From e088e4c9cdb618675874becb91b2fd581ee707e6 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Tue, 25 Nov 2008 13:29:47 -0500
Subject: [CPUFREQ] Disable sysfs ui for p4-clockmod.

p4-clockmod has a long history of abuse.   It pretends to be a CPU
frequency scaling driver, even though it doesn't actually change
the CPU frequency, but instead just modulates the frequency with
wait-states.
The biggest misconception is that when running at the lower 'frequency'
p4-clockmod is saving power.  This isn't the case, as workloads running
slower take longer to complete, preventing the CPU from entering deep C states.

However p4-clockmod does have a purpose.  It can prevent overheating.
Having it hooked up to the cpufreq interfaces is the wrong way to achieve
cooling however. It should instead be hooked up to ACPI.

This diff introduces a means for a cpufreq driver to register with the
cpufreq core, but not present a sysfs interface.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Dave Jones <davej@redhat.com>
---
 include/linux/cpufreq.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 1ee608fd7b77..484b3abf61bb 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -234,6 +234,7 @@ struct cpufreq_driver {
 	int	(*suspend)	(struct cpufreq_policy *policy, pm_message_t pmsg);
 	int	(*resume)	(struct cpufreq_policy *policy);
 	struct freq_attr	**attr;
+	bool			hide_interface;
 };
 
 /* flags */
-- 
cgit v1.2.3-70-g09d2


From ea319518ba3de282c13ae1cf4bf2215c5e03e67e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Fri, 26 Dec 2008 15:08:55 +0100
Subject: locking, percpu counters: introduce separate lock classes

Impact: fix lockdep false positives

Classify percpu_counter instances similar to regular lock objects --
that is, per instantiation site.

The networking code has increased its use of percpu_counters, which
leads to false positives if they are treated as a single class.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/percpu_counter.h | 14 ++++++++++----
 lib/percpu_counter.c           | 18 ++++--------------
 lib/proportions.c              |  6 +++---
 mm/backing-dev.c               |  2 +-
 4 files changed, 18 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 9007ccdfc112..96bdde36599f 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -30,8 +30,16 @@ struct percpu_counter {
 #define FBC_BATCH	(NR_CPUS*4)
 #endif
 
-int percpu_counter_init(struct percpu_counter *fbc, s64 amount);
-int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount);
+int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+			  struct lock_class_key *key);
+
+#define percpu_counter_init(fbc, value)					\
+	({								\
+		static struct lock_class_key __key;			\
+									\
+		__percpu_counter_init(fbc, value, &__key);		\
+	})
+
 void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
@@ -85,8 +93,6 @@ static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount)
 	return 0;
 }
 
-#define percpu_counter_init_irq percpu_counter_init
-
 static inline void percpu_counter_destroy(struct percpu_counter *fbc)
 {
 }
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index a8663890a88c..c7fe2e4e8ed1 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -71,11 +71,11 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 }
 EXPORT_SYMBOL(__percpu_counter_sum);
 
-static struct lock_class_key percpu_counter_irqsafe;
-
-int percpu_counter_init(struct percpu_counter *fbc, s64 amount)
+int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+			  struct lock_class_key *key)
 {
 	spin_lock_init(&fbc->lock);
+	lockdep_set_class(&fbc->lock, key);
 	fbc->count = amount;
 	fbc->counters = alloc_percpu(s32);
 	if (!fbc->counters)
@@ -87,17 +87,7 @@ int percpu_counter_init(struct percpu_counter *fbc, s64 amount)
 #endif
 	return 0;
 }
-EXPORT_SYMBOL(percpu_counter_init);
-
-int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount)
-{
-	int err;
-
-	err = percpu_counter_init(fbc, amount);
-	if (!err)
-		lockdep_set_class(&fbc->lock, &percpu_counter_irqsafe);
-	return err;
-}
+EXPORT_SYMBOL(__percpu_counter_init);
 
 void percpu_counter_destroy(struct percpu_counter *fbc)
 {
diff --git a/lib/proportions.c b/lib/proportions.c
index 4f387a643d72..7367f2b727d0 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -83,11 +83,11 @@ int prop_descriptor_init(struct prop_descriptor *pd, int shift)
 	pd->index = 0;
 	pd->pg[0].shift = shift;
 	mutex_init(&pd->mutex);
-	err = percpu_counter_init_irq(&pd->pg[0].events, 0);
+	err = percpu_counter_init(&pd->pg[0].events, 0);
 	if (err)
 		goto out;
 
-	err = percpu_counter_init_irq(&pd->pg[1].events, 0);
+	err = percpu_counter_init(&pd->pg[1].events, 0);
 	if (err)
 		percpu_counter_destroy(&pd->pg[0].events);
 
@@ -191,7 +191,7 @@ int prop_local_init_percpu(struct prop_local_percpu *pl)
 	spin_lock_init(&pl->lock);
 	pl->shift = 0;
 	pl->period = 0;
-	return percpu_counter_init_irq(&pl->events, 0);
+	return percpu_counter_init(&pl->events, 0);
 }
 
 void prop_local_destroy_percpu(struct prop_local_percpu *pl)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f2e574dbc300..f3b125857827 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -220,7 +220,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	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);
+		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
 		if (err)
 			goto err;
 	}
-- 
cgit v1.2.3-70-g09d2


From 9188e79ec3fd43a0a605274324aecfb731baa88b Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Wed, 12 Nov 2008 16:14:08 +0100
Subject: HID: add phys and name ioctls to hidraw

The hiddev interface provides ioctl() calls which can be used
to obtain phys and raw name of the underlying device.

Add the corresponding support also into hidraw.

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hidraw.c   | 28 ++++++++++++++++++++++++++++
 include/linux/hidraw.h |  2 ++
 2 files changed, 30 insertions(+)

(limited to 'include')

diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 7685ae6808c4..975edd88a3db 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -265,6 +265,34 @@ static long hidraw_ioctl(struct file *file, unsigned int cmd,
 				break;
 			}
 		default:
+			{
+				struct hid_device *hid = dev->hid;
+				if (_IOC_TYPE(cmd) != 'H' || _IOC_DIR(cmd) != _IOC_READ)
+					return -EINVAL;
+
+				if (_IOC_NR(cmd) == _IOC_NR(HIDIOCGRAWNAME(0))) {
+					int len;
+					if (!hid->name)
+						return 0;
+					len = strlen(hid->name) + 1;
+					if (len > _IOC_SIZE(cmd))
+						len = _IOC_SIZE(cmd);
+					return copy_to_user(user_arg, hid->name, len) ?
+						-EFAULT : len;
+				}
+
+				if (_IOC_NR(cmd) == _IOC_NR(HIDIOCGRAWPHYS(0))) {
+					int len;
+					if (!hid->phys)
+						return 0;
+					len = strlen(hid->phys) + 1;
+					if (len > _IOC_SIZE(cmd))
+						len = _IOC_SIZE(cmd);
+					return copy_to_user(user_arg, hid->phys, len) ?
+						-EFAULT : len;
+				}
+                }
+
 			ret = -ENOTTY;
 	}
 	unlock_kernel();
diff --git a/include/linux/hidraw.h b/include/linux/hidraw.h
index dbb5c8c374f0..dd8d69269176 100644
--- a/include/linux/hidraw.h
+++ b/include/linux/hidraw.h
@@ -33,6 +33,8 @@ struct hidraw_devinfo {
 #define HIDIOCGRDESCSIZE	_IOR('H', 0x01, int)
 #define HIDIOCGRDESC		_IOR('H', 0x02, struct hidraw_report_descriptor)
 #define HIDIOCGRAWINFO		_IOR('H', 0x03, struct hidraw_devinfo)
+#define HIDIOCGRAWNAME(len)     _IOC(_IOC_READ, 'H', 0x04, len)
+#define HIDIOCGRAWPHYS(len)     _IOC(_IOC_READ, 'H', 0x05, len)
 
 #define HIDRAW_FIRST_MINOR 0
 #define HIDRAW_MAX_DEVICES 64
-- 
cgit v1.2.3-70-g09d2


From 0ed94b334265b6ee3e3336b4fedacfa9cb2ccaba Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jirislaby@gmail.com>
Date: Mon, 24 Nov 2008 16:20:07 +0100
Subject: HID: move usbhid flags to usbhid.h

Move usbhid specific flags from global hid.h into local usbhid.h.

Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/usbhid/usbhid.h | 10 ++++++++++
 include/linux/hid.h         |  9 ---------
 2 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h
index 332abcdf9956..9eb30564be9c 100644
--- a/drivers/hid/usbhid/usbhid.h
+++ b/drivers/hid/usbhid/usbhid.h
@@ -40,6 +40,16 @@ int usbhid_open(struct hid_device *hid);
 void usbhid_init_reports(struct hid_device *hid);
 void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir);
 
+/* iofl flags */
+#define HID_CTRL_RUNNING	1
+#define HID_OUT_RUNNING		2
+#define HID_IN_RUNNING		3
+#define HID_RESET_PENDING	4
+#define HID_SUSPENDED		5
+#define HID_CLEAR_HALT		6
+#define HID_DISCONNECTED	7
+#define HID_STARTED		8
+
 /*
  * USB-specific HID struct, to be pointed to
  * from struct hid_device->driver_data
diff --git a/include/linux/hid.h b/include/linux/hid.h
index e5780f8c934a..2c20f20283b2 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -403,15 +403,6 @@ struct hid_output_fifo {
 #define HID_STAT_ADDED		1
 #define HID_STAT_PARSED		2
 
-#define HID_CTRL_RUNNING	1
-#define HID_OUT_RUNNING		2
-#define HID_IN_RUNNING		3
-#define HID_RESET_PENDING	4
-#define HID_SUSPENDED		5
-#define HID_CLEAR_HALT		6
-#define HID_DISCONNECTED	7
-#define HID_STARTED		8
-
 struct hid_input {
 	struct list_head list;
 	struct hid_report *report;
-- 
cgit v1.2.3-70-g09d2


From 3a6f82f7a22cf19687f556997c6978b31c109360 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jirislaby@gmail.com>
Date: Mon, 24 Nov 2008 16:20:09 +0100
Subject: HID: add dynids facility

Allow adding new devices to the hid drivers on the fly without
a need of kernel recompilation.

Now, one can test a driver e.g. by:
echo 0003:045E:00F0.0003 > ../generic-usb/unbind
echo 0003 045E 00F0 > new_id
from some driver subdir.

Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/hid.h    |   5 +++
 2 files changed, 103 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 344f8fdb2824..34cc3b0d01f6 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1304,12 +1304,92 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ }
 };
 
+struct hid_dynid {
+	struct list_head list;
+	struct hid_device_id id;
+};
+
+/**
+ * store_new_id - add a new HID device ID to this driver and re-probe devices
+ * @driver: target device driver
+ * @buf: buffer for scanning device ID data
+ * @count: input size
+ *
+ * Adds a new dynamic hid device ID to this driver,
+ * and causes the driver to probe for all devices again.
+ */
+static ssize_t store_new_id(struct device_driver *drv, const char *buf,
+		size_t count)
+{
+	struct hid_driver *hdrv = container_of(drv, struct hid_driver, driver);
+	struct hid_dynid *dynid;
+	__u32 bus, vendor, product;
+	unsigned long driver_data = 0;
+	int ret;
+
+	ret = sscanf(buf, "%x %x %x %lx",
+			&bus, &vendor, &product, &driver_data);
+	if (ret < 3)
+		return -EINVAL;
+
+	dynid = kzalloc(sizeof(*dynid), GFP_KERNEL);
+	if (!dynid)
+		return -ENOMEM;
+
+	dynid->id.bus = bus;
+	dynid->id.vendor = vendor;
+	dynid->id.product = product;
+	dynid->id.driver_data = driver_data;
+
+	spin_lock(&hdrv->dyn_lock);
+	list_add_tail(&dynid->list, &hdrv->dyn_list);
+	spin_unlock(&hdrv->dyn_lock);
+
+	ret = 0;
+	if (get_driver(&hdrv->driver)) {
+		ret = driver_attach(&hdrv->driver);
+		put_driver(&hdrv->driver);
+	}
+
+	return ret ? : count;
+}
+static DRIVER_ATTR(new_id, S_IWUSR, NULL, store_new_id);
+
+static void hid_free_dynids(struct hid_driver *hdrv)
+{
+	struct hid_dynid *dynid, *n;
+
+	spin_lock(&hdrv->dyn_lock);
+	list_for_each_entry_safe(dynid, n, &hdrv->dyn_list, list) {
+		list_del(&dynid->list);
+		kfree(dynid);
+	}
+	spin_unlock(&hdrv->dyn_lock);
+}
+
+static const struct hid_device_id *hid_match_device(struct hid_device *hdev,
+		struct hid_driver *hdrv)
+{
+	struct hid_dynid *dynid;
+
+	spin_lock(&hdrv->dyn_lock);
+	list_for_each_entry(dynid, &hdrv->dyn_list, list) {
+		if (hid_match_one_id(hdev, &dynid->id)) {
+			spin_unlock(&hdrv->dyn_lock);
+			return &dynid->id;
+		}
+	}
+	spin_unlock(&hdrv->dyn_lock);
+
+	return hid_match_id(hdev, hdrv->id_table);
+}
+
 static int hid_bus_match(struct device *dev, struct device_driver *drv)
 {
 	struct hid_driver *hdrv = container_of(drv, struct hid_driver, driver);
 	struct hid_device *hdev = container_of(dev, struct hid_device, dev);
 
-	if (!hid_match_id(hdev, hdrv->id_table))
+	if (!hid_match_device(hdev, hdrv))
 		return 0;
 
 	/* generic wants all non-blacklisted */
@@ -1328,7 +1408,7 @@ static int hid_device_probe(struct device *dev)
 	int ret = 0;
 
 	if (!hdev->driver) {
-		id = hid_match_id(hdev, hdrv->id_table);
+		id = hid_match_device(hdev, hdrv);
 		if (id == NULL)
 			return -ENODEV;
 
@@ -1695,18 +1775,33 @@ EXPORT_SYMBOL_GPL(hid_destroy_device);
 int __hid_register_driver(struct hid_driver *hdrv, struct module *owner,
 		const char *mod_name)
 {
+	int ret;
+
 	hdrv->driver.name = hdrv->name;
 	hdrv->driver.bus = &hid_bus_type;
 	hdrv->driver.owner = owner;
 	hdrv->driver.mod_name = mod_name;
 
-	return driver_register(&hdrv->driver);
+	INIT_LIST_HEAD(&hdrv->dyn_list);
+	spin_lock_init(&hdrv->dyn_lock);
+
+	ret = driver_register(&hdrv->driver);
+	if (ret)
+		return ret;
+
+	ret = driver_create_file(&hdrv->driver, &driver_attr_new_id);
+	if (ret)
+		driver_unregister(&hdrv->driver);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(__hid_register_driver);
 
 void hid_unregister_driver(struct hid_driver *hdrv)
 {
+	driver_remove_file(&hdrv->driver, &driver_attr_new_id);
 	driver_unregister(&hdrv->driver);
+	hid_free_dynids(hdrv);
 }
 EXPORT_SYMBOL_GPL(hid_unregister_driver);
 
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 2c20f20283b2..215035bbb288 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -531,6 +531,8 @@ struct hid_usage_id {
  * @name: driver name (e.g. "Footech_bar-wheel")
  * @id_table: which devices is this driver for (must be non-NULL for probe
  * 	      to be called)
+ * @dyn_list: list of dynamically added device ids
+ * @dyn_lock: lock protecting @dyn_list
  * @probe: new device inserted
  * @remove: device removed (NULL if not a hot-plug capable driver)
  * @report_table: on which reports to call raw_event (NULL means all)
@@ -558,6 +560,9 @@ struct hid_driver {
 	char *name;
 	const struct hid_device_id *id_table;
 
+	struct list_head dyn_list;
+	spinlock_t dyn_lock;
+
 	int (*probe)(struct hid_device *dev, const struct hid_device_id *id);
 	void (*remove)(struct hid_device *dev);
 
-- 
cgit v1.2.3-70-g09d2


From 725cf0f47dbb02e0482f081828cff73f55479b79 Mon Sep 17 00:00:00 2001
From: Hannes Eder <hannes@hanneseder.net>
Date: Tue, 16 Dec 2008 14:20:23 +0100
Subject: HID: avoid sparse warning in HID_COMPAT_LOAD_DRIVER

Impact: include a prototype for the exported function in the macro

Fix about 20 of this warnings:

  drivers/hid/hid-a4tech.c:162:1: warning: symbol 'hid_compat_a4tech' was not declared. Should it be static?

Signed-off-by: Hannes Eder <hannes@hanneseder.net>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/hid.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/hid.h b/include/linux/hid.h
index 215035bbb288..81aa84d60c6b 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -793,6 +793,8 @@ dbg_hid(const char *fmt, ...)
 
