIVATE) */
-#define BDI_CAP_MAP_DIRECT	0x00000008	/* Can be mapped directly (MAP_SHARED) */
-#define BDI_CAP_READ_MAP	0x00000010	/* Can be mapped for reading */
-#define BDI_CAP_WRITE_MAP	0x00000020	/* Can be mapped for writing */
-#define BDI_CAP_EXEC_MAP	0x00000040	/* Can be mapped for execution */
+#define BDI_CAP_NO_ACCT_DIRTY	0x00000001
+#define BDI_CAP_NO_WRITEBACK	0x00000002
+#define BDI_CAP_MAP_COPY	0x00000004
+#define BDI_CAP_MAP_DIRECT	0x00000008
+#define BDI_CAP_READ_MAP	0x00000010
+#define BDI_CAP_WRITE_MAP	0x00000020
+#define BDI_CAP_EXEC_MAP	0x00000040
+#define BDI_CAP_NO_ACCT_WB	0x00000080
+
 #define BDI_CAP_VMFLAGS \
 	(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
 
+#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
+	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
+
 #if defined(VM_MAYREAD) && \
 	(BDI_CAP_READ_MAP != VM_MAYREAD || \
 	 BDI_CAP_WRITE_MAP != VM_MAYWRITE || \
@@ -206,17 +228,32 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int rw);
 void set_bdi_congested(struct backing_dev_info *bdi, int rw);
 long congestion_wait(int rw, long timeout);
 
-#define bdi_cap_writeback_dirty(bdi) \
-	(!((bdi)->capabilities & BDI_CAP_NO_WRITEBACK))
 
-#define bdi_cap_account_dirty(bdi) \
-	(!((bdi)->capabilities & BDI_CAP_NO_ACCT_DIRTY))
+static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
+{
+	return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK);
+}
+
+static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi)
+{
+	return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY);
+}
 
-#define mapping_cap_writeback_dirty(mapping) \
-	bdi_cap_writeback_dirty((mapping)->backing_dev_info)
+static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
+{
+	/* Paranoia: BDI_CAP_NO_WRITEBACK implies BDI_CAP_NO_ACCT_WB */
+	return !(bdi->capabilities & (BDI_CAP_NO_ACCT_WB |
+				      BDI_CAP_NO_WRITEBACK));
+}
 
-#define mapping_cap_account_dirty(mapping) \
-	bdi_cap_account_dirty((mapping)->backing_dev_info)
+static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
+{
+	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
+}
 
+static inline bool mapping_cap_account_dirty(struct address_space *mapping)
+{
+	return bdi_cap_account_dirty(mapping->backing_dev_info);
+}
 
 #endif		/* _LINUX_BACKING_DEV_H */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b9d467d83fc1..fbc6fc8949b4 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -575,7 +575,7 @@ static struct inode_operations cgroup_dir_inode_operations;
 static struct file_operations proc_cgroupstats_operations;
 
 static struct backing_dev_info cgroup_backing_dev_info = {
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
 static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2a9942f5387c..bbcb916190c9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1246,7 +1246,7 @@ int test_clear_page_writeback(struct page *page)
 			radix_tree_tag_clear(&mapping->page_tree,
 						page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
-			if (bdi_cap_writeback_dirty(bdi)) {
+			if (bdi_cap_account_writeback(bdi)) {
 				__dec_bdi_stat(bdi, BDI_WRITEBACK);
 				__bdi_writeout_inc(bdi);
 			}
@@ -1275,7 +1275,7 @@ int test_set_page_writeback(struct page *page)
 			radix_tree_tag_set(&mapping->page_tree,
 						page_index(page),
 						PAGECACHE_TAG_WRITEBACK);
-			if (bdi_cap_writeback_dirty(bdi))
+			if (bdi_cap_account_writeback(bdi))
 				__inc_bdi_stat(bdi, BDI_WRITEBACK);
 		}
 		if (!PageDirty(page))
diff --git a/mm/shmem.c b/mm/shmem.c
index e6d9298aa22a..e2a6ae1a44e9 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -201,7 +201,7 @@ static struct vm_operations_struct shmem_vm_ops;
 
 static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 	.unplug_io_fn	= default_unplug_io_fn,
 };
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 50757ee3f9f3..d8aadaf2a0ba 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -33,7 +33,7 @@ static const struct address_space_operations swap_aops = {
 };
 
 static struct backing_dev_info swap_backing_dev_info = {
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 	.unplug_io_fn	= swap_unplug_io_fn,
 };
 
-- 
cgit v1.3


From dd5656e59ca7b25fb60a22f9079905ed0da5ed0c Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Wed, 30 Apr 2008 00:54:37 -0700
Subject: mm: bdi: export bdi_writeout_inc()

Fuse needs this for writable mmap support.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/backing-dev.h |  2 ++
 mm/page-writeback.c         | 10 ++++++++++
 2 files changed, 12 insertions(+)

(limited to 'include/linux/backing-dev.h')

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 13ab79d99268..0a24d5550eb3 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -135,6 +135,8 @@ static inline s64 bdi_stat_sum(struct backing_dev_info *bdi,
 	return sum;
 }
 
+extern void bdi_writeout_inc(struct backing_dev_info *bdi);
+
 /*
  * maximal error of a stat counter.
  */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index bbcb916190c9..c90a1e8e479f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -168,6 +168,16 @@ static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
 			      bdi->max_prop_frac);
 }
 
+void bdi_writeout_inc(struct backing_dev_info *bdi)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__bdi_writeout_inc(bdi);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(bdi_writeout_inc);
+
 static inline void task_dirty_inc(struct task_struct *tsk)
 {
 	prop_inc_single(&vm_dirties, &tsk->dirties);
-- 
cgit v1.3