 #ifdef CONFIG_HID_COMPAT
 #define HID_COMPAT_LOAD_DRIVER(name)	\
+/* prototype to avoid sparse warning */	\
+extern void hid_compat_##name(void);	\
 void hid_compat_##name(void) { }	\
 EXPORT_SYMBOL(hid_compat_##name)
 #else
-- 
cgit v1.2.3-70-g09d2


From 0c8a601678960fbcc1c1185a283d6d107575810b Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Sat, 8 Nov 2008 01:10:16 +0100
Subject: mfd: Add WM8350 revision H support

No other software changes are required.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/wm8350-core.c       | 7 ++++++-
 include/linux/mfd/wm8350/core.h | 1 +
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index d63a530c4fe8..c013afde260d 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -1202,9 +1202,14 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 			dev_info(wm8350->dev, "Found Rev G device\n");
 			wm8350->rev = WM8350_REV_G;
 			break;
+		case WM8350_REV_H:
+			dev_info(wm8350->dev, "Found Rev H device\n");
+			wm8350->rev = WM8350_REV_H;
+			break;
 		default:
 			/* For safety we refuse to run on unknown hardware */
-			dev_info(wm8350->dev, "Found unknown rev\n");
+			dev_info(wm8350->dev, "Found unknown rev %x\n",
+				 (id2 & WM8350_CHIP_REV_MASK) >> 12);
 			ret = -ENODEV;
 			goto err;
 		}
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index 6ebf97f2a475..9490ec175d5a 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -536,6 +536,7 @@
 #define WM8350_REV_E				0x4
 #define WM8350_REV_F				0x5
 #define WM8350_REV_G				0x6
+#define WM8350_REV_H				0x7
 
 #define WM8350_NUM_IRQ				63
 
-- 
cgit v1.2.3-70-g09d2


From 67488526349d043372d141c054f4dc6313780b3c Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Sat, 8 Nov 2008 01:10:21 +0100
Subject: mfd: Add AUXADC support for WM8350

The auxiliary ADC in the WM8350 is shared between several subdevices
so access to it needs to be arbitrated by the core driver.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/wm8350-core.c             | 51 ++++++++++++++++++++++++++++++++++-
 include/linux/mfd/wm8350/comparator.h |  8 ++++++
 include/linux/mfd/wm8350/core.h       |  2 ++
 3 files changed, 60 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index c013afde260d..60439bd3984d 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -63,7 +63,6 @@
  */
 static DEFINE_MUTEX(io_mutex);
 static DEFINE_MUTEX(reg_lock_mutex);
-static DEFINE_MUTEX(auxadc_mutex);
 
 /* Perform a physical read from the device.
  */
@@ -1082,6 +1081,55 @@ int wm8350_unmask_irq(struct wm8350 *wm8350, int irq)
 }
 EXPORT_SYMBOL_GPL(wm8350_unmask_irq);
 
+int wm8350_read_auxadc(struct wm8350 *wm8350, int channel, int scale, int vref)
+{
+	u16 reg, result = 0;
+	int tries = 5;
+
+	if (channel < WM8350_AUXADC_AUX1 || channel > WM8350_AUXADC_TEMP)
+		return -EINVAL;
+	if (channel >= WM8350_AUXADC_USB && channel <= WM8350_AUXADC_TEMP
+	    && (scale != 0 || vref != 0))
+		return -EINVAL;
+
+	mutex_lock(&wm8350->auxadc_mutex);
+
+	/* Turn on the ADC */
+	reg = wm8350_reg_read(wm8350, WM8350_POWER_MGMT_5);
+	wm8350_reg_write(wm8350, WM8350_POWER_MGMT_5, reg | WM8350_AUXADC_ENA);
+
+	if (scale || vref) {
+		reg = scale << 13;
+		reg |= vref << 12;
+		wm8350_reg_write(wm8350, WM8350_AUX1_READBACK + channel, reg);
+	}
+
+	reg = wm8350_reg_read(wm8350, WM8350_DIGITISER_CONTROL_1);
+	reg |= 1 << channel | WM8350_AUXADC_POLL;
+	wm8350_reg_write(wm8350, WM8350_DIGITISER_CONTROL_1, reg);
+
+	do {
+		schedule_timeout_interruptible(1);
+		reg = wm8350_reg_read(wm8350, WM8350_DIGITISER_CONTROL_1);
+	} while (tries-- && (reg & WM8350_AUXADC_POLL));
+
+	if (!tries)
+		dev_err(wm8350->dev, "adc chn %d read timeout\n", channel);
+	else
+		result = wm8350_reg_read(wm8350,
+					 WM8350_AUX1_READBACK + channel);
+
+	/* Turn off the ADC */
+	reg = wm8350_reg_read(wm8350, WM8350_POWER_MGMT_5);
+	wm8350_reg_write(wm8350, WM8350_POWER_MGMT_5,
+			 reg & ~WM8350_AUXADC_ENA);
+
+	mutex_unlock(&wm8350->auxadc_mutex);
+
+	return result & WM8350_AUXADC_DATA1_MASK;
+}
+EXPORT_SYMBOL_GPL(wm8350_read_auxadc);
+
 /*
  * Cache is always host endian.
  */
@@ -1239,6 +1287,7 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 		}
 	}
 
+	mutex_init(&wm8350->auxadc_mutex);
 	mutex_init(&wm8350->irq_mutex);
 	INIT_WORK(&wm8350->irq_work, wm8350_irq_worker);
 	if (irq) {
diff --git a/include/linux/mfd/wm8350/comparator.h b/include/linux/mfd/wm8350/comparator.h
index 053788649452..54bc5d0fd502 100644
--- a/include/linux/mfd/wm8350/comparator.h
+++ b/include/linux/mfd/wm8350/comparator.h
@@ -164,4 +164,12 @@
 #define WM8350_AUXADC_BATT			6
 #define WM8350_AUXADC_TEMP			7
 
+struct wm8350;
+
+/*
+ * AUX ADC Readback
+ */
+int wm8350_read_auxadc(struct wm8350 *wm8350, int channel, int scale,
+		       int vref);
+
 #endif
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index 9490ec175d5a..cc190055b9c4 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -573,6 +573,8 @@ struct wm8350 {
 			 void *src);
 	u16 *reg_cache;
 
+	struct mutex auxadc_mutex;
+
 	/* Interrupt handling */
 	struct work_struct irq_work;
 	struct mutex irq_mutex; /* IRQ table mutex */
-- 
cgit v1.2.3-70-g09d2


From 3fba19ec1ae5b460c73a7f32efed8d3b3300b246 Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Sat, 8 Nov 2008 01:13:16 +0100
Subject: mfd: allow reading entire register banks on twl4030

Minor change to the TWL4030 utility interface:  support reads
of all 256 bytes in each register bank (vs just 255).  This
can help when debugging, but is otherwise a NOP.

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/twl4030-core.c  | 4 ++--
 include/linux/i2c/twl4030.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/twl4030-core.c b/drivers/mfd/twl4030-core.c
index dd843c4fbcc7..ef9a971e3ead 100644
--- a/drivers/mfd/twl4030-core.c
+++ b/drivers/mfd/twl4030-core.c
@@ -225,7 +225,7 @@ static struct twl4030mapping twl4030_map[TWL4030_MODULE_LAST + 1] = {
  *
  * Returns the result of operation - 0 is success
  */
-int twl4030_i2c_write(u8 mod_no, u8 *value, u8 reg, u8 num_bytes)
+int twl4030_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes)
 {
 	int ret;
 	int sid;
@@ -274,7 +274,7 @@ EXPORT_SYMBOL(twl4030_i2c_write);
  *
  * Returns result of operation - num_bytes is success else failure.
  */
-int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, u8 num_bytes)
+int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes)
 {
 	int ret;
 	u8 val;
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
index fb604dcd38f1..ae25c907b7cf 100644
--- a/include/linux/i2c/twl4030.h
+++ b/include/linux/i2c/twl4030.h
@@ -78,8 +78,8 @@ int twl4030_i2c_read_u8(u8 mod_no, u8 *val, u8 reg);
  * IMPORTANT:  For twl4030_i2c_write(), allocate num_bytes + 1
  * for the value, and populate your data starting at offset 1.
  */
-int twl4030_i2c_write(u8 mod_no, u8 *value, u8 reg, u8 num_bytes);
-int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, u8 num_bytes);
+int twl4030_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes);
+int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes);
 
 /*----------------------------------------------------------------------*/
 
-- 
cgit v1.2.3-70-g09d2


From 14431aa0c5a443d13d24e6f865a8838f97dab973 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Sun, 16 Nov 2008 20:16:47 +0100
Subject: power_supply: Add support for WM8350 PMU

This patch adds support for the PMU provided by the WM8350 which
implements battery, line and USB supplies including a battery charger.
The hardware functions largely autonomously, with minimal software
control required to initiate fast charging.

Support for configuration of the USB supply is not yet implemented.
This means that the hardware will remain in the mode configured at
startup, by default limiting the current drawn from USB to 100mA.

This driver was originally written by Liam Girdwood with subsequent
updates for submission by Mark Brown.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Anton Vorontsov <cbouatmailru@gmail.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/power/Kconfig             |   7 +
 drivers/power/Makefile            |   1 +
 drivers/power/wm8350_power.c      | 515 ++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/wm8350/core.h   |  26 ++
 include/linux/mfd/wm8350/supply.h |  23 +-
 5 files changed, 571 insertions(+), 1 deletion(-)
 create mode 100644 drivers/power/wm8350_power.c

(limited to 'include')

diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 8e0c2b47803c..52f86767f72e 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -29,6 +29,13 @@ config APM_POWER
 	  Say Y here to enable support APM status emulation using
 	  battery class devices.
 
+config WM8350_POWER
+        tristate "WM8350 PMU support"
+        depends on MFD_WM8350
+        help
+          Say Y here to enable support for the power management unit
+	  provided by the Wolfson Microelectronics WM8350 PMIC.
+
 config BATTERY_DS2760
 	tristate "DS2760 battery driver (HP iPAQ & others)"
 	select W1
diff --git a/drivers/power/Makefile b/drivers/power/Makefile
index e8f1ecec5d8f..e6f68655d9e8 100644
--- a/drivers/power/Makefile
+++ b/drivers/power/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_POWER_SUPPLY)	+= power_supply.o
 
 obj-$(CONFIG_PDA_POWER)		+= pda_power.o
 obj-$(CONFIG_APM_POWER)		+= apm_power.o
+obj-$(CONFIG_WM8350_POWER)	+= wm8350_power.o
 
 obj-$(CONFIG_BATTERY_DS2760)	+= ds2760_battery.o
 obj-$(CONFIG_BATTERY_PMU)	+= pmu_battery.o
diff --git a/drivers/power/wm8350_power.c b/drivers/power/wm8350_power.c
new file mode 100644
index 000000000000..9c0a847a1139
--- /dev/null
+++ b/drivers/power/wm8350_power.c
@@ -0,0 +1,515 @@
+/*
+ * Battery driver for wm8350 PMIC
+ *
+ * Copyright 2007, 2008 Wolfson Microelectronics PLC.
+ *
+ * Based on OLPC Battery Driver
+ *
+ * Copyright 2006  David Woodhouse <dwmw2@infradead.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/mfd/wm8350/supply.h>
+#include <linux/mfd/wm8350/core.h>
+#include <linux/mfd/wm8350/comparator.h>
+
+static int wm8350_read_battery_uvolts(struct wm8350 *wm8350)
+{
+	return wm8350_read_auxadc(wm8350, WM8350_AUXADC_BATT, 0, 0)
+		* WM8350_AUX_COEFF;
+}
+
+static int wm8350_read_line_uvolts(struct wm8350 *wm8350)
+{
+	return wm8350_read_auxadc(wm8350, WM8350_AUXADC_LINE, 0, 0)
+		* WM8350_AUX_COEFF;
+}
+
+static int wm8350_read_usb_uvolts(struct wm8350 *wm8350)
+{
+	return wm8350_read_auxadc(wm8350, WM8350_AUXADC_USB, 0, 0)
+		* WM8350_AUX_COEFF;
+}
+
+#define WM8350_BATT_SUPPLY	1
+#define WM8350_USB_SUPPLY	2
+#define WM8350_LINE_SUPPLY	4
+
+static inline int wm8350_charge_time_min(struct wm8350 *wm8350, int min)
+{
+	if (wm8350->rev < WM8350_REV_G)
+		return (((min - 30) / 15) & 0xf) << 8;
+	else
+		return (((min - 30) / 30) & 0xf) << 8;
+}
+
+static int wm8350_get_supplies(struct wm8350 *wm8350)
+{
+	u16 sm, ov, co, chrg;
+	int supplies = 0;
+
+	sm = wm8350_reg_read(wm8350, WM8350_STATE_MACHINE_STATUS);
+	ov = wm8350_reg_read(wm8350, WM8350_MISC_OVERRIDES);
+	co = wm8350_reg_read(wm8350, WM8350_COMPARATOR_OVERRIDES);
+	chrg = wm8350_reg_read(wm8350, WM8350_BATTERY_CHARGER_CONTROL_2);
+
+	/* USB_SM */
+	sm = (sm & WM8350_USB_SM_MASK) >> WM8350_USB_SM_SHIFT;
+
+	/* CHG_ISEL */
+	chrg &= WM8350_CHG_ISEL_MASK;
+
+	/* If the USB state machine is active then we're using that with or
+	 * without battery, otherwise check for wall supply */
+	if (((sm == WM8350_USB_SM_100_SLV) ||
+	     (sm == WM8350_USB_SM_500_SLV) ||
+	     (sm == WM8350_USB_SM_STDBY_SLV))
+	    && !(ov & WM8350_USB_LIMIT_OVRDE))
+		supplies = WM8350_USB_SUPPLY;
+	else if (((sm == WM8350_USB_SM_100_SLV) ||
+		  (sm == WM8350_USB_SM_500_SLV) ||
+		  (sm == WM8350_USB_SM_STDBY_SLV))
+		 && (ov & WM8350_USB_LIMIT_OVRDE) && (chrg == 0))
+		supplies = WM8350_USB_SUPPLY | WM8350_BATT_SUPPLY;
+	else if (co & WM8350_WALL_FB_OVRDE)
+		supplies = WM8350_LINE_SUPPLY;
+	else
+		supplies = WM8350_BATT_SUPPLY;
+
+	return supplies;
+}
+
+static int wm8350_charger_config(struct wm8350 *wm8350,
+				 struct wm8350_charger_policy *policy)
+{
+	u16 reg, eoc_mA, fast_limit_mA;
+
+	if (!policy) {
+		dev_warn(wm8350->dev,
+			 "No charger policy, charger not configured.\n");
+		return -EINVAL;
+	}
+
+	/* make sure USB fast charge current is not > 500mA */
+	if (policy->fast_limit_USB_mA > 500) {
+		dev_err(wm8350->dev, "USB fast charge > 500mA\n");
+		return -EINVAL;
+	}
+
+	eoc_mA = WM8350_CHG_EOC_mA(policy->eoc_mA);
+
+	wm8350_reg_unlock(wm8350);
+
+	reg = wm8350_reg_read(wm8350, WM8350_BATTERY_CHARGER_CONTROL_1)
+		& WM8350_CHG_ENA_R168;
+	wm8350_reg_write(wm8350, WM8350_BATTERY_CHARGER_CONTROL_1,
+			 reg | eoc_mA | policy->trickle_start_mV |
+			 WM8350_CHG_TRICKLE_TEMP_CHOKE |
+			 WM8350_CHG_TRICKLE_USB_CHOKE |
+			 WM8350_CHG_FAST_USB_THROTTLE);
+
+	if (wm8350_get_supplies(wm8350) & WM8350_USB_SUPPLY) {
+		fast_limit_mA =
+			WM8350_CHG_FAST_LIMIT_mA(policy->fast_limit_USB_mA);
+		wm8350_reg_write(wm8350, WM8350_BATTERY_CHARGER_CONTROL_2,
+			    policy->charge_mV | policy->trickle_charge_USB_mA |
+			    fast_limit_mA | wm8350_charge_time_min(wm8350,
+						policy->charge_timeout));
+
+	} else {
+		fast_limit_mA =
+			WM8350_CHG_FAST_LIMIT_mA(policy->fast_limit_mA);
+		wm8350_reg_write(wm8350, WM8350_BATTERY_CHARGER_CONTROL_2,
+			    policy->charge_mV | policy->trickle_charge_mA |
+			    fast_limit_mA | wm8350_charge_time_min(wm8350,
+						policy->charge_timeout));
+	}
+
+	wm8350_reg_lock(wm8350);
+	return 0;
+}
+
+static int wm8350_batt_status(struct wm8350 *wm8350)
+{
+	u16 state;
+
+	state = wm8350_reg_read(wm8350, WM8350_BATTERY_CHARGER_CONTROL_2);
+	state &= WM8350_CHG_STS_MASK;
+
+	switch (state) {
+	case WM8350_CHG_STS_OFF:
+		return POWER_SUPPLY_STATUS_DISCHARGING;
+
+	case WM8350_CHG_STS_TRICKLE:
+	case WM8350_CHG_STS_FAST:
+		return POWER_SUPPLY_STATUS_CHARGING;
+
+	default:
+		return POWER_SUPPLY_STATUS_UNKNOWN;
+	}
+}
+
+static ssize_t charger_state_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct wm8350 *wm8350 = dev_get_drvdata(dev);
+	char *charge;
+	int state;
+
+	state = wm8350_reg_read(wm8350, WM8350_BATTERY_CHARGER_CONTROL_2) &
+	    WM8350_CHG_STS_MASK;
+	switch (state) {
+	case WM8350_CHG_STS_OFF:
+		charge = "Charger Off";
+		break;
+	case WM8350_CHG_STS_TRICKLE:
+		charge = "Trickle Charging";
+		break;
+	case WM8350_CHG_STS_FAST:
+		charge = "Fast Charging";
+		break;
+	default:
+		return 0;
+	}
+
+	return sprintf(buf, "%s\n", charge);
+}
+
+static DEVICE_ATTR(charger_state, 0444, charger_state_show, NULL);
+
+static void wm8350_charger_handler(struct wm8350 *wm8350, int irq, void *data)
+{
+	struct wm8350_power *power = &wm8350->power;
+	struct wm8350_charger_policy *policy = power->policy;
+
+	switch (irq) {
+	case WM8350_IRQ_CHG_BAT_HOT:
+		dev_err(wm8350->dev, "battery too hot\n");
+		break;
+	case WM8350_IRQ_CHG_BAT_COLD:
+		dev_err(wm8350->dev, "battery too cold\n");
+		break;
+	case WM8350_IRQ_CHG_BAT_FAIL:
+		dev_err(wm8350->dev, "battery failed\n");
+		break;
+	case WM8350_IRQ_CHG_TO:
+		dev_err(wm8350->dev, "charger timeout\n");
+		break;
+	case WM8350_IRQ_CHG_END:
+		power_supply_changed(&power->battery);
+		break;
+	case WM8350_IRQ_CHG_START:
+		power_supply_changed(&power->battery);
+		break;
+
+	case WM8350_IRQ_CHG_FAST_RDY:
+		dev_dbg(wm8350->dev, "fast charger ready\n");
+		wm8350_charger_config(wm8350, policy);
+		wm8350_reg_unlock(wm8350);
+		wm8350_set_bits(wm8350, WM8350_BATTERY_CHARGER_CONTROL_1,
+				WM8350_CHG_FAST);
+		wm8350_reg_lock(wm8350);
+		break;
+
+	case WM8350_IRQ_CHG_VBATT_LT_3P9:
+		dev_warn(wm8350->dev, "battery < 3.9V\n");
+		break;
+	case WM8350_IRQ_CHG_VBATT_LT_3P1:
+		dev_warn(wm8350->dev, "battery < 3.1V\n");
+		break;
+	case WM8350_IRQ_CHG_VBATT_LT_2P85:
+		dev_warn(wm8350->dev, "battery < 2.85V\n");
+		break;
+
+		/* Supply change.  We will overnotify but it should do
+		 * no harm. */
+	case WM8350_IRQ_EXT_USB_FB:
+	case WM8350_IRQ_EXT_WALL_FB:
+		wm8350_charger_config(wm8350, policy);
+	case WM8350_IRQ_EXT_BAT_FB:   /* Fall through */
+		power_supply_changed(&power->battery);
+		power_supply_changed(&power->usb);
+		power_supply_changed(&power->ac);
+		break;
+
+	default:
+		dev_err(wm8350->dev, "Unknown interrupt %d\n", irq);
+	}
+}
+
+/*********************************************************************
+ *		AC Power
+ *********************************************************************/
+static int wm8350_ac_get_prop(struct power_supply *psy,
+			      enum power_supply_property psp,
+			      union power_supply_propval *val)
+{
+	struct wm8350 *wm8350 = dev_get_drvdata(psy->dev->parent);
+	int ret = 0;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = !!(wm8350_get_supplies(wm8350) &
+				 WM8350_LINE_SUPPLY);
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		val->intval = wm8350_read_line_uvolts(wm8350);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static enum power_supply_property wm8350_ac_props[] = {
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+};
+
+/*********************************************************************
+ *		USB Power
+ *********************************************************************/
+static int wm8350_usb_get_prop(struct power_supply *psy,
+			       enum power_supply_property psp,
+			       union power_supply_propval *val)
+{
+	struct wm8350 *wm8350 = dev_get_drvdata(psy->dev->parent);
+	int ret = 0;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = !!(wm8350_get_supplies(wm8350) &
+				 WM8350_USB_SUPPLY);
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		val->intval = wm8350_read_usb_uvolts(wm8350);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static enum power_supply_property wm8350_usb_props[] = {
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+};
+
+/*********************************************************************
+ *		Battery properties
+ *********************************************************************/
+
+static int wm8350_bat_get_property(struct power_supply *psy,
+				   enum power_supply_property psp,
+				   union power_supply_propval *val)
+{
+	struct wm8350 *wm8350 = dev_get_drvdata(psy->dev->parent);
+	int ret = 0;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_STATUS:
+		val->intval = wm8350_batt_status(wm8350);
+		break;
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = !!(wm8350_get_supplies(wm8350) &
+				 WM8350_BATT_SUPPLY);
+		break;
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		val->intval = wm8350_read_battery_uvolts(wm8350);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static enum power_supply_property wm8350_bat_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+};
+
+/*********************************************************************
+ *		Initialisation
+ *********************************************************************/
+
+static void wm8350_init_charger(struct wm8350 *wm8350)
+{
+	/* register our interest in charger events */
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_BAT_HOT,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_BAT_HOT);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_BAT_COLD,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_BAT_COLD);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_BAT_FAIL,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_BAT_FAIL);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_TO,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_TO);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_END,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_END);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_START,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_START);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_FAST_RDY,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_FAST_RDY);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_3P9,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_3P9);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_3P1,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_3P1);
+	wm8350_register_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_2P85,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_2P85);
+
+	/* and supply change events */
+	wm8350_register_irq(wm8350, WM8350_IRQ_EXT_USB_FB,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_EXT_USB_FB);
+	wm8350_register_irq(wm8350, WM8350_IRQ_EXT_WALL_FB,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_EXT_WALL_FB);
+	wm8350_register_irq(wm8350, WM8350_IRQ_EXT_BAT_FB,
+			    wm8350_charger_handler, NULL);
+	wm8350_unmask_irq(wm8350, WM8350_IRQ_EXT_BAT_FB);
+}
+
+static void free_charger_irq(struct wm8350 *wm8350)
+{
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_BAT_HOT);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_BAT_HOT);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_BAT_COLD);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_BAT_COLD);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_BAT_FAIL);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_BAT_FAIL);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_TO);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_TO);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_END);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_END);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_START);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_START);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_3P9);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_3P9);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_3P1);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_3P1);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_2P85);
+	wm8350_free_irq(wm8350, WM8350_IRQ_CHG_VBATT_LT_2P85);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_EXT_USB_FB);
+	wm8350_free_irq(wm8350, WM8350_IRQ_EXT_USB_FB);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_EXT_WALL_FB);
+	wm8350_free_irq(wm8350, WM8350_IRQ_EXT_WALL_FB);
+	wm8350_mask_irq(wm8350, WM8350_IRQ_EXT_BAT_FB);
+	wm8350_free_irq(wm8350, WM8350_IRQ_EXT_BAT_FB);
+}
+
+static __devinit int wm8350_power_probe(struct platform_device *pdev)
+{
+	struct wm8350 *wm8350 = platform_get_drvdata(pdev);
+	struct wm8350_power *power = &wm8350->power;
+	struct wm8350_charger_policy *policy = power->policy;
+	struct power_supply *usb = &power->usb;
+	struct power_supply *battery = &power->battery;
+	struct power_supply *ac = &power->ac;
+	int ret;
+
+	ac->name = "wm8350-ac";
+	ac->type = POWER_SUPPLY_TYPE_MAINS;
+	ac->properties = wm8350_ac_props;
+	ac->num_properties = ARRAY_SIZE(wm8350_ac_props);
+	ac->get_property = wm8350_ac_get_prop;
+	ret = power_supply_register(&pdev->dev, ac);
+	if (ret)
+		return ret;
+
+	battery->name = "wm8350-battery";
+	battery->properties = wm8350_bat_props;
+	battery->num_properties = ARRAY_SIZE(wm8350_bat_props);
+	battery->get_property = wm8350_bat_get_property;
+	battery->use_for_apm = 1;
+	ret = power_supply_register(&pdev->dev, battery);
+	if (ret)
+		goto battery_failed;
+
+	usb->name = "wm8350-usb",
+	usb->type = POWER_SUPPLY_TYPE_USB;
+	usb->properties = wm8350_usb_props;
+	usb->num_properties = ARRAY_SIZE(wm8350_usb_props);
+	usb->get_property = wm8350_usb_get_prop;
+	ret = power_supply_register(&pdev->dev, usb);
+	if (ret)
+		goto usb_failed;
+
+	ret = device_create_file(&pdev->dev, &dev_attr_charger_state);
+	if (ret < 0)
+		dev_warn(wm8350->dev, "failed to add charge sysfs: %d\n", ret);
+	ret = 0;
+
+	wm8350_init_charger(wm8350);
+	if (wm8350_charger_config(wm8350, policy) == 0) {
+		wm8350_reg_unlock(wm8350);
+		wm8350_set_bits(wm8350, WM8350_POWER_MGMT_5, WM8350_CHG_ENA);
+		wm8350_reg_lock(wm8350);
+	}
+
+	return ret;
+
+usb_failed:
+	power_supply_unregister(battery);
+battery_failed:
+	power_supply_unregister(ac);
+
+	return ret;
+}
+
+static __devexit int wm8350_power_remove(struct platform_device *pdev)
+{
+	struct wm8350 *wm8350 = platform_get_drvdata(pdev);
+	struct wm8350_power *power = &wm8350->power;
+
+	free_charger_irq(wm8350);
+	device_remove_file(&pdev->dev, &dev_attr_charger_state);
+	power_supply_unregister(&power->battery);
+	power_supply_unregister(&power->ac);
+	power_supply_unregister(&power->usb);
+	return 0;
+}
+
+static struct platform_driver wm8350_power_driver = {
+	.probe = wm8350_power_probe,
+	.remove = __devexit_p(wm8350_power_remove),
+	.driver = {
+		.name = "wm8350-power",
+	},
+};
+
+static int __init wm8350_power_init(void)
+{
+	return platform_driver_register(&wm8350_power_driver);
+}
+module_init(wm8350_power_init);
+
+static void __exit wm8350_power_exit(void)
+{
+	platform_driver_unregister(&wm8350_power_driver);
+}
+module_exit(wm8350_power_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Power supply driver for WM8350");
+MODULE_ALIAS("platform:wm8350-power");
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index cc190055b9c4..d2614dfc9397 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -57,6 +57,9 @@
 #define WM8350_OVER_CURRENT_INT_STATUS_MASK     0x25
 #define WM8350_GPIO_INT_STATUS_MASK             0x26
 #define WM8350_COMPARATOR_INT_STATUS_MASK       0x27
+#define WM8350_MISC_OVERRIDES			0xE3
+#define WM8350_COMPARATOR_OVERRIDES		0xE7
+#define WM8350_STATE_MACHINE_STATUS		0xE9
 
 #define WM8350_MAX_REGISTER                     0xFF
 
@@ -523,6 +526,29 @@
 #define WM8350_DC2_STS                          0x0002
 #define WM8350_DC1_STS                          0x0001
 
+/*
+ * R227 (0xE3) - Misc Overrides
+ */
+#define WM8350_USB_LIMIT_OVRDE			0x0400
+
+/*
+ * R227 (0xE7) - Comparator Overrides
+ */
+#define WM8350_USB_FB_OVRDE			0x8000
+#define WM8350_WALL_FB_OVRDE			0x4000
+#define WM8350_BATT_FB_OVRDE			0x2000
+
+
+/*
+ * R233 (0xE9) - State Machinine Status
+ */
+#define WM8350_USB_SM_MASK			0x0700
+#define WM8350_USB_SM_SHIFT			8
+
+#define WM8350_USB_SM_100_SLV   1
+#define WM8350_USB_SM_500_SLV   5
+#define WM8350_USB_SM_STDBY_SLV 7
+
 /* WM8350 wake up conditions */
 #define WM8350_IRQ_WKUP_OFF_STATE		43
 #define WM8350_IRQ_WKUP_HIB_STATE		44
diff --git a/include/linux/mfd/wm8350/supply.h b/include/linux/mfd/wm8350/supply.h
index 1c8f3cde79b0..79721513fa9f 100644
--- a/include/linux/mfd/wm8350/supply.h
+++ b/include/linux/mfd/wm8350/supply.h
@@ -13,7 +13,8 @@
 #ifndef __LINUX_MFD_WM8350_SUPPLY_H_
 #define __LINUX_MFD_WM8350_SUPPLY_H_
 
-#include <linux/platform_device.h>
+#include <linux/mutex.h>
+#include <linux/power_supply.h>
 
 /*
  * Charger registers
@@ -104,8 +105,28 @@
 #define WM8350_IRQ_EXT_WALL_FB			37
 #define WM8350_IRQ_EXT_BAT_FB			38
 
+/*
+ * Policy to control charger state machine.
+ */
+struct wm8350_charger_policy {
+
+	/* charger state machine policy  - set in machine driver */
+	int eoc_mA;		/* end of charge current (mA)  */
+	int charge_mV;		/* charge voltage */
+	int fast_limit_mA;	/* fast charge current limit */
+	int fast_limit_USB_mA;	/* USB fast charge current limit */
+	int charge_timeout;	/* charge timeout (mins) */
+	int trickle_start_mV;	/* trickle charge starts at mV */
+	int trickle_charge_mA;	/* trickle charge current */
+	int trickle_charge_USB_mA;	/* USB trickle charge current */
+};
+
 struct wm8350_power {
 	struct platform_device *pdev;
+	struct power_supply battery;
+	struct power_supply usb;
+	struct power_supply ac;
+	struct wm8350_charger_policy *policy;
 };
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From d756f4a4446227ca9626087939a6769ca55ab036 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Mon, 24 Nov 2008 20:20:30 +0100
Subject: mfd: Switch WM8350 revision detection to a feature based model

Rather than check for chip revisions in the WM8350 drivers have the core
code set flags for relevant differences.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/wm8350-core.c         | 6 ++----
 drivers/power/wm8350_power.c      | 2 +-
 include/linux/mfd/wm8350/core.h   | 2 --
 include/linux/mfd/wm8350/supply.h | 2 ++
 4 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index 60439bd3984d..764bf15ea684 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -1240,19 +1240,17 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 		switch ((id2 & WM8350_CHIP_REV_MASK) >> 12) {
 		case WM8350_REV_E:
 			dev_info(wm8350->dev, "Found Rev E device\n");
-			wm8350->rev = WM8350_REV_E;
 			break;
 		case WM8350_REV_F:
 			dev_info(wm8350->dev, "Found Rev F device\n");
-			wm8350->rev = WM8350_REV_F;
 			break;
 		case WM8350_REV_G:
 			dev_info(wm8350->dev, "Found Rev G device\n");
-			wm8350->rev = WM8350_REV_G;
+			wm8350->power.rev_g_coeff = 1;
 			break;
 		case WM8350_REV_H:
 			dev_info(wm8350->dev, "Found Rev H device\n");
-			wm8350->rev = WM8350_REV_H;
+			wm8350->power.rev_g_coeff = 1;
 			break;
 		default:
 			/* For safety we refuse to run on unknown hardware */
diff --git a/drivers/power/wm8350_power.c b/drivers/power/wm8350_power.c
index 9c0a847a1139..74e7593beffb 100644
--- a/drivers/power/wm8350_power.c
+++ b/drivers/power/wm8350_power.c
@@ -44,7 +44,7 @@ static int wm8350_read_usb_uvolts(struct wm8350 *wm8350)
 
 static inline int wm8350_charge_time_min(struct wm8350 *wm8350, int min)
 {
-	if (wm8350->rev < WM8350_REV_G)
+	if (!wm8350->power.rev_g_coeff)
 		return (((min - 30) / 15) & 0xf) << 8;
 	else
 		return (((min - 30) / 30) & 0xf) << 8;
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index d2614dfc9397..3c9735663f36 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -585,8 +585,6 @@ struct wm8350_irq {
 };
 
 struct wm8350 {
-	int rev;		/* chip revision */
-
 	struct device *dev;
 
 	/* device IO */
diff --git a/include/linux/mfd/wm8350/supply.h b/include/linux/mfd/wm8350/supply.h
index 79721513fa9f..2b9479310bbd 100644
--- a/include/linux/mfd/wm8350/supply.h
+++ b/include/linux/mfd/wm8350/supply.h
@@ -127,6 +127,8 @@ struct wm8350_power {
 	struct power_supply usb;
 	struct power_supply ac;
 	struct wm8350_charger_policy *policy;
+
+	int rev_g_coeff;
 };
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From b797a5551979da22b0a35632198ffc8a330d9537 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Mon, 24 Nov 2008 20:22:58 +0100
Subject: mfd: Refactor WM8350 chip identification

Since the WM8350 driver was originally written the semantics for the
identification registers of the chip have been clarified, allowing
us to do an exact match on all the fields. This avoids mistakenly
running on unsupported hardware.

Also change to using the datasheet names more consistently for
legibility and fix a printk() that should be dev_err().

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/wm8350-core.c       | 54 ++++++++++++++++++++++++++++-------------
 include/linux/mfd/wm8350/core.h |  6 +++++
 2 files changed, 43 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index 764bf15ea684..2188d759cbde 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -1227,52 +1227,72 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 		       struct wm8350_platform_data *pdata)
 {
 	int ret = -EINVAL;
-	u16 id1, id2, mask, mode;
+	u16 id1, id2, mask_rev;
+	u16 cust_id, mode, chip_rev;
 
 	/* get WM8350 revision and config mode */
 	wm8350->read_dev(wm8350, WM8350_RESET_ID, sizeof(id1), &id1);
 	wm8350->read_dev(wm8350, WM8350_ID, sizeof(id2), &id2);
+	wm8350->read_dev(wm8350, WM8350_REVISION, sizeof(mask_rev), &mask_rev);
 
 	id1 = be16_to_cpu(id1);
 	id2 = be16_to_cpu(id2);
+	mask_rev = be16_to_cpu(mask_rev);
 
-	if (id1 == 0x6143) {
-		switch ((id2 & WM8350_CHIP_REV_MASK) >> 12) {
+	if (id1 != 0x6143) {
+		dev_err(wm8350->dev,
+			"Device with ID %x is not a WM8350\n", id1);
+		ret = -ENODEV;
+		goto err;
+	}
+
+	mode = id2 & WM8350_CONF_STS_MASK >> 10;
+	cust_id = id2 & WM8350_CUST_ID_MASK;
+	chip_rev = (id2 & WM8350_CHIP_REV_MASK) >> 12;
+	dev_info(wm8350->dev,
+		 "CONF_STS %d, CUST_ID %d, MASK_REV %d, CHIP_REV %d\n",
+		 mode, cust_id, mask_rev, chip_rev);
+
+	if (cust_id != 0) {
+		dev_err(wm8350->dev, "Unsupported CUST_ID\n");
+		ret = -ENODEV;
+		goto err;
+	}
+
+	switch (mask_rev) {
+	case 0:
+		switch (chip_rev) {
 		case WM8350_REV_E:
-			dev_info(wm8350->dev, "Found Rev E device\n");
+			dev_info(wm8350->dev, "WM8350 Rev E\n");
 			break;
 		case WM8350_REV_F:
-			dev_info(wm8350->dev, "Found Rev F device\n");
+			dev_info(wm8350->dev, "WM8350 Rev F\n");
 			break;
 		case WM8350_REV_G:
-			dev_info(wm8350->dev, "Found Rev G device\n");
+			dev_info(wm8350->dev, "WM8350 Rev G\n");
 			wm8350->power.rev_g_coeff = 1;
 			break;
 		case WM8350_REV_H:
-			dev_info(wm8350->dev, "Found Rev H device\n");
+			dev_info(wm8350->dev, "WM8350 Rev H\n");
 			wm8350->power.rev_g_coeff = 1;
 			break;
 		default:
 			/* For safety we refuse to run on unknown hardware */
-			dev_info(wm8350->dev, "Found unknown rev %x\n",
-				 (id2 & WM8350_CHIP_REV_MASK) >> 12);
+			dev_err(wm8350->dev, "Unknown WM8350 CHIP_REV\n");
 			ret = -ENODEV;
 			goto err;
 		}
-	} else {
-		dev_info(wm8350->dev, "Device with ID %x is not a WM8350\n",
-			 id1);
+		break;
+
+	default:
+		dev_err(wm8350->dev, "Unknown MASK_REV\n");
 		ret = -ENODEV;
 		goto err;
 	}
 
-	mode = id2 & WM8350_CONF_STS_MASK >> 10;
-	mask = id2 & WM8350_CUST_ID_MASK;
-	dev_info(wm8350->dev, "Config mode %d, ROM mask %d\n", mode, mask);
-
 	ret = wm8350_create_cache(wm8350, mode);
 	if (ret < 0) {
-		printk(KERN_ERR "wm8350: failed to create register cache\n");
+		dev_err(wm8350->dev, "Failed to create register cache\n");
 		return ret;
 	}
 
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index 3c9735663f36..2a7abeebe777 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -29,6 +29,7 @@
  */
 #define WM8350_RESET_ID                         0x00
 #define WM8350_ID                               0x01
+#define WM8350_REVISION				0x02
 #define WM8350_SYSTEM_CONTROL_1                 0x03
 #define WM8350_SYSTEM_CONTROL_2                 0x04
 #define WM8350_SYSTEM_HIBERNATE                 0x05
@@ -79,6 +80,11 @@
 #define WM8350_CONF_STS_MASK                    0x0C00
 #define WM8350_CUST_ID_MASK                     0x00FF
 
+/*
+ * R2 (0x02) - Revision
+ */
+#define WM8350_MASK_REV_MASK			0x00FF
+
 /*
  * R3 (0x03) - System Control 1
  */
-- 
cgit v1.2.3-70-g09d2


From 7e386e6e0e4f34f0545e8923e22fe4dd61ef9d48 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Sun, 30 Nov 2008 22:43:21 +0100
Subject: power_supply: Add cold to the POWER_SUPPLY_HEALTH report values

Some systems are able to report problems with batteries being under
temperature.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Anton Vorontsov <cbouatmailru@gmail.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/power/power_supply_sysfs.c | 2 +-
 include/linux/power_supply.h       | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c
index 23ae8460f5c1..ac01e06817fb 100644
--- a/drivers/power/power_supply_sysfs.c
+++ b/drivers/power/power_supply_sysfs.c
@@ -45,7 +45,7 @@ static ssize_t power_supply_show_property(struct device *dev,
 	};
 	static char *health_text[] = {
 		"Unknown", "Good", "Overheat", "Dead", "Over voltage",
-		"Unspecified failure"
+		"Unspecified failure", "Cold",
 	};
 	static char *technology_text[] = {
 		"Unknown", "NiMH", "Li-ion", "Li-poly", "LiFe", "NiCd",
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index f9348cba6dc1..8ff25e0e7f7a 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -45,6 +45,7 @@ enum {
 	POWER_SUPPLY_HEALTH_DEAD,
 	POWER_SUPPLY_HEALTH_OVERVOLTAGE,
 	POWER_SUPPLY_HEALTH_UNSPEC_FAILURE,
+	POWER_SUPPLY_HEALTH_COLD,
 };
 
 enum {
-- 
cgit v1.2.3-70-g09d2


From 4008e879e1325c29362aa2c3fa4b527273ae15a8 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Sun, 30 Nov 2008 22:45:14 +0100
Subject: power_supply: Add battery health reporting for WM8350

Implement support for reporting battery health in the WM8350 battery
interface. Since we are now able to report this via the classs remove
the diagnostics from the interrupt handler.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Anton Vorontsov <cbouatmailru@gmail.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/wm8350-regmap.c     |  2 +-
 drivers/power/wm8350_power.c    | 33 +++++++++++++++++++++++++--------
 include/linux/mfd/wm8350/core.h |  7 +++++++
 3 files changed, 33 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/wm8350-regmap.c b/drivers/mfd/wm8350-regmap.c
index aaf394aa9c2d..b43d64c2b920 100644
--- a/drivers/mfd/wm8350-regmap.c
+++ b/drivers/mfd/wm8350-regmap.c
@@ -1314,7 +1314,7 @@ const struct wm8350_reg_access wm8350_reg_io_map[] = {
 	{ 0xFFFF, 0xFFFF, 0xFFFF }, /* R223 */
 	{ 0x0000, 0x0000, 0x0000 }, /* R224 */
 	{ 0x8F3F, 0x0000, 0xFFFF }, /* R225 - DCDC/LDO status */
-	{ 0x0000, 0x0000, 0x0000 }, /* R226 */
+	{ 0x0000, 0x0000, 0xFFFF }, /* R226 - Charger status */
 	{ 0x0000, 0x0000, 0xFFFF }, /* R227 */
 	{ 0x0000, 0x0000, 0x0000 }, /* R228 */
 	{ 0x0000, 0x0000, 0x0000 }, /* R229 */
diff --git a/drivers/power/wm8350_power.c b/drivers/power/wm8350_power.c
index 74e7593beffb..1b16bf343f2f 100644
--- a/drivers/power/wm8350_power.c
+++ b/drivers/power/wm8350_power.c
@@ -190,22 +190,18 @@ static void wm8350_charger_handler(struct wm8350 *wm8350, int irq, void *data)
 	struct wm8350_charger_policy *policy = power->policy;
 
 	switch (irq) {
-	case WM8350_IRQ_CHG_BAT_HOT:
-		dev_err(wm8350->dev, "battery too hot\n");
-		break;
-	case WM8350_IRQ_CHG_BAT_COLD:
-		dev_err(wm8350->dev, "battery too cold\n");
-		break;
 	case WM8350_IRQ_CHG_BAT_FAIL:
 		dev_err(wm8350->dev, "battery failed\n");
 		break;
 	case WM8350_IRQ_CHG_TO:
 		dev_err(wm8350->dev, "charger timeout\n");
-		break;
-	case WM8350_IRQ_CHG_END:
 		power_supply_changed(&power->battery);
 		break;
+
+	case WM8350_IRQ_CHG_BAT_HOT:
+	case WM8350_IRQ_CHG_BAT_COLD:
 	case WM8350_IRQ_CHG_START:
+	case WM8350_IRQ_CHG_END:
 		power_supply_changed(&power->battery);
 		break;
 
@@ -308,6 +304,23 @@ static enum power_supply_property wm8350_usb_props[] = {
  *		Battery properties
  *********************************************************************/
 
+static int wm8350_bat_check_health(struct wm8350 *wm8350)
+{
+	u16 reg;
+
+	if (wm8350_read_battery_uvolts(wm8350) < 2850000)
+		return POWER_SUPPLY_HEALTH_UNSPEC_FAILURE;
+
+	reg = wm8350_reg_read(wm8350, WM8350_CHARGER_OVERRIDES);
+	if (reg & WM8350_CHG_BATT_HOT_OVRDE)
+		return POWER_SUPPLY_HEALTH_OVERHEAT;
+
+	if (reg & WM8350_CHG_BATT_COLD_OVRDE)
+		return POWER_SUPPLY_HEALTH_COLD;
+
+	return POWER_SUPPLY_HEALTH_GOOD;
+}
+
 static int wm8350_bat_get_property(struct power_supply *psy,
 				   enum power_supply_property psp,
 				   union power_supply_propval *val)
@@ -326,6 +339,9 @@ static int wm8350_bat_get_property(struct power_supply *psy,
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
 		val->intval = wm8350_read_battery_uvolts(wm8350);
 		break;
+	case POWER_SUPPLY_PROP_HEALTH:
+		val->intval = wm8350_bat_check_health(wm8350);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -338,6 +354,7 @@ static enum power_supply_property wm8350_bat_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_ONLINE,
 	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_HEALTH,
 };
 
 /*********************************************************************
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index 2a7abeebe777..afeff6f1316c 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -58,6 +58,7 @@
 #define WM8350_OVER_CURRENT_INT_STATUS_MASK     0x25
 #define WM8350_GPIO_INT_STATUS_MASK             0x26
 #define WM8350_COMPARATOR_INT_STATUS_MASK       0x27
+#define WM8350_CHARGER_OVERRIDES		0xE2
 #define WM8350_MISC_OVERRIDES			0xE3
 #define WM8350_COMPARATOR_OVERRIDES		0xE7
 #define WM8350_STATE_MACHINE_STATUS		0xE9
@@ -532,6 +533,12 @@
 #define WM8350_DC2_STS                          0x0002
 #define WM8350_DC1_STS                          0x0001
 
+/*
+ * R226 (0xE2) - Charger status
+ */
+#define WM8350_CHG_BATT_HOT_OVRDE		0x8000
+#define WM8350_CHG_BATT_COLD_OVRDE		0x4000
+
 /*
  * R227 (0xE3) - Misc Overrides
  */
-- 
cgit v1.2.3-70-g09d2


From 67460a7c26271fd7a32e5d51b2c806a84ce78a62 Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Mon, 1 Dec 2008 00:35:33 +0100
Subject: mfd: twl4030: cleanup symbols and OMAP dependency

Finish removing dependency of TWL driver stack on platform-specific
IRQ definitions ... and remove the build dependency on OMAP.

This lets the TWL4030 code be included in test builds for most
platforms, and will make it easier for non-OMAP folk to update
most of this code for new APIs etc.

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/Kconfig         |  2 +-
 include/linux/i2c/twl4030.h | 31 -------------------------------
 2 files changed, 1 insertion(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 257277394f8c..8cd3dd9a69b2 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -63,7 +63,7 @@ config UCB1400_CORE
 
 config TWL4030_CORE
 	bool "Texas Instruments TWL4030/TPS659x0 Support"
-	depends on I2C=y && GENERIC_HARDIRQS && (ARCH_OMAP2 || ARCH_OMAP3)
+	depends on I2C=y && GENERIC_HARDIRQS
 	help
 	  Say yes here if you have TWL4030 family chip on your board.
 	  This core driver provides register access and IRQ handling
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
index ae25c907b7cf..d4846695bcd0 100644
--- a/include/linux/i2c/twl4030.h
+++ b/include/linux/i2c/twl4030.h
@@ -285,33 +285,6 @@ struct twl4030_platform_data {
 
 int twl4030_sih_setup(int module);
 
-/*
- * FIXME completely stop using TWL4030_IRQ_BASE ... instead, pass the
- * IRQ data to subsidiary devices using platform device resources.
- */
-
-/* IRQ information-need base */
-#include <mach/irqs.h>
-/* TWL4030 interrupts */
-
-/* #define TWL4030_MODIRQ_GPIO		(TWL4030_IRQ_BASE + 0) */
-#define TWL4030_MODIRQ_KEYPAD		(TWL4030_IRQ_BASE + 1)
-#define TWL4030_MODIRQ_BCI		(TWL4030_IRQ_BASE + 2)
-#define TWL4030_MODIRQ_MADC		(TWL4030_IRQ_BASE + 3)
-/* #define TWL4030_MODIRQ_USB		(TWL4030_IRQ_BASE + 4) */
-/* #define TWL4030_MODIRQ_PWR		(TWL4030_IRQ_BASE + 5) */
-
-#define TWL4030_PWRIRQ_PWRBTN		(TWL4030_PWR_IRQ_BASE + 0)
-/* #define TWL4030_PWRIRQ_CHG_PRES		(TWL4030_PWR_IRQ_BASE + 1) */
-/* #define TWL4030_PWRIRQ_USB_PRES		(TWL4030_PWR_IRQ_BASE + 2) */
-/* #define TWL4030_PWRIRQ_RTC		(TWL4030_PWR_IRQ_BASE + 3) */
-/* #define TWL4030_PWRIRQ_HOT_DIE		(TWL4030_PWR_IRQ_BASE + 4) */
-/* #define TWL4030_PWRIRQ_PWROK_TIMEOUT	(TWL4030_PWR_IRQ_BASE + 5) */
-/* #define TWL4030_PWRIRQ_MBCHG		(TWL4030_PWR_IRQ_BASE + 6) */
-/* #define TWL4030_PWRIRQ_SC_DETECT	(TWL4030_PWR_IRQ_BASE + 7) */
-
-/* Rest are unsued currently*/
-
 /* Offsets to Power Registers */
 #define TWL4030_VDAC_DEV_GRP		0x3B
 #define TWL4030_VDAC_DEDICATED		0x3E
@@ -322,10 +295,6 @@ int twl4030_sih_setup(int module);
 #define TWL4030_VAUX3_DEV_GRP		0x1F
 #define TWL4030_VAUX3_DEDICATED		0x22
 
-/* TWL4030 GPIO interrupt definitions */
-
-#define TWL4030_GPIO_IRQ_NO(n)		(TWL4030_GPIO_IRQ_BASE + (n))
-
 /*
  * Exported TWL4030 GPIO APIs
  *
-- 
cgit v1.2.3-70-g09d2


From dad759ff8ba79927766e3f0159bfc5fb6de0f982 Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Mon, 1 Dec 2008 00:43:58 +0100
Subject: mfd: twl4030: create some regulator devices

Initial code to create twl4030 voltage regulator devices, using
the new regulator framework.  Note that this now starts to care
what name is used to declare the TWL chip:

 - TWL4030 is the "old" chip; newer ones have a bigger variety
   of VAUX2 voltages.

 - TWL5030 is the core "new" chip; TPS65950 is its catalog version.

 - The TPS65930 and TPS65920 are cost-reduced catalog versions of
   TWL5030 parts ... fewer regulators, no battery charger, etc.

Board-specific regulator configuration should be provided, listing
which regulators are used and their constraints (e.g. 1.8V only).

Code that could ("should"?) leverage the regulator stuff includes
TWL4030 USB transceiver support and MMC glue, LCD support for the
3430SDP and Labrador boards, and S-Video output.

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/twl4030-core.c  | 174 +++++++++++++++++++++++++++++++++++++++++---
 include/linux/i2c/twl4030.h |  47 ++++++++++++
 2 files changed, 211 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/twl4030-core.c b/drivers/mfd/twl4030-core.c
index f5486cce86f4..8ab9ee8543a6 100644
--- a/drivers/mfd/twl4030-core.c
+++ b/drivers/mfd/twl4030-core.c
@@ -33,6 +33,8 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 
+#include <linux/regulator/machine.h>
+
 #include <linux/i2c.h>
 #include <linux/i2c/twl4030.h>
 
@@ -71,6 +73,13 @@
 #define twl_has_gpio()	false
 #endif
 
+#if defined(CONFIG_REGULATOR_TWL4030) \
+	|| defined(CONFIG_REGULATOR_TWL4030_MODULE)
+#define twl_has_regulator()	true
+#else
+#define twl_has_regulator()	false
+#endif
+
 #if defined(CONFIG_TWL4030_MADC) || defined(CONFIG_TWL4030_MADC_MODULE)
 #define twl_has_madc()	true
 #else
@@ -149,6 +158,10 @@
 #define HIGH_PERF_SQ			(1 << 3)
 
 
+/* chip-specific feature flags, for i2c_device_id.driver_data */
+#define TWL4030_VAUX2		BIT(0)	/* pre-5030 voltage ranges */
+#define TPS_SUBSET		BIT(1)	/* tps659[23]0 have fewer LDOs */
+
 /*----------------------------------------------------------------------*/
 
 /* is driver active, bound to a chip? */
@@ -352,7 +365,8 @@ EXPORT_SYMBOL(twl4030_i2c_read_u8);
 
 /*----------------------------------------------------------------------*/
 
-static struct device *add_child(unsigned chip, const char *name,
+static struct device *
+add_numbered_child(unsigned chip, const char *name, int num,
 		void *pdata, unsigned pdata_len,
 		bool can_wakeup, int irq0, int irq1)
 {
@@ -360,7 +374,7 @@ static struct device *add_child(unsigned chip, const char *name,
 	struct twl4030_client	*twl = &twl4030_modules[chip];
 	int			status;
 
-	pdev = platform_device_alloc(name, -1);
+	pdev = platform_device_alloc(name, num);
 	if (!pdev) {
 		dev_dbg(&twl->client->dev, "can't alloc dev\n");
 		status = -ENOMEM;
@@ -402,17 +416,52 @@ err:
 	return &pdev->dev;
 }
 
+static inline struct device *add_child(unsigned chip, const char *name,
+		void *pdata, unsigned pdata_len,
+		bool can_wakeup, int irq0, int irq1)
+{
+	return add_numbered_child(chip, name, -1, pdata, pdata_len,
+		can_wakeup, irq0, irq1);
+}
+
+static struct device *
+add_regulator_linked(int num, struct regulator_init_data *pdata,
+		struct regulator_consumer_supply *consumers,
+		unsigned num_consumers)
+{
+	/* regulator framework demands init_data ... */
+	if (!pdata)
+		return NULL;
+
+	if (consumers && !pdata->consumer_supplies) {
+		pdata->consumer_supplies = consumers;
+		pdata->num_consumer_supplies = num_consumers;
+	}
+
+	/* NOTE:  we currently ignore regulator IRQs, e.g. for short circuits */
+	return add_numbered_child(3, "twl4030_reg", num,
+		pdata, sizeof(*pdata), false, 0, 0);
+}
+
+static struct device *
+add_regulator(int num, struct regulator_init_data *pdata)
+{
+	return add_regulator_linked(num, pdata, NULL, 0);
+}
+
 /*
  * NOTE:  We know the first 8 IRQs after pdata->base_irq are
  * for the PIH, and the next are for the PWR_INT SIH, since
  * that's how twl_init_irq() sets things up.
  */
 
-static int add_children(struct twl4030_platform_data *pdata)
+static int
+add_children(struct twl4030_platform_data *pdata, unsigned long features)
 {
 	struct device	*child;
+	struct device	*usb_transceiver = NULL;
 
-	if (twl_has_bci() && pdata->bci) {
+	if (twl_has_bci() && pdata->bci && !(features & TPS_SUBSET)) {
 		child = add_child(3, "twl4030_bci",
 				pdata->bci, sizeof(*pdata->bci),
 				false,
@@ -469,6 +518,111 @@ static int add_children(struct twl4030_platform_data *pdata)
 				pdata->irq_base + 8 + 2, pdata->irq_base + 4);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
+
+		/* we need to connect regulators to this transceiver */
+		usb_transceiver = child;
+	}
+
+	if (twl_has_regulator()) {
+		/*
+		child = add_regulator(TWL4030_REG_VPLL1, pdata->vpll1);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+		*/
+
+		child = add_regulator(TWL4030_REG_VMMC1, pdata->vmmc1);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator(TWL4030_REG_VDAC, pdata->vdac);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator((features & TWL4030_VAUX2)
+					? TWL4030_REG_VAUX2_4030
+					: TWL4030_REG_VAUX2,
+				pdata->vaux2);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+	}
+
+	if (twl_has_regulator() && usb_transceiver) {
+		static struct regulator_consumer_supply usb1v5 = {
+			.supply =	"usb1v5",
+		};
+		static struct regulator_consumer_supply usb1v8 = {
+			.supply =	"usb1v8",
+		};
+		static struct regulator_consumer_supply usb3v1 = {
+			.supply =	"usb3v1",
+		};
+		static struct regulator_consumer_supply usbcp = {
+			.supply =	"usbcp",
+		};
+
+		/* this is a template that gets copied */
+		struct regulator_init_data usb_fixed = {
+			.constraints.valid_modes_mask =
+				  REGULATOR_MODE_NORMAL
+				| REGULATOR_MODE_STANDBY,
+			.constraints.valid_ops_mask =
+				  REGULATOR_CHANGE_MODE
+				| REGULATOR_CHANGE_STATUS,
+		};
+
+		usb1v5.dev = usb_transceiver;
+		usb1v8.dev = usb_transceiver;
+		usb3v1.dev = usb_transceiver;
+		usbcp.dev = usb_transceiver;
+
+		child = add_regulator_linked(TWL4030_REG_VUSB1V5, &usb_fixed,
+				&usb1v5, 1);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator_linked(TWL4030_REG_VUSB1V8, &usb_fixed,
+				&usb1v8, 1);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator_linked(TWL4030_REG_VUSB3V1, &usb_fixed,
+				&usb3v1, 1);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator_linked(TWL4030_REG_VUSBCP, &usb_fixed,
+				&usbcp, 1);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+	}
+
+	/* maybe add LDOs that are omitted on cost-reduced parts */
+	if (twl_has_regulator() && !(features & TPS_SUBSET)) {
+		/*
+		child = add_regulator(TWL4030_REG_VPLL2, pdata->vpll2);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+		*/
+
+		child = add_regulator(TWL4030_REG_VMMC2, pdata->vmmc2);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator(TWL4030_REG_VSIM, pdata->vsim);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator(TWL4030_REG_VAUX1, pdata->vaux1);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator(TWL4030_REG_VAUX3, pdata->vaux3);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+
+		child = add_regulator(TWL4030_REG_VAUX4, pdata->vaux4);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
 	}
 
 	return 0;
@@ -632,7 +786,7 @@ twl4030_probe(struct i2c_client *client, const struct i2c_device_id *id)
 			goto fail;
 	}
 
-	status = add_children(pdata);
+	status = add_children(pdata, id->driver_data);
 fail:
 	if (status < 0)
 		twl4030_remove(client);
@@ -640,11 +794,11 @@ fail:
 }
 
 static const struct i2c_device_id twl4030_ids[] = {
-	{ "twl4030", 0 },	/* "Triton 2" */
-	{ "tps65950", 0 },	/* catalog version of twl4030 */
-	{ "tps65930", 0 },	/* fewer LDOs and DACs; no charger */
-	{ "tps65920", 0 },	/* fewer LDOs; no codec or charger */
-	{ "twl5030", 0 },	/* T2 updated */
+	{ "twl4030", TWL4030_VAUX2 },	/* "Triton 2" */
+	{ "twl5030", 0 },		/* T2 updated */
+	{ "tps65950", 0 },		/* catalog version of twl5030 */
+	{ "tps65930", TPS_SUBSET },	/* fewer LDOs and DACs; no charger */
+	{ "tps65920", TPS_SUBSET },	/* fewer LDOs; no codec or charger */
 	{ /* end of list */ },
 };
 MODULE_DEVICE_TABLE(i2c, twl4030_ids);
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
index d4846695bcd0..e06555d40d35 100644
--- a/include/linux/i2c/twl4030.h
+++ b/include/linux/i2c/twl4030.h
@@ -278,6 +278,18 @@ struct twl4030_platform_data {
 	struct twl4030_keypad_data		*keypad;
 	struct twl4030_usb_data			*usb;
 
+	/* LDO regulators */
+	struct regulator_init_data		*vdac;
+	struct regulator_init_data		*vpll1;
+	struct regulator_init_data		*vpll2;
+	struct regulator_init_data		*vmmc1;
+	struct regulator_init_data		*vmmc2;
+	struct regulator_init_data		*vsim;
+	struct regulator_init_data		*vaux1;
+	struct regulator_init_data		*vaux2;
+	struct regulator_init_data		*vaux3;
+	struct regulator_init_data		*vaux4;
+
 	/* REVISIT more to come ... _nothing_ should be hard-wired */
 };
 
@@ -309,4 +321,39 @@ int twl4030_set_gpio_debounce(int gpio, int enable);
 	static inline int twl4030charger_usb_en(int enable) { return 0; }
 #endif
 
+/*----------------------------------------------------------------------*/
+
+/* Linux-specific regulator identifiers ... for now, we only support
+ * the LDOs, and leave the three buck converters alone.  VDD1 and VDD2
+ * need to tie into hardware based voltage scaling (cpufreq etc), while
+ * VIO is generally fixed.
+ */
+
+/* EXTERNAL dc-to-dc buck converters */
+#define TWL4030_REG_VDD1	0
+#define TWL4030_REG_VDD2	1
+#define TWL4030_REG_VIO		2
+
+/* EXTERNAL LDOs */
+#define TWL4030_REG_VDAC	3
+#define TWL4030_REG_VPLL1	4
+#define TWL4030_REG_VPLL2	5	/* not on all chips */
+#define TWL4030_REG_VMMC1	6
+#define TWL4030_REG_VMMC2	7	/* not on all chips */
+#define TWL4030_REG_VSIM	8	/* not on all chips */
+#define TWL4030_REG_VAUX1	9	/* not on all chips */
+#define TWL4030_REG_VAUX2_4030	10	/* (twl4030-specific) */
+#define TWL4030_REG_VAUX2	11	/* (twl5030 and newer) */
+#define TWL4030_REG_VAUX3	12	/* not on all chips */
+#define TWL4030_REG_VAUX4	13	/* not on all chips */
+
+/* INTERNAL LDOs */
+#define TWL4030_REG_VINTANA1	14
+#define TWL4030_REG_VINTANA2	15
+#define TWL4030_REG_VINTDIG	16
+#define TWL4030_REG_VUSB1V5	17
+#define TWL4030_REG_VUSB1V8	18
+#define TWL4030_REG_VUSB3V1	19
+#define TWL4030_REG_VUSBCP	20
+
 #endif /* End of __TWL4030_H */
-- 
cgit v1.2.3-70-g09d2


From b73eac7871d002835be17d4602cced2c15c0db4b Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Sun, 7 Dec 2008 19:10:58 +0100
Subject: mfd: twl4030 regulator bug fixes

This contains two bugfixes to the initial twl4030 regulator
support patch related to USB:

 (a) always overwrite the old list of consumers ... else
     the regulator handles all use the same "usb1v5" name;
 (b) don't set up the "usbcp" regulator, which turns out
     to be managed through separate controls, usually ULPI
     directly from the OTG controller.

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/twl4030-core.c  | 11 +----------
 include/linux/i2c/twl4030.h |  1 -
 2 files changed, 1 insertion(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/twl4030-core.c b/drivers/mfd/twl4030-core.c
index 8ab9ee8543a6..fdfbd313ae09 100644
--- a/drivers/mfd/twl4030-core.c
+++ b/drivers/mfd/twl4030-core.c
@@ -433,7 +433,7 @@ add_regulator_linked(int num, struct regulator_init_data *pdata,
 	if (!pdata)
 		return NULL;
 
-	if (consumers && !pdata->consumer_supplies) {
+	if (consumers) {
 		pdata->consumer_supplies = consumers;
 		pdata->num_consumer_supplies = num_consumers;
 	}
@@ -556,9 +556,6 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 		static struct regulator_consumer_supply usb3v1 = {
 			.supply =	"usb3v1",
 		};
-		static struct regulator_consumer_supply usbcp = {
-			.supply =	"usbcp",
-		};
 
 		/* this is a template that gets copied */
 		struct regulator_init_data usb_fixed = {
@@ -573,7 +570,6 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 		usb1v5.dev = usb_transceiver;
 		usb1v8.dev = usb_transceiver;
 		usb3v1.dev = usb_transceiver;
-		usbcp.dev = usb_transceiver;
 
 		child = add_regulator_linked(TWL4030_REG_VUSB1V5, &usb_fixed,
 				&usb1v5, 1);
@@ -589,11 +585,6 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 				&usb3v1, 1);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
-
-		child = add_regulator_linked(TWL4030_REG_VUSBCP, &usb_fixed,
-				&usbcp, 1);
-		if (IS_ERR(child))
-			return PTR_ERR(child);
 	}
 
 	/* maybe add LDOs that are omitted on cost-reduced parts */
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
index e06555d40d35..a8f84c01f82e 100644
--- a/include/linux/i2c/twl4030.h
+++ b/include/linux/i2c/twl4030.h
@@ -354,6 +354,5 @@ int twl4030_set_gpio_debounce(int gpio, int enable);
 #define TWL4030_REG_VUSB1V5	17
 #define TWL4030_REG_VUSB1V8	18
 #define TWL4030_REG_VUSB3V1	19
-#define TWL4030_REG_VUSBCP	20
 
 #endif /* End of __TWL4030_H */
-- 
cgit v1.2.3-70-g09d2


From 856f6fd119411d5701d5db96e1aae1dd69923887 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <mike@compulab.co.il>
Date: Thu, 18 Dec 2008 10:54:27 +0100
Subject: mfd: Dialog DA9030 battery charger MFD driver

This patch amends DA903x MFD driver with definitions and methods
needed for battery charger driver.

Signed-off-by: Mike Rapoport <mike@compulab.co.il>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/da903x.c       | 12 ++++++++++++
 include/linux/mfd/da903x.h | 44 ++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 54 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/da903x.c b/drivers/mfd/da903x.c
index 0b5bd85dfcec..fcaf1f6028dd 100644
--- a/drivers/mfd/da903x.c
+++ b/drivers/mfd/da903x.c
@@ -151,12 +151,24 @@ int da903x_write(struct device *dev, int reg, uint8_t val)
 }
 EXPORT_SYMBOL_GPL(da903x_write);
 
+int da903x_writes(struct device *dev, int reg, int len, uint8_t *val)
+{
+	return __da903x_writes(to_i2c_client(dev), reg, len, val);
+}
+EXPORT_SYMBOL_GPL(da903x_writes);
+
 int da903x_read(struct device *dev, int reg, uint8_t *val)
 {
 	return __da903x_read(to_i2c_client(dev), reg, val);
 }
 EXPORT_SYMBOL_GPL(da903x_read);
 
+int da903x_reads(struct device *dev, int reg, int len, uint8_t *val)
+{
+	return __da903x_reads(to_i2c_client(dev), reg, len, val);
+}
+EXPORT_SYMBOL_GPL(da903x_reads);
+
 int da903x_set_bits(struct device *dev, int reg, uint8_t bit_mask)
 {
 	struct da903x_chip *chip = dev_get_drvdata(dev);
diff --git a/include/linux/mfd/da903x.h b/include/linux/mfd/da903x.h
index cad314c12439..115dbe965082 100644
--- a/include/linux/mfd/da903x.h
+++ b/include/linux/mfd/da903x.h
@@ -32,6 +32,7 @@ enum {
 	DA9030_ID_LDO18,
 	DA9030_ID_LDO19,
 	DA9030_ID_LDO_INT,	/* LDO Internal */
+	DA9030_ID_BAT,		/* battery charger */
 
 	DA9034_ID_LED_1,
 	DA9034_ID_LED_2,
@@ -93,6 +94,43 @@ struct da9034_touch_pdata {
 	int	y_inverted;
 };
 
+/* DA9030 battery charger data */
+struct power_supply_info;
+
+struct da9030_battery_info {
+	/* battery parameters */
+	struct power_supply_info *battery_info;
+
+	/* current and voltage to use for battery charging */
+	unsigned int charge_milliamp;
+	unsigned int charge_millivolt;
+
+	/* voltage thresholds (in millivolts) */
+	int vbat_low;
+	int vbat_crit;
+	int vbat_charge_start;
+	int vbat_charge_stop;
+	int vbat_charge_restart;
+
+	/* battery nominal minimal and maximal voltages in millivolts */
+	int vcharge_min;
+	int vcharge_max;
+
+	/* Temperature thresholds. These are DA9030 register values
+	   "as is" and should be measured for each battery type */
+	int tbat_low;
+	int tbat_high;
+	int tbat_restart;
+
+
+	/* battery monitor interval (seconds) */
+	unsigned int batmon_interval;
+
+	/* platform callbacks for battery low and critical events */
+	void (*battery_low)(void);
+	void (*battery_critical)(void);
+};
+
 struct da903x_subdev_info {
 	int		id;
 	const char	*name;
@@ -190,11 +228,13 @@ extern int da903x_unregister_notifier(struct device *dev,
 extern int da903x_query_status(struct device *dev, unsigned int status);
 
 
-/* NOTE: the two functions below are not intended for use outside
- * of the DA9034 sub-device drivers
+/* NOTE: the functions below are not intended for use outside
+ * of the DA903x sub-device drivers
  */
 extern int da903x_write(struct device *dev, int reg, uint8_t val);
+extern int da903x_writes(struct device *dev, int reg, int len, uint8_t *val);
 extern int da903x_read(struct device *dev, int reg, uint8_t *val);
+extern int da903x_reads(struct device *dev, int reg, int len, uint8_t *val);
 extern int da903x_update(struct device *dev, int reg, uint8_t val, uint8_t mask);
 extern int da903x_set_bits(struct device *dev, int reg, uint8_t bit_mask);
 extern int da903x_clr_bits(struct device *dev, int reg, uint8_t bit_mask);
-- 
cgit v1.2.3-70-g09d2


From 96920630624868add3f63f596523e70dbb64549a Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Thu, 18 Dec 2008 23:09:50 +0100
Subject: mfd: Add WM8352 support

The WM8352 is a variant of the WM8350. Aside from the register defaults
there are no software visible differences to the WM8350.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/Kconfig             |   16 +
 drivers/mfd/wm8350-core.c       |   86 +++-
 drivers/mfd/wm8350-i2c.c        |    1 +
 drivers/mfd/wm8350-regmap.c     | 1052 +++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/wm8350/core.h |    4 +
 5 files changed, 1143 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index ddfb12b52f54..76a482dfc177 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -143,6 +143,22 @@ config MFD_WM8350_CONFIG_MODE_3
 	bool
 	depends on MFD_WM8350
 
+config MFD_WM8352_CONFIG_MODE_0
+	bool
+	depends on MFD_WM8350
+
+config MFD_WM8352_CONFIG_MODE_1
+	bool
+	depends on MFD_WM8350
+
+config MFD_WM8352_CONFIG_MODE_2
+	bool
+	depends on MFD_WM8350
+
+config MFD_WM8352_CONFIG_MODE_3
+	bool
+	depends on MFD_WM8350
+
 config MFD_WM8350_I2C
 	tristate "Support Wolfson Microelectronics WM8350 with I2C"
 	select MFD_WM8350
diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index 2188d759cbde..fa505ac76c84 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -1133,35 +1133,75 @@ EXPORT_SYMBOL_GPL(wm8350_read_auxadc);
 /*
  * Cache is always host endian.
  */
-static int wm8350_create_cache(struct wm8350 *wm8350, int mode)
+static int wm8350_create_cache(struct wm8350 *wm8350, int type, int mode)
 {
 	int i, ret = 0;
 	u16 value;
 	const u16 *reg_map;
 
-	switch (mode) {
-#ifdef CONFIG_MFD_WM8350_CONFIG_MODE_0
+	switch (type) {
 	case 0:
-		reg_map = wm8350_mode0_defaults;
-		break;
+		switch (mode) {
+#ifdef CONFIG_MFD_WM8350_CONFIG_MODE_0
+		case 0:
+			reg_map = wm8350_mode0_defaults;
+			break;
 #endif
 #ifdef CONFIG_MFD_WM8350_CONFIG_MODE_1
-	case 1:
-		reg_map = wm8350_mode1_defaults;
-		break;
+		case 1:
+			reg_map = wm8350_mode1_defaults;
+			break;
 #endif
 #ifdef CONFIG_MFD_WM8350_CONFIG_MODE_2
-	case 2:
-		reg_map = wm8350_mode2_defaults;
-		break;
+		case 2:
+			reg_map = wm8350_mode2_defaults;
+			break;
 #endif
 #ifdef CONFIG_MFD_WM8350_CONFIG_MODE_3
-	case 3:
-		reg_map = wm8350_mode3_defaults;
-		break;
+		case 3:
+			reg_map = wm8350_mode3_defaults;
+			break;
 #endif
+		default:
+			dev_err(wm8350->dev,
+				"WM8350 configuration mode %d not supported\n",
+				mode);
+			return -EINVAL;
+		}
+
+	case 2:
+		switch (mode) {
+#ifdef CONFIG_MFD_WM8352_CONFIG_MODE_0
+		case 0:
+			reg_map = wm8352_mode0_defaults;
+			break;
+#endif
+#ifdef CONFIG_MFD_WM8352_CONFIG_MODE_1
+		case 1:
+			reg_map = wm8352_mode1_defaults;
+			break;
+#endif
+#ifdef CONFIG_MFD_WM8352_CONFIG_MODE_2
+		case 2:
+			reg_map = wm8352_mode2_defaults;
+			break;
+#endif
+#ifdef CONFIG_MFD_WM8352_CONFIG_MODE_3
+		case 3:
+			reg_map = wm8352_mode3_defaults;
+			break;
+#endif
+		default:
+			dev_err(wm8350->dev,
+				"WM8352 configuration mode %d not supported\n",
+				mode);
+			return -EINVAL;
+		}
+		break;
+
 	default:
-		dev_err(wm8350->dev, "Configuration mode %d not supported\n",
+		dev_err(wm8350->dev,
+			"WM835x configuration mode %d not supported\n",
 			mode);
 		return -EINVAL;
 	}
@@ -1284,13 +1324,27 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 		}
 		break;
 
+	case 2:
+		switch (chip_rev) {
+		case 0:
+			dev_info(wm8350->dev, "WM8352 Rev A\n");
+			wm8350->power.rev_g_coeff = 1;
+			break;
+
+		default:
+			dev_err(wm8350->dev, "Unknown WM8352 CHIP_REV\n");
+			ret = -ENODEV;
+			goto err;
+		}
+		break;
+
 	default:
 		dev_err(wm8350->dev, "Unknown MASK_REV\n");
 		ret = -ENODEV;
 		goto err;
 	}
 
-	ret = wm8350_create_cache(wm8350, mode);
+	ret = wm8350_create_cache(wm8350, mask_rev, mode);
 	if (ret < 0) {
 		dev_err(wm8350->dev, "Failed to create register cache\n");
 		return ret;
diff --git a/drivers/mfd/wm8350-i2c.c b/drivers/mfd/wm8350-i2c.c
index 876e693582bd..878051253084 100644
--- a/drivers/mfd/wm8350-i2c.c
+++ b/drivers/mfd/wm8350-i2c.c
@@ -97,6 +97,7 @@ static int wm8350_i2c_remove(struct i2c_client *i2c)
 
 static const struct i2c_device_id wm8350_i2c_id[] = {
        { "wm8350", 0 },
+       { "wm8352", 0 },
        { }
 };
 MODULE_DEVICE_TABLE(i2c, wm8350_i2c_id);
diff --git a/drivers/mfd/wm8350-regmap.c b/drivers/mfd/wm8350-regmap.c
index b43d64c2b920..3e2cc37961f3 100644
--- a/drivers/mfd/wm8350-regmap.c
+++ b/drivers/mfd/wm8350-regmap.c
@@ -1074,6 +1074,1058 @@ const u16 wm8350_mode3_defaults[] = {
 };
 #endif
 
+#ifdef CONFIG_MFD_WM8352_CONFIG_MODE_0
+
+#undef WM8350_HAVE_CONFIG_MODE
+#define WM8350_HAVE_CONFIG_MODE
+
+const u16 wm8352_mode0_defaults[] = {
+	0x6143,     /* R0   - Reset/ID */
+	0x0000,     /* R1   - ID */
+	0x0002,     /* R2   - Revision */
+	0x1C02,     /* R3   - System Control 1 */
+	0x0004,     /* R4   - System Control 2 */
+	0x0000,     /* R5   - System Hibernate */
+	0x8A00,     /* R6   - Interface Control */
+	0x0000,     /* R7 */
+	0x8000,     /* R8   - Power mgmt (1) */
+	0x0000,     /* R9   - Power mgmt (2) */
+	0x0000,     /* R10  - Power mgmt (3) */
+	0x2000,     /* R11  - Power mgmt (4) */
+	0x0E00,     /* R12  - Power mgmt (5) */
+	0x0000,     /* R13  - Power mgmt (6) */
+	0x0000,     /* R14  - Power mgmt (7) */
+	0x0000,     /* R15 */
+	0x0000,     /* R16  - RTC Seconds/Minutes */
+	0x0100,     /* R17  - RTC Hours/Day */
+	0x0101,     /* R18  - RTC Date/Month */
+	0x1400,     /* R19  - RTC Year */
+	0x0000,     /* R20  - Alarm Seconds/Minutes */
+	0x0000,     /* R21  - Alarm Hours/Day */
+	0x0000,     /* R22  - Alarm Date/Month */
+	0x0320,     /* R23  - RTC Time Control */
+	0x0000,     /* R24  - System Interrupts */
+	0x0000,     /* R25  - Interrupt Status 1 */
+	0x0000,     /* R26  - Interrupt Status 2 */
+	0x0000,     /* R27 */
+	0x0000,     /* R28  - Under Voltage Interrupt status */
+	0x0000,     /* R29  - Over Current Interrupt status */
+	0x0000,     /* R30  - GPIO Interrupt Status */
+	0x0000,     /* R31  - Comparator Interrupt Status */
+	0x3FFF,     /* R32  - System Interrupts Mask */
+	0x0000,     /* R33  - Interrupt Status 1 Mask */
+	0x0000,     /* R34  - Interrupt Status 2 Mask */
+	0x0000,     /* R35 */
+	0x0000,     /* R36  - Under Voltage Interrupt status Mask */
+	0x0000,     /* R37  - Over Current Interrupt status Mask */
+	0x0000,     /* R38  - GPIO Interrupt Status Mask */
+	0x0000,     /* R39  - Comparator Interrupt Status Mask */
+	0x0040,     /* R40  - Clock Control 1 */
+	0x0000,     /* R41  - Clock Control 2 */
+	0x3A00,     /* R42  - FLL Control 1 */
+	0x7086,     /* R43  - FLL Control 2 */
+	0xC226,     /* R44  - FLL Control 3 */
+	0x0000,     /* R45  - FLL Control 4 */
+	0x0000,     /* R46 */
+	0x0000,     /* R47 */
+	0x0000,     /* R48  - DAC Control */
+	0x0000,     /* R49 */
+	0x00C0,     /* R50  - DAC Digital Volume L */
+	0x00C0,     /* R51  - DAC Digital Volume R */
+	0x0000,     /* R52 */
+	0x0040,     /* R53  - DAC LR Rate */
+	0x0000,     /* R54  - DAC Clock Control */
+	0x0000,     /* R55 */
+	0x0000,     /* R56 */
+	0x0000,     /* R57 */
+	0x4000,     /* R58  - DAC Mute */
+	0x0000,     /* R59  - DAC Mute Volume */
+	0x0000,     /* R60  - DAC Side */
+	0x0000,     /* R61 */
+	0x0000,     /* R62 */
+	0x0000,     /* R63 */
+	0x8000,     /* R64  - ADC Control */
+	0x0000,     /* R65 */
+	0x00C0,     /* R66  - ADC Digital Volume L */
+	0x00C0,     /* R67  - ADC Digital Volume R */
+	0x0000,     /* R68  - ADC Divider */
+	0x0000,     /* R69 */
+	0x0040,     /* R70  - ADC LR Rate */
+	0x0000,     /* R71 */
+	0x0303,     /* R72  - Input Control */
+	0x0000,     /* R73  - IN3 Input Control */
+	0x0000,     /* R74  - Mic Bias Control */
+	0x0000,     /* R75 */
+	0x0000,     /* R76  - Output Control */
+	0x0000,     /* R77  - Jack Detect */
+	0x0000,     /* R78  - Anti Pop Control */
+	0x0000,     /* R79 */
+	0x0040,     /* R80  - Left Input Volume */
+	0x0040,     /* R81  - Right Input Volume */
+	0x0000,     /* R82 */
+	0x0000,     /* R83 */
+	0x0000,     /* R84 */
+	0x0000,     /* R85 */
+	0x0000,     /* R86 */
+	0x0000,     /* R87 */
+	0x0800,     /* R88  - Left Mixer Control */
+	0x1000,     /* R89  - Right Mixer Control */
+	0x0000,     /* R90 */
+	0x0000,     /* R91 */
+	0x0000,     /* R92  - OUT3 Mixer Control */
+	0x0000,     /* R93  - OUT4 Mixer Control */
+	0x0000,     /* R94 */
+	0x0000,     /* R95 */
+	0x0000,     /* R96  - Output Left Mixer Volume */
+	0x0000,     /* R97  - Output Right Mixer Volume */
+	0x0000,     /* R98  - Input Mixer Volume L */
+	0x0000,     /* R99  - Input Mixer Volume R */
+	0x0000,     /* R100 - Input Mixer Volume */
+	0x0000,     /* R101 */
+	0x0000,     /* R102 */
+	0x0000,     /* R103 */
+	0x00E4,     /* R104 - OUT1L Volume */
+	0x00E4,     /* R105 - OUT1R Volume */
+	0x00E4,     /* R106 - OUT2L Volume */
+	0x02E4,     /* R107 - OUT2R Volume */
+	0x0000,     /* R108 */
+	0x0000,     /* R109 */
+	0x0000,     /* R110 */
+	0x0000,     /* R111 - BEEP Volume */
+	0x0A00,     /* R112 - AI Formating */
+	0x0000,     /* R113 - ADC DAC COMP */
+	0x0020,     /* R114 - AI ADC Control */
+	0x0020,     /* R115 - AI DAC Control */
+	0x0000,     /* R116 */
+	0x0000,     /* R117 */
+	0x0000,     /* R118 */
+	0x0000,     /* R119 */
+	0x0000,     /* R120 */
+	0x0000,     /* R121 */
+	0x0000,     /* R122 */
+	0x0000,     /* R123 */
+	0x0000,     /* R124 */
+	0x0000,     /* R125 */
+	0x0000,     /* R126 */
+	0x0000,     /* R127 */
+	0x1FFF,     /* R128 - GPIO Debounce */
+	0x0000,     /* R129 - GPIO Pin pull up Control */
+	0x0000,     /* R130 - GPIO Pull down Control */
+	0x0000,     /* R131 - GPIO Interrupt Mode */
+	0x0000,     /* R132 */
+	0x0000,     /* R133 - GPIO Control */
+	0x0FFC,     /* R134 - GPIO Configuration (i/o) */
+	0x0FFC,     /* R135 - GPIO Pin Polarity / Type */
+	0x0000,     /* R136 */
+	0x0000,     /* R137 */
+	0x0000,     /* R138 */
+	0x0000,     /* R139 */
+	0x0013,     /* R140 - GPIO Function Select 1 */
+	0x0000,     /* R141 - GPIO Function Select 2 */
+	0x0000,     /* R142 - GPIO Function Select 3 */
+	0x0003,     /* R143 - GPIO Function Select 4 */
+	0x0000,     /* R144 - Digitiser Control (1) */
+	0x0002,     /* R145 - Digitiser Control (2) */
+	0x0000,     /* R146 */
+	0x0000,     /* R147 */
+	0x0000,     /* R148 */
+	0x0000,     /* R149 */
+	0x0000,     /* R150 */
+	0x0000,     /* R151 */
+	0x7000,     /* R152 - AUX1 Readback */
+	0x7000,     /* R153 - AUX2 Readback */
+	0x7000,     /* R154 - AUX3 Readback */
+	0x7000,     /* R155 - AUX4 Readback */
+	0x0000,     /* R156 - USB Voltage Readback */
+	0x0000,     /* R157 - LINE Voltage Readback */
+	0x0000,     /* R158 - BATT Voltage Readback */
+	0x0000,     /* R159 - Chip Temp Readback */
+	0x0000,     /* R160 */
+	0x0000,     /* R161 */
+	0x0000,     /* R162 */
+	0x0000,     /* R163 - Generic Comparator Control */
+	0x0000,     /* R164 - Generic comparator 1 */
+	0x0000,     /* R165 - Generic comparator 2 */
+	0x0000,     /* R166 - Generic comparator 3 */
+	0x0000,     /* R167 - Generic comparator 4 */
+	0xA00F,     /* R168 - Battery Charger Control 1 */
+	0x0B06,     /* R169 - Battery Charger Control 2 */
+	0x0000,     /* R170 - Battery Charger Control 3 */
+	0x0000,     /* R171 */
+	0x0000,     /* R172 - Current Sink Driver A */
+	0x0000,     /* R173 - CSA Flash control */
+	0x0000,     /* R174 - Current Sink Driver B */
+	0x0000,     /* R175 - CSB Flash control */
+	0x0000,     /* R176 - DCDC/LDO requested */
+	0x032D,     /* R177 - DCDC Active options */
+	0x0000,     /* R178 - DCDC Sleep options */
+	0x0025,     /* R179 - Power-check comparator */
+	0x000E,     /* R180 - DCDC1 Control */
+	0x0000,     /* R181 - DCDC1 Timeouts */
+	0x1006,     /* R182 - DCDC1 Low Power */
+	0x0018,     /* R183 - DCDC2 Control */
+	0x0000,     /* R184 - DCDC2 Timeouts */
+	0x0000,     /* R185 */
+	0x0000,     /* R186 - DCDC3 Control */
+	0x0000,     /* R187 - DCDC3 Timeouts */
+	0x0006,     /* R188 - DCDC3 Low Power */
+	0x0000,     /* R189 - DCDC4 Control */
+	0x0000,     /* R190 - DCDC4 Timeouts */
+	0x0006,     /* R191 - DCDC4 Low Power */
+	0x0008,     /* R192 - DCDC5 Control */
+	0x0000,     /* R193 - DCDC5 Timeouts */
+	0x0000,     /* R194 */
+	0x0000,     /* R195 - DCDC6 Control */
+	0x0000,     /* R196 - DCDC6 Timeouts */
+	0x0006,     /* R197 - DCDC6 Low Power */
+	0x0000,     /* R198 */
+	0x0003,     /* R199 - Limit Switch Control */
+	0x001C,     /* R200 - LDO1 Control */
+	0x0000,     /* R201 - LDO1 Timeouts */
+	0x001C,     /* R202 - LDO1 Low Power */
+	0x001B,     /* R203 - LDO2 Control */
+	0x0000,     /* R204 - LDO2 Timeouts */
+	0x001C,     /* R205 - LDO2 Low Power */
+	0x001B,     /* R206 - LDO3 Control */
+	0x0000,     /* R207 - LDO3 Timeouts */
+	0x001C,     /* R208 - LDO3 Low Power */
+	0x001B,     /* R209 - LDO4 Control */
+	0x0000,     /* R210 - LDO4 Timeouts */
+	0x001C,     /* R211 - LDO4 Low Power */
+	0x0000,     /* R212 */
+	0x0000,     /* R213 */
+	0x0000,     /* R214 */
+	0x0000,     /* R215 - VCC_FAULT Masks */
+	0x001F,     /* R216 - Main Bandgap Control */
+	0x0000,     /* R217 - OSC Control */
+	0x9000,     /* R218 - RTC Tick Control */
+	0x0000,     /* R219 - Security1 */
+	0x4000,     /* R220 */
+	0x0000,     /* R221 */
+	0x0000,     /* R222 */
+	0x0000,     /* R223 */
+	0x0000,     /* R224 - Signal overrides */
+	0x0000,     /* R225 - DCDC/LDO status */
+	0x0000,     /* R226 - Charger Overides/status */
+	0x0000,     /* R227 - misc overrides */
+	0x0000,     /* R228 - Supply overrides/status 1 */
+	0x0000,     /* R229 - Supply overrides/status 2 */
+	0xE000,     /* R230 - GPIO Pin Status */
+	0x0000,     /* R231 - comparotor overrides */
+	0x0000,     /* R232 */
+	0x0000,     /* R233 - State Machine status */
+	0x1200,     /* R234 */
+	0x0000,     /* R235 */
+	0x8000,     /* R236 */
+	0x0000,     /* R237 */
+	0x0000,     /* R238 */
+	0x0000,     /* R239 */
+	0x0003,     /* R240 */
+	0x0000,     /* R241 */
+	0x0000,     /* R242 */
+	0x0004,     /* R243 */
+	0x0300,     /* R244 */
+	0x0000,     /* R245 */
+	0x0200,     /* R246 */
+	0x0000,     /* R247 */
+	0x1000,     /* R248 - DCDC1 Test Controls */
+	0x5000,     /* R249 */
+	0x1000,     /* R250 - DCDC3 Test Controls */
+	0x1000,     /* R251 - DCDC4 Test Controls */
+	0x5100,     /* R252 */
+	0x1000,     /* R253 - DCDC6 Test Controls */
+};
+#endif
+
+#ifdef CONFIG_MFD_WM8352_CONFIG_MODE_1
+
+#undef WM8350_HAVE_CONFIG_MODE
+#define WM8350_HAVE_CONFIG_MODE
+
+const u16 wm8352_mode1_defaults[] = {
+	0x6143,     /* R0   - Reset/ID */
+	0x0000,     /* R1   - ID */
+	0x0002,     /* R2   - Revision */
+	0x1C02,     /* R3   - System Control 1 */
+	0x0204,     /* R4   - System Control 2 */
+	0x0000,     /* R5   - System Hibernate */
+	0x8A00,     /* R6   - Interface Control */
+	0x0000,     /* R7 */
+	0x8000,     /* R8   - Power mgmt (1) */
+	0x0000,     /* R9   - Power mgmt (2) */
+	0x0000,     /* R10  - Power mgmt (3) */
+	0x2000,     /* R11  - Power mgmt (4) */
+	0x0E00,     /* R12  - Power mgmt (5) */
+	0x0000,     /* R13  - Power mgmt (6) */
+	0x0000,     /* R14  - Power mgmt (7) */
+	0x0000,     /* R15 */
+	0x0000,     /* R16  - RTC Seconds/Minutes */
+	0x0100,     /* R17  - RTC Hours/Day */
+	0x0101,     /* R18  - RTC Date/Month */
+	0x1400,     /* R19  - RTC Year */
+	0x0000,     /* R20  - Alarm Seconds/Minutes */
+	0x0000,     /* R21  - Alarm Hours/Day */
+	0x0000,     /* R22  - Alarm Date/Month */
+	0x0320,     /* R23  - RTC Time Control */
+	0x0000,     /* R24  - System Interrupts */
+	0x0000,     /* R25  - Interrupt Status 1 */
+	0x0000,     /* R26  - Interrupt Status 2 */
+	0x0000,     /* R27 */
+	0x0000,     /* R28  - Under Voltage Interrupt status */
+	0x0000,     /* R29  - Over Current Interrupt status */
+	0x0000,     /* R30  - GPIO Interrupt Status */
+	0x0000,     /* R31  - Comparator Interrupt Status */
+	0x3FFF,     /* R32  - System Interrupts Mask */
+	0x0000,     /* R33  - Interrupt Status 1 Mask */
+	0x0000,     /* R34  - Interrupt Status 2 Mask */
+	0x0000,     /* R35 */
+	0x0000,     /* R36  - Under Voltage Interrupt status Mask */
+	0x0000,     /* R37  - Over Current Interrupt status Mask */
+	0x0000,     /* R38  - GPIO Interrupt Status Mask */
+	0x0000,     /* R39  - Comparator Interrupt Status Mask */
+	0x0040,     /* R40  - Clock Control 1 */
+	0x0000,     /* R41  - Clock Control 2 */
+	0x3A00,     /* R42  - FLL Control 1 */
+	0x7086,     /* R43  - FLL Control 2 */
+	0xC226,     /* R44  - FLL Control 3 */
+	0x0000,     /* R45  - FLL Control 4 */
+	0x0000,     /* R46 */
+	0x0000,     /* R47 */
+	0x0000,     /* R48  - DAC Control */
+	0x0000,     /* R49 */
+	0x00C0,     /* R50  - DAC Digital Volume L */
+	0x00C0,     /* R51  - DAC Digital Volume R */
+	0x0000,     /* R52 */
+	0x0040,     /* R53  - DAC LR Rate */
+	0x0000,     /* R54  - DAC Clock Control */
+	0x0000,     /* R55 */
+	0x0000,     /* R56 */
+	0x0000,     /* R57 */
+	0x4000,     /* R58  - DAC Mute */
+	0x0000,     /* R59  - DAC Mute Volume */
+	0x0000,     /* R60  - DAC Side */
+	0x0000,     /* R61 */
+	0x0000,     /* R62 */
+	0x0000,     /* R63 */
+	0x8000,     /* R64  - ADC Control */
+	0x0000,     /* R65 */
+	0x00C0,     /* R66  - ADC Digital Volume L */
+	0x00C0,     /* R67  - ADC Digital Volume R */
+	0x0000,     /* R68  - ADC Divider */
+	0x0000,     /* R69 */
+	0x0040,     /* R70  - ADC LR Rate */
+	0x0000,     /* R71 */
+	0x0303,     /* R72  - Input Control */
+	0x0000,     /* R73  - IN3 Input Control */
+	0x0000,     /* R74  - Mic Bias Control */
+	0x0000,     /* R75 */
+	0x0000,     /* R76  - Output Control */
+	0x0000,     /* R77  - Jack Detect */
+	0x0000,     /* R78  - Anti Pop Control */
+	0x0000,     /* R79 */
+	0x0040,     /* R80  - Left Input Volume */
+	0x0040,     /* R81  - Right Input Volume */
+	0x0000,     /* R82 */
+	0x0000,     /* R83 */
+	0x0000,     /* R84 */
+	0x0000,     /* R85 */
+	0x0000,     /* R86 */
+	0x0000,     /* R87 */
+	0x0800,     /* R88  - Left Mixer Control */
+	0x1000,     /* R89  - Right Mixer Control */
+	0x0000,     /* R90 */
+	0x0000,     /* R91 */
+	0x0000,     /* R92  - OUT3 Mixer Control */
+	0x0000,     /* R93  - OUT4 Mixer Control */
+	0x0000,     /* R94 */
+	0x0000,     /* R95 */
+	0x0000,     /* R96  - Output Left Mixer Volume */
+	0x0000,     /* R97  - Output Right Mixer Volume */
+	0x0000,     /* R98  - Input Mixer Volume L */
+	0x0000,     /* R99  - Input Mixer Volume R */
+	0x0000,     /* R100 - Input Mixer Volume */
+	0x0000,     /* R101 */
+	0x0000,     /* R102 */
+	0x0000,     /* R103 */
+	0x00E4,     /* R104 - OUT1L Volume */
+	0x00E4,     /* R105 - OUT1R Volume */
+	0x00E4,     /* R106 - OUT2L Volume */
+	0x02E4,     /* R107 - OUT2R Volume */
+	0x0000,     /* R108 */
+	0x0000,     /* R109 */
+	0x0000,     /* R110 */
+	0x0000,     /* R111 - BEEP Volume */
+	0x0A00,     /* R112 - AI Formating */
+	0x0000,     /* R113 - ADC DAC COMP */
+	0x0020,     /* R114 - AI ADC Control */
+	0x0020,     /* R115 - AI DAC Control */
+	0x0000,     /* R116 */
+	0x0000,     /* R117 */
+	0x0000,     /* R118 */
+	0x0000,     /* R119 */
+	0x0000,     /* R120 */
+	0x0000,     /* R121 */
+	0x0000,     /* R122 */
+	0x0000,     /* R123 */
+	0x0000,     /* R124 */
+	0x0000,     /* R125 */
+	0x0000,     /* R126 */
+	0x0000,     /* R127 */
+	0x1FFF,     /* R128 - GPIO Debounce */
+	0x0000,     /* R129 - GPIO Pin pull up Control */
+	0x0000,     /* R130 - GPIO Pull down Control */
+	0x0000,     /* R131 - GPIO Interrupt Mode */
+	0x0000,     /* R132 */
+	0x0000,     /* R133 - GPIO Control */
+	0x0BFB,     /* R134 - GPIO Configuration (i/o) */
+	0x0FFF,     /* R135 - GPIO Pin Polarity / Type */
+	0x0000,     /* R136 */
+	0x0000,     /* R137 */
+	0x0000,     /* R138 */
+	0x0000,     /* R139 */
+	0x0300,     /* R140 - GPIO Function Select 1 */
+	0x0000,     /* R141 - GPIO Function Select 2 */
+	0x2300,     /* R142 - GPIO Function Select 3 */
+	0x0003,     /* R143 - GPIO Function Select 4 */
+	0x0000,     /* R144 - Digitiser Control (1) */
+	0x0002,     /* R145 - Digitiser Control (2) */
+	0x0000,     /* R146 */
+	0x0000,     /* R147 */
+	0x0000,     /* R148 */
+	0x0000,     /* R149 */
+	0x0000,     /* R150 */
+	0x0000,     /* R151 */
+	0x7000,     /* R152 - AUX1 Readback */
+	0x7000,     /* R153 - AUX2 Readback */
+	0x7000,     /* R154 - AUX3 Readback */
+	0x7000,     /* R155 - AUX4 Readback */
+	0x0000,     /* R156 - USB Voltage Readback */
+	0x0000,     /* R157 - LINE Voltage Readback */
+	0x0000,     /* R158 - BATT Voltage Readback */
+	0x0000,     /* R159 - Chip Temp Readback */
+	0x0000,     /* R160 */
+	0x0000,     /* R161 */
+	0x0000,     /* R162 */
+	0x0000,     /* R163 - Generic Comparator Control */
+	0x0000,     /* R164 - Generic comparator 1 */
+	0x0000,     /* R165 - Generic comparator 2 */
+	0x0000,     /* R166 - Generic comparator 3 */
+	0x0000,     /* R167 - Generic comparator 4 */
+	0xA00F,     /* R168 - Battery Charger Control 1 */
+	0x0B06,     /* R169 - Battery Charger Control 2 */
+	0x0000,     /* R170 - Battery Charger Control 3 */
+	0x0000,     /* R171 */
+	0x0000,     /* R172 - Current Sink Driver A */
+	0x0000,     /* R173 - CSA Flash control */
+	0x0000,     /* R174 - Current Sink Driver B */
+	0x0000,     /* R175 - CSB Flash control */
+	0x0000,     /* R176 - DCDC/LDO requested */
+	0x032D,     /* R177 - DCDC Active options */
+	0x0000,     /* R178 - DCDC Sleep options */
+	0x0025,     /* R179 - Power-check comparator */
+	0x0062,     /* R180 - DCDC1 Control */
+	0x0400,     /* R181 - DCDC1 Timeouts */
+	0x1006,     /* R182 - DCDC1 Low Power */
+	0x0018,     /* R183 - DCDC2 Control */
+	0x0000,     /* R184 - DCDC2 Timeouts */
+	0x0000,     /* R185 */
+	0x0006,     /* R186 - DCDC3 Control */
+	0x0800,     /* R187 - DCDC3 Timeouts */
+	0x0006,     /* R188 - DCDC3 Low Power */
+	0x0006,     /* R189 - DCDC4 Control */
+	0x0C00,     /* R190 - DCDC4 Timeouts */
+	0x0006,     /* R191 - DCDC4 Low Power */
+	0x0008,     /* R192 - DCDC5 Control */
+	0x0000,     /* R193 - DCDC5 Timeouts */
+	0x0000,     /* R194 */
+	0x0026,     /* R195 - DCDC6 Control */
+	0x1000,     /* R196 - DCDC6 Timeouts */
+	0x0006,     /* R197 - DCDC6 Low Power */
+	0x0000,     /* R198 */
+	0x0003,     /* R199 - Limit Switch Control */
+	0x0002,     /* R200 - LDO1 Control */
+	0x0000,     /* R201 - LDO1 Timeouts */
+	0x001C,     /* R202 - LDO1 Low Power */
+	0x001A,     /* R203 - LDO2 Control */
+	0x0000,     /* R204 - LDO2 Timeouts */
+	0x001C,     /* R205 - LDO2 Low Power */
+	0x001F,     /* R206 - LDO3 Control */
+	0x0000,     /* R207 - LDO3 Timeouts */
+	0x001C,     /* R208 - LDO3 Low Power */
+	0x001F,     /* R209 - LDO4 Control */
+	0x0000,     /* R210 - LDO4 Timeouts */
+	0x001C,     /* R211 - LDO4 Low Power */
+	0x0000,     /* R212 */
+	0x0000,     /* R213 */
+	0x0000,     /* R214 */
+	0x0000,     /* R215 - VCC_FAULT Masks */
+	0x001F,     /* R216 - Main Bandgap Control */
+	0x0000,     /* R217 - OSC Control */
+	0x9000,     /* R218 - RTC Tick Control */
+	0x0000,     /* R219 - Security1 */
+	0x4000,     /* R220 */
+	0x0000,     /* R221 */
+	0x0000,     /* R222 */
+	0x0000,     /* R223 */
+	0x0000,     /* R224 - Signal overrides */
+	0x0000,     /* R225 - DCDC/LDO status */
+	0x0000,     /* R226 - Charger Overides/status */
+	0x0000,     /* R227 - misc overrides */
+	0x0000,     /* R228 - Supply overrides/status 1 */
+	0x0000,     /* R229 - Supply overrides/status 2 */
+	0xE000,     /* R230 - GPIO Pin Status */
+	0x0000,     /* R231 - comparotor overrides */
+	0x0000,     /* R232 */
+	0x0000,     /* R233 - State Machine status */
+	0x1200,     /* R234 */
+	0x0000,     /* R235 */
+	0x8000,     /* R236 */
+	0x0000,     /* R237 */
+	0x0000,     /* R238 */
+	0x0000,     /* R239 */
+	0x0003,     /* R240 */
+	0x0000,     /* R241 */
+	0x0000,     /* R242 */
+	0x0004,     /* R243 */
+	0x0300,     /* R244 */
+	0x0000,     /* R245 */
+	0x0200,     /* R246 */
+	0x0000,     /* R247 */
+	0x1000,     /* R248 - DCDC1 Test Controls */
+	0x5000,     /* R249 */
+	0x1000,     /* R250 - DCDC3 Test Controls */
+	0x1000,     /* R251 - DCDC4 Test Controls */
+	0x5100,     /* R252 */
+	0x1000,     /* R253 - DCDC6 Test Controls */
+};
+#endif
+
+#ifdef CONFIG_MFD_WM8352_CONFIG_MODE_2
+
+#undef WM8350_HAVE_CONFIG_MODE
+#define WM8350_HAVE_CONFIG_MODE
+
+const u16 wm8352_mode2_defaults[] = {
+	0x6143,     /* R0   - Reset/ID */
+	0x0000,     /* R1   - ID */
+	0x0002,     /* R2   - Revision */
+	0x1C02,     /* R3   - System Control 1 */
+	0x0204,     /* R4   - System Control 2 */
+	0x0000,     /* R5   - System Hibernate */
+	0x8A00,     /* R6   - Interface Control */
+	0x0000,     /* R7 */
+	0x8000,     /* R8   - Power mgmt (1) */
+	0x0000,     /* R9   - Power mgmt (2) */
+	0x0000,     /* R10  - Power mgmt (3) */
+	0x2000,     /* R11  - Power mgmt (4) */
+	0x0E00,     /* R12  - Power mgmt (5) */
+	0x0000,     /* R13  - Power mgmt (6) */
+	0x0000,     /* R14  - Power mgmt (7) */
+	0x0000,     /* R15 */
+	0x0000,     /* R16  - RTC Seconds/Minutes */
+	0x0100,     /* R17  - RTC Hours/Day */
+	0x0101,     /* R18  - RTC Date/Month */
+	0x1400,     /* R19  - RTC Year */
+	0x0000,     /* R20  - Alarm Seconds/Minutes */
+	0x0000,     /* R21  - Alarm Hours/Day */
+	0x0000,     /* R22  - Alarm Date/Month */
+	0x0320,     /* R23  - RTC Time Control */
+	0x0000,     /* R24  - System Interrupts */
+	0x0000,     /* R25  - Interrupt Status 1 */
+	0x0000,     /* R26  - Interrupt Status 2 */
+	0x0000,     /* R27 */
+	0x0000,     /* R28  - Under Voltage Interrupt status */
+	0x0000,     /* R29  - Over Current Interrupt status */
+	0x0000,     /* R30  - GPIO Interrupt Status */
+	0x0000,     /* R31  - Comparator Interrupt Status */
+	0x3FFF,     /* R32  - System Interrupts Mask */
+	0x0000,     /* R33  - Interrupt Status 1 Mask */
+	0x0000,     /* R34  - Interrupt Status 2 Mask */
+	0x0000,     /* R35 */
+	0x0000,     /* R36  - Under Voltage Interrupt status Mask */
+	0x0000,     /* R37  - Over Current Interrupt status Mask */
+	0x0000,     /* R38  - GPIO Interrupt Status Mask */
+	0x0000,     /* R39  - Comparator Interrupt Status Mask */
+	0x0040,     /* R40  - Clock Control 1 */
+	0x0000,     /* R41  - Clock Control 2 */
+	0x3A00,     /* R42  - FLL Control 1 */
+	0x7086,     /* R43  - FLL Control 2 */
+	0xC226,     /* R44  - FLL Control 3 */
+	0x0000,     /* R45  - FLL Control 4 */
+	0x0000,     /* R46 */
+	0x0000,     /* R47 */
+	0x0000,     /* R48  - DAC Control */
+	0x0000,     /* R49 */
+	0x00C0,     /* R50  - DAC Digital Volume L */
+	0x00C0,     /* R51  - DAC Digital Volume R */
+	0x0000,     /* R52 */
+	0x0040,     /* R53  - DAC LR Rate */
+	0x0000,     /* R54  - DAC Clock Control */
+	0x0000,     /* R55 */
+	0x0000,     /* R56 */
+	0x0000,     /* R57 */
+	0x4000,     /* R58  - DAC Mute */
+	0x0000,     /* R59  - DAC Mute Volume */
+	0x0000,     /* R60  - DAC Side */
+	0x0000,     /* R61 */
+	0x0000,     /* R62 */
+	0x0000,     /* R63 */
+	0x8000,     /* R64  - ADC Control */
+	0x0000,     /* R65 */
+	0x00C0,     /* R66  - ADC Digital Volume L */
+	0x00C0,     /* R67  - ADC Digital Volume R */
+	0x0000,     /* R68  - ADC Divider */
+	0x0000,     /* R69 */
+	0x0040,     /* R70  - ADC LR Rate */
+	0x0000,     /* R71 */
+	0x0303,     /* R72  - Input Control */
+	0x0000,     /* R73  - IN3 Input Control */
+	0x0000,     /* R74  - Mic Bias Control */
+	0x0000,     /* R75 */
+	0x0000,     /* R76  - Output Control */
+	0x0000,     /* R77  - Jack Detect */
+	0x0000,     /* R78  - Anti Pop Control */
+	0x0000,     /* R79 */
+	0x0040,     /* R80  - Left Input Volume */
+	0x0040,     /* R81  - Right Input Volume */
+	0x0000,     /* R82 */
+	0x0000,     /* R83 */
+	0x0000,     /* R84 */
+	0x0000,     /* R85 */
+	0x0000,     /* R86 */
+	0x0000,     /* R87 */
+	0x0800,     /* R88  - Left Mixer Control */
+	0x1000,     /* R89  - Right Mixer Control */
+	0x0000,     /* R90 */
+	0x0000,     /* R91 */
+	0x0000,     /* R92  - OUT3 Mixer Control */
+	0x0000,     /* R93  - OUT4 Mixer Control */
+	0x0000,     /* R94 */
+	0x0000,     /* R95 */
+	0x0000,     /* R96  - Output Left Mixer Volume */
+	0x0000,     /* R97  - Output Right Mixer Volume */
+	0x0000,     /* R98  - Input Mixer Volume L */
+	0x0000,     /* R99  - Input Mixer Volume R */
+	0x0000,     /* R100 - Input Mixer Volume */
+	0x0000,     /* R101 */
+	0x0000,     /* R102 */
+	0x0000,     /* R103 */
+	0x00E4,     /* R104 - OUT1L Volume */
+	0x00E4,     /* R105 - OUT1R Volume */
+	0x00E4,     /* R106 - OUT2L Volume */
+	0x02E4,     /* R107 - OUT2R Volume */
+	0x0000,     /* R108 */
+	0x0000,     /* R109 */
+	0x0000,     /* R110 */
+	0x0000,     /* R111 - BEEP Volume */
+	0x0A00,     /* R112 - AI Formating */
+	0x0000,     /* R113 - ADC DAC COMP */
+	0x0020,     /* R114 - AI ADC Control */
+	0x0020,     /* R115 - AI DAC Control */
+	0x0000,     /* R116 */
+	0x0000,     /* R117 */
+	0x0000,     /* R118 */
+	0x0000,     /* R119 */
+	0x0000,     /* R120 */
+	0x0000,     /* R121 */
+	0x0000,     /* R122 */
+	0x0000,     /* R123 */
+	0x0000,     /* R124 */
+	0x0000,     /* R125 */
+	0x0000,     /* R126 */
+	0x0000,     /* R127 */
+	0x1FFF,     /* R128 - GPIO Debounce */
+	0x0000,     /* R129 - GPIO Pin pull up Control */
+	0x0110,     /* R130 - GPIO Pull down Control */
+	0x0000,     /* R131 - GPIO Interrupt Mode */
+	0x0000,     /* R132 */
+	0x0000,     /* R133 - GPIO Control */
+	0x09DA,     /* R134 - GPIO Configuration (i/o) */
+	0x0DD6,     /* R135 - GPIO Pin Polarity / Type */
+	0x0000,     /* R136 */
+	0x0000,     /* R137 */
+	0x0000,     /* R138 */
+	0x0000,     /* R139 */
+	0x1310,     /* R140 - GPIO Function Select 1 */
+	0x0033,     /* R141 - GPIO Function Select 2 */
+	0x2000,     /* R142 - GPIO Function Select 3 */
+	0x0000,     /* R143 - GPIO Function Select 4 */
+	0x0000,     /* R144 - Digitiser Control (1) */
+	0x0002,     /* R145 - Digitiser Control (2) */
+	0x0000,     /* R146 */
+	0x0000,     /* R147 */
+	0x0000,     /* R148 */
+	0x0000,     /* R149 */
+	0x0000,     /* R150 */
+	0x0000,     /* R151 */
+	0x7000,     /* R152 - AUX1 Readback */
+	0x7000,     /* R153 - AUX2 Readback */
+	0x7000,     /* R154 - AUX3 Readback */
+	0x7000,     /* R155 - AUX4 Readback */
+	0x0000,     /* R156 - USB Voltage Readback */
+	0x0000,     /* R157 - LINE Voltage Readback */
+	0x0000,     /* R158 - BATT Voltage Readback */
+	0x0000,     /* R159 - Chip Temp Readback */
+	0x0000,     /* R160 */
+	0x0000,     /* R161 */
+	0x0000,     /* R162 */
+	0x0000,     /* R163 - Generic Comparator Control */
+	0x0000,     /* R164 - Generic comparator 1 */
+	0x0000,     /* R165 - Generic comparator 2 */
+	0x0000,     /* R166 - Generic comparator 3 */
+	0x0000,     /* R167 - Generic comparator 4 */
+	0xA00F,     /* R168 - Battery Charger Control 1 */
+	0x0B06,     /* R169 - Battery Charger Control 2 */
+	0x0000,     /* R170 - Battery Charger Control 3 */
+	0x0000,     /* R171 */
+	0x0000,     /* R172 - Current Sink Driver A */
+	0x0000,     /* R173 - CSA Flash control */
+	0x0000,     /* R174 - Current Sink Driver B */
+	0x0000,     /* R175 - CSB Flash control */
+	0x0000,     /* R176 - DCDC/LDO requested */
+	0x032D,     /* R177 - DCDC Active options */
+	0x0000,     /* R178 - DCDC Sleep options */
+	0x0025,     /* R179 - Power-check comparator */
+	0x000E,     /* R180 - DCDC1 Control */
+	0x0800,     /* R181 - DCDC1 Timeouts */
+	0x1006,     /* R182 - DCDC1 Low Power */
+	0x0018,     /* R183 - DCDC2 Control */
+	0x0000,     /* R184 - DCDC2 Timeouts */
+	0x0000,     /* R185 */
+	0x0056,     /* R186 - DCDC3 Control */
+	0x1800,     /* R187 - DCDC3 Timeouts */
+	0x0006,     /* R188 - DCDC3 Low Power */
+	0x000E,     /* R189 - DCDC4 Control */
+	0x1000,     /* R190 - DCDC4 Timeouts */
+	0x0006,     /* R191 - DCDC4 Low Power */
+	0x0008,     /* R192 - DCDC5 Control */
+	0x0000,     /* R193 - DCDC5 Timeouts */
+	0x0000,     /* R194 */
+	0x0026,     /* R195 - DCDC6 Control */
+	0x0C00,     /* R196 - DCDC6 Timeouts */
+	0x0006,     /* R197 - DCDC6 Low Power */
+	0x0000,     /* R198 */
+	0x0003,     /* R199 - Limit Switch Control */
+	0x001C,     /* R200 - LDO1 Control */
+	0x0000,     /* R201 - LDO1 Timeouts */
+	0x001C,     /* R202 - LDO1 Low Power */
+	0x0006,     /* R203 - LDO2 Control */
+	0x0400,     /* R204 - LDO2 Timeouts */
+	0x001C,     /* R205 - LDO2 Low Power */
+	0x001C,     /* R206 - LDO3 Control */
+	0x1400,     /* R207 - LDO3 Timeouts */
+	0x001C,     /* R208 - LDO3 Low Power */
+	0x001A,     /* R209 - LDO4 Control */
+	0x0000,     /* R210 - LDO4 Timeouts */
+	0x001C,     /* R211 - LDO4 Low Power */
+	0x0000,     /* R212 */
+	0x0000,     /* R213 */
+	0x0000,     /* R214 */
+	0x0000,     /* R215 - VCC_FAULT Masks */
+	0x001F,     /* R216 - Main Bandgap Control */
+	0x0000,     /* R217 - OSC Control */
+	0x9000,     /* R218 - RTC Tick Control */
+	0x0000,     /* R219 - Security1 */
+	0x4000,     /* R220 */
+	0x0000,     /* R221 */
+	0x0000,     /* R222 */
+	0x0000,     /* R223 */
+	0x0000,     /* R224 - Signal overrides */
+	0x0000,     /* R225 - DCDC/LDO status */
+	0x0000,     /* R226 - Charger Overides/status */
+	0x0000,     /* R227 - misc overrides */
+	0x0000,     /* R228 - Supply overrides/status 1 */
+	0x0000,     /* R229 - Supply overrides/status 2 */
+	0xE000,     /* R230 - GPIO Pin Status */
+	0x0000,     /* R231 - comparotor overrides */
+	0x0000,     /* R232 */
+	0x0000,     /* R233 - State Machine status */
+	0x1200,     /* R234 */
+	0x0000,     /* R235 */
+	0x8000,     /* R236 */
+	0x0000,     /* R237 */
+	0x0000,     /* R238 */
+	0x0000,     /* R239 */
+	0x0003,     /* R240 */
+	0x0000,     /* R241 */
+	0x0000,     /* R242 */
+	0x0004,     /* R243 */
+	0x0300,     /* R244 */
+	0x0000,     /* R245 */
+	0x0200,     /* R246 */
+	0x0000,     /* R247 */
+	0x1000,     /* R248 - DCDC1 Test Controls */
+	0x5000,     /* R249 */
+	0x1000,     /* R250 - DCDC3 Test Controls */
+	0x1000,     /* R251 - DCDC4 Test Controls */
+	0x5100,     /* R252 */
+	0x1000,     /* R253 - DCDC6 Test Controls */
+};
+#endif
+
+#ifdef CONFIG_MFD_WM8352_CONFIG_MODE_3
+
+#undef WM8350_HAVE_CONFIG_MODE
+#define WM8350_HAVE_CONFIG_MODE
+
+const u16 wm8352_mode3_defaults[] = {
+	0x6143,     /* R0   - Reset/ID */
+	0x0000,     /* R1   - ID */
+	0x0002,     /* R2   - Revision */
+	0x1C02,     /* R3   - System Control 1 */
+	0x0204,     /* R4   - System Control 2 */
+	0x0000,     /* R5   - System Hibernate */
+	0x8A00,     /* R6   - Interface Control */
+	0x0000,     /* R7 */
+	0x8000,     /* R8   - Power mgmt (1) */
+	0x0000,     /* R9   - Power mgmt (2) */
+	0x0000,     /* R10  - Power mgmt (3) */
+	0x2000,     /* R11  - Power mgmt (4) */
+	0x0E00,     /* R12  - Power mgmt (5) */
+	0x0000,     /* R13  - Power mgmt (6) */
+	0x0000,     /* R14  - Power mgmt (7) */
+	0x0000,     /* R15 */
+	0x0000,     /* R16  - RTC Seconds/Minutes */
+	0x0100,     /* R17  - RTC Hours/Day */
+	0x0101,     /* R18  - RTC Date/Month */
+	0x1400,     /* R19  - RTC Year */
+	0x0000,     /* R20  - Alarm Seconds/Minutes */
+	0x0000,     /* R21  - Alarm Hours/Day */
+	0x0000,     /* R22  - Alarm Date/Month */
+	0x0320,     /* R23  - RTC Time Control */
+	0x0000,     /* R24  - System Interrupts */
+	0x0000,     /* R25  - Interrupt Status 1 */
+	0x0000,     /* R26  - Interrupt Status 2 */
+	0x0000,     /* R27 */
+	0x0000,     /* R28  - Under Voltage Interrupt status */
+	0x0000,     /* R29  - Over Current Interrupt status */
+	0x0000,     /* R30  - GPIO Interrupt Status */
+	0x0000,     /* R31  - Comparator Interrupt Status */
+	0x3FFF,     /* R32  - System Interrupts Mask */
+	0x0000,     /* R33  - Interrupt Status 1 Mask */
+	0x0000,     /* R34  - Interrupt Status 2 Mask */
+	0x0000,     /* R35 */
+	0x0000,     /* R36  - Under Voltage Interrupt status Mask */
+	0x0000,     /* R37  - Over Current Interrupt status Mask */
+	0x0000,     /* R38  - GPIO Interrupt Status Mask */
+	0x0000,     /* R39  - Comparator Interrupt Status Mask */
+	0x0040,     /* R40  - Clock Control 1 */
+	0x0000,     /* R41  - Clock Control 2 */
+	0x3A00,     /* R42  - FLL Control 1 */
+	0x7086,     /* R43  - FLL Control 2 */
+	0xC226,     /* R44  - FLL Control 3 */
+	0x0000,     /* R45  - FLL Control 4 */
+	0x0000,     /* R46 */
+	0x0000,     /* R47 */
+	0x0000,     /* R48  - DAC Control */
+	0x0000,     /* R49 */
+	0x00C0,     /* R50  - DAC Digital Volume L */
+	0x00C0,     /* R51  - DAC Digital Volume R */
+	0x0000,     /* R52 */
+	0x0040,     /* R53  - DAC LR Rate */
+	0x0000,     /* R54  - DAC Clock Control */
+	0x0000,     /* R55 */
+	0x0000,     /* R56 */
+	0x0000,     /* R57 */
+	0x4000,     /* R58  - DAC Mute */
+	0x0000,     /* R59  - DAC Mute Volume */
+	0x0000,     /* R60  - DAC Side */
+	0x0000,     /* R61 */
+	0x0000,     /* R62 */
+	0x0000,     /* R63 */
+	0x8000,     /* R64  - ADC Control */
+	0x0000,     /* R65 */
+	0x00C0,     /* R66  - ADC Digital Volume L */
+	0x00C0,     /* R67  - ADC Digital Volume R */
+	0x0000,     /* R68  - ADC Divider */
+	0x0000,     /* R69 */
+	0x0040,     /* R70  - ADC LR Rate */
+	0x0000,     /* R71 */
+	0x0303,     /* R72  - Input Control */
+	0x0000,     /* R73  - IN3 Input Control */
+	0x0000,     /* R74  - Mic Bias Control */
+	0x0000,     /* R75 */
+	0x0000,     /* R76  - Output Control */
+	0x0000,     /* R77  - Jack Detect */
+	0x0000,     /* R78  - Anti Pop Control */
+	0x0000,     /* R79 */
+	0x0040,     /* R80  - Left Input Volume */
+	0x0040,     /* R81  - Right Input Volume */
+	0x0000,     /* R82 */
+	0x0000,     /* R83 */
+	0x0000,     /* R84 */
+	0x0000,     /* R85 */
+	0x0000,     /* R86 */
+	0x0000,     /* R87 */
+	0x0800,     /* R88  - Left Mixer Control */
+	0x1000,     /* R89  - Right Mixer Control */
+	0x0000,     /* R90 */
+	0x0000,     /* R91 */
+	0x0000,     /* R92  - OUT3 Mixer Control */
+	0x0000,     /* R93  - OUT4 Mixer Control */
+	0x0000,     /* R94 */
+	0x0000,     /* R95 */
+	0x0000,     /* R96  - Output Left Mixer Volume */
+	0x0000,     /* R97  - Output Right Mixer Volume */
+	0x0000,     /* R98  - Input Mixer Volume L */
+	0x0000,     /* R99  - Input Mixer Volume R */
+	0x0000,     /* R100 - Input Mixer Volume */
+	0x0000,     /* R101 */
+	0x0000,     /* R102 */
+	0x0000,     /* R103 */
+	0x00E4,     /* R104 - OUT1L Volume */
+	0x00E4,     /* R105 - OUT1R Volume */
+	0x00E4,     /* R106 - OUT2L Volume */
+	0x02E4,     /* R107 - OUT2R Volume */
+	0x0000,     /* R108 */
+	0x0000,     /* R109 */
+	0x0000,     /* R110 */
+	0x0000,     /* R111 - BEEP Volume */
+	0x0A00,     /* R112 - AI Formating */
+	0x0000,     /* R113 - ADC DAC COMP */
+	0x0020,     /* R114 - AI ADC Control */
+	0x0020,     /* R115 - AI DAC Control */
+	0x0000,     /* R116 */
+	0x0000,     /* R117 */
+	0x0000,     /* R118 */
+	0x0000,     /* R119 */
+	0x0000,     /* R120 */
+	0x0000,     /* R121 */
+	0x0000,     /* R122 */
+	0x0000,     /* R123 */
+	0x0000,     /* R124 */
+	0x0000,     /* R125 */
+	0x0000,     /* R126 */
+	0x0000,     /* R127 */
+	0x1FFF,     /* R128 - GPIO Debounce */
+	0x0010,     /* R129 - GPIO Pin pull up Control */
+	0x0000,     /* R130 - GPIO Pull down Control */
+	0x0000,     /* R131 - GPIO Interrupt Mode */
+	0x0000,     /* R132 */
+	0x0000,     /* R133 - GPIO Control */
+	0x0BFB,     /* R134 - GPIO Configuration (i/o) */
+	0x0FFD,     /* R135 - GPIO Pin Polarity / Type */
+	0x0000,     /* R136 */
+	0x0000,     /* R137 */
+	0x0000,     /* R138 */
+	0x0000,     /* R139 */
+	0x0310,     /* R140 - GPIO Function Select 1 */
+	0x0001,     /* R141 - GPIO Function Select 2 */
+	0x2300,     /* R142 - GPIO Function Select 3 */
+	0x0003,     /* R143 - GPIO Function Select 4 */
+	0x0000,     /* R144 - Digitiser Control (1) */
+	0x0002,     /* R145 - Digitiser Control (2) */
+	0x0000,     /* R146 */
+	0x0000,     /* R147 */
+	0x0000,     /* R148 */
+	0x0000,     /* R149 */
+	0x0000,     /* R150 */
+	0x0000,     /* R151 */
+	0x7000,     /* R152 - AUX1 Readback */
+	0x7000,     /* R153 - AUX2 Readback */
+	0x7000,     /* R154 - AUX3 Readback */
+	0x7000,     /* R155 - AUX4 Readback */
+	0x0000,     /* R156 - USB Voltage Readback */
+	0x0000,     /* R157 - LINE Voltage Readback */
+	0x0000,     /* R158 - BATT Voltage Readback */
+	0x0000,     /* R159 - Chip Temp Readback */
+	0x0000,     /* R160 */
+	0x0000,     /* R161 */
+	0x0000,     /* R162 */
+	0x0000,     /* R163 - Generic Comparator Control */
+	0x0000,     /* R164 - Generic comparator 1 */
+	0x0000,     /* R165 - Generic comparator 2 */
+	0x0000,     /* R166 - Generic comparator 3 */
+	0x0000,     /* R167 - Generic comparator 4 */
+	0xA00F,     /* R168 - Battery Charger Control 1 */
+	0x0B06,     /* R169 - Battery Charger Control 2 */
+	0x0000,     /* R170 - Battery Charger Control 3 */
+	0x0000,     /* R171 */
+	0x0000,     /* R172 - Current Sink Driver A */
+	0x0000,     /* R173 - CSA Flash control */
+	0x0000,     /* R174 - Current Sink Driver B */
+	0x0000,     /* R175 - CSB Flash control */
+	0x0000,     /* R176 - DCDC/LDO requested */
+	0x032D,     /* R177 - DCDC Active options */
+	0x0000,     /* R178 - DCDC Sleep options */
+	0x0025,     /* R179 - Power-check comparator */
+	0x0006,     /* R180 - DCDC1 Control */
+	0x0400,     /* R181 - DCDC1 Timeouts */
+	0x1006,     /* R182 - DCDC1 Low Power */
+	0x0018,     /* R183 - DCDC2 Control */
+	0x0000,     /* R184 - DCDC2 Timeouts */
+	0x0000,     /* R185 */
+	0x0050,     /* R186 - DCDC3 Control */
+	0x0C00,     /* R187 - DCDC3 Timeouts */
+	0x0006,     /* R188 - DCDC3 Low Power */
+	0x000E,     /* R189 - DCDC4 Control */
+	0x0400,     /* R190 - DCDC4 Timeouts */
+	0x0006,     /* R191 - DCDC4 Low Power */
+	0x0008,     /* R192 - DCDC5 Control */
+	0x0000,     /* R193 - DCDC5 Timeouts */
+	0x0000,     /* R194 */
+	0x0029,     /* R195 - DCDC6 Control */
+	0x0800,     /* R196 - DCDC6 Timeouts */
+	0x0006,     /* R197 - DCDC6 Low Power */
+	0x0000,     /* R198 */
+	0x0003,     /* R199 - Limit Switch Control */
+	0x001D,     /* R200 - LDO1 Control */
+	0x1000,     /* R201 - LDO1 Timeouts */
+	0x001C,     /* R202 - LDO1 Low Power */
+	0x0017,     /* R203 - LDO2 Control */
+	0x1000,     /* R204 - LDO2 Timeouts */
+	0x001C,     /* R205 - LDO2 Low Power */
+	0x0006,     /* R206 - LDO3 Control */
+	0x1000,     /* R207 - LDO3 Timeouts */
+	0x001C,     /* R208 - LDO3 Low Power */
+	0x0010,     /* R209 - LDO4 Control */
+	0x1000,     /* R210 - LDO4 Timeouts */
+	0x001C,     /* R211 - LDO4 Low Power */
+	0x0000,     /* R212 */
+	0x0000,     /* R213 */
+	0x0000,     /* R214 */
+	0x0000,     /* R215 - VCC_FAULT Masks */
+	0x001F,     /* R216 - Main Bandgap Control */
+	0x0000,     /* R217 - OSC Control */
+	0x9000,     /* R218 - RTC Tick Control */
+	0x0000,     /* R219 - Security1 */
+	0x4000,     /* R220 */
+	0x0000,     /* R221 */
+	0x0000,     /* R222 */
+	0x0000,     /* R223 */
+	0x0000,     /* R224 - Signal overrides */
+	0x0000,     /* R225 - DCDC/LDO status */
+	0x0000,     /* R226 - Charger Overides/status */
+	0x0000,     /* R227 - misc overrides */
+	0x0000,     /* R228 - Supply overrides/status 1 */
+	0x0000,     /* R229 - Supply overrides/status 2 */
+	0xE000,     /* R230 - GPIO Pin Status */
+	0x0000,     /* R231 - comparotor overrides */
+	0x0000,     /* R232 */
+	0x0000,     /* R233 - State Machine status */
+	0x1200,     /* R234 */
+	0x0000,     /* R235 */
+	0x8000,     /* R236 */
+	0x0000,     /* R237 */
+	0x0000,     /* R238 */
+	0x0000,     /* R239 */
+	0x0003,     /* R240 */
+	0x0000,     /* R241 */
+	0x0000,     /* R242 */
+	0x0004,     /* R243 */
+	0x0300,     /* R244 */
+	0x0000,     /* R245 */
+	0x0200,     /* R246 */
+	0x0000,     /* R247 */
+	0x1000,     /* R248 - DCDC1 Test Controls */
+	0x5000,     /* R249 */
+	0x1000,     /* R250 - DCDC3 Test Controls */
+	0x1000,     /* R251 - DCDC4 Test Controls */
+	0x5100,     /* R252 */
+	0x1000,     /* R253 - DCDC6 Test Controls */
+};
+#endif
+
 /* The register defaults for the config mode used must be compiled in but
  * due to the impact on kernel size it is possible to disable
  */
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index afeff6f1316c..737579086d01 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -589,6 +589,10 @@ extern const u16 wm8350_mode0_defaults[];
 extern const u16 wm8350_mode1_defaults[];
 extern const u16 wm8350_mode2_defaults[];
 extern const u16 wm8350_mode3_defaults[];
+extern const u16 wm8352_mode0_defaults[];
+extern const u16 wm8352_mode1_defaults[];
+extern const u16 wm8352_mode2_defaults[];
+extern const u16 wm8352_mode3_defaults[];
 
 struct wm8350;
 
-- 
cgit v1.2.3-70-g09d2


From 645524a9c6e1e42dc4fe03217befb20e2fc4d43e Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Thu, 18 Dec 2008 23:12:16 +0100
Subject: mfd: Support configurable numbers of DCDCs and ISINKs on WM8350

Some WM8350 variants have fewer DCDCs and ISINKs. Identify these at
probe and refuse to use the absent DCDCs when running on these chips.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/wm8350-core.c            | 6 ++++++
 drivers/regulator/wm8350-regulator.c | 7 +++++++
 include/linux/mfd/wm8350/pmic.h      | 4 ++++
 3 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index 03af3b12c020..56c363c240a9 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -1301,6 +1301,9 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 
 	switch (mask_rev) {
 	case 0:
+		wm8350->pmic.max_dcdc = WM8350_DCDC_6;
+		wm8350->pmic.max_isink = WM8350_ISINK_B;
+
 		switch (chip_rev) {
 		case WM8350_REV_E:
 			dev_info(wm8350->dev, "WM8350 Rev E\n");
@@ -1325,6 +1328,9 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 		break;
 
 	case 2:
+		wm8350->pmic.max_dcdc = WM8350_DCDC_6;
+		wm8350->pmic.max_isink = WM8350_ISINK_B;
+
 		switch (chip_rev) {
 		case 0:
 			dev_info(wm8350->dev, "WM8352 Rev A\n");
diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c
index 1f44b17e23b1..c68c496b2c49 100644
--- a/drivers/regulator/wm8350-regulator.c
+++ b/drivers/regulator/wm8350-regulator.c
@@ -1380,6 +1380,13 @@ int wm8350_register_regulator(struct wm8350 *wm8350, int reg,
 	if (wm8350->pmic.pdev[reg])
 		return -EBUSY;
 
+	if (reg >= WM8350_DCDC_1 && reg <= WM8350_DCDC_6 &&
+	    reg > wm8350->pmic.max_dcdc)
+		return -ENODEV;
+	if (reg >= WM8350_ISINK_A && reg <= WM8350_ISINK_B &&
+	    reg > wm8350->pmic.max_isink)
+		return -ENODEV;
+
 	pdev = platform_device_alloc("wm8350-regulator", reg);
 	if (!pdev)
 		return -ENOMEM;
diff --git a/include/linux/mfd/wm8350/pmic.h b/include/linux/mfd/wm8350/pmic.h
index 69b69e07f62f..96acbfc8aa12 100644
--- a/include/linux/mfd/wm8350/pmic.h
+++ b/include/linux/mfd/wm8350/pmic.h
@@ -701,6 +701,10 @@ struct platform_device;
 struct regulator_init_data;
 
 struct wm8350_pmic {
+	/* Number of regulators of each type on this device */
+	int max_dcdc;
+	int max_isink;
+
 	/* ISINK to DCDC mapping */
 	int isink_A_dcdc;
 	int isink_B_dcdc;
-- 
cgit v1.2.3-70-g09d2


From ca23f8c1b0aa15dc69565244fc5dffa67a72dd02 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Thu, 18 Dec 2008 23:12:28 +0100
Subject: mfd: Add WM8351 support

The WM8351 is a WM8350 variant. As well as register default changes the
WM8351 has fewer voltage and current regulators than the WM8350.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/Kconfig             |   16 +
 drivers/mfd/wm8350-core.c       |   47 ++
 drivers/mfd/wm8350-i2c.c        |    1 +
 drivers/mfd/wm8350-regmap.c     | 1044 +++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/wm8350/core.h |    4 +
 5 files changed, 1112 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 76a482dfc177..781a27955ff5 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -143,6 +143,22 @@ config MFD_WM8350_CONFIG_MODE_3
 	bool
 	depends on MFD_WM8350
 
+config MFD_WM8351_CONFIG_MODE_0
+	bool
+	depends on MFD_WM8350
+
+config MFD_WM8351_CONFIG_MODE_1
+	bool
+	depends on MFD_WM8350
+
+config MFD_WM8351_CONFIG_MODE_2
+	bool
+	depends on MFD_WM8350
+
+config MFD_WM8351_CONFIG_MODE_3
+	bool
+	depends on MFD_WM8350
+
 config MFD_WM8352_CONFIG_MODE_0
 	bool
 	depends on MFD_WM8350
diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index 56c363c240a9..e03fe60b55bf 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -1169,6 +1169,36 @@ static int wm8350_create_cache(struct wm8350 *wm8350, int type, int mode)
 			return -EINVAL;
 		}
 
+	case 1:
+		switch (mode) {
+#ifdef CONFIG_MFD_WM8351_CONFIG_MODE_0
+		case 0:
+			reg_map = wm8351_mode0_defaults;
+			break;
+#endif
+#ifdef CONFIG_MFD_WM8351_CONFIG_MODE_1
+		case 1:
+			reg_map = wm8351_mode1_defaults;
+			break;
+#endif
+#ifdef CONFIG_MFD_WM8351_CONFIG_MODE_2
+		case 2:
+			reg_map = wm8351_mode2_defaults;
+			break;
+#endif
+#ifdef CONFIG_MFD_WM8351_CONFIG_MODE_3
+		case 3:
+			reg_map = wm8351_mode3_defaults;
+			break;
+#endif
+		default:
+			dev_err(wm8350->dev,
+				"WM8351 configuration mode %d not supported\n",
+				mode);
+			return -EINVAL;
+		}
+		break;
+
 	case 2:
 		switch (mode) {
 #ifdef CONFIG_MFD_WM8352_CONFIG_MODE_0
@@ -1327,6 +1357,23 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 		}
 		break;
 
+	case 1:
+		wm8350->pmic.max_dcdc = WM8350_DCDC_4;
+		wm8350->pmic.max_isink = WM8350_ISINK_A;
+
+		switch (chip_rev) {
+		case 0:
+			dev_info(wm8350->dev, "WM8351 Rev A\n");
+			wm8350->power.rev_g_coeff = 1;
+			break;
+
+		default:
+			dev_err(wm8350->dev, "Unknown WM8351 CHIP_REV\n");
+			ret = -ENODEV;
+			goto err;
+		}
+		break;
+
 	case 2:
 		wm8350->pmic.max_dcdc = WM8350_DCDC_6;
 		wm8350->pmic.max_isink = WM8350_ISINK_B;
diff --git a/drivers/mfd/wm8350-i2c.c b/drivers/mfd/wm8350-i2c.c
index 878051253084..8d8c93217572 100644
--- a/drivers/mfd/wm8350-i2c.c
+++ b/drivers/mfd/wm8350-i2c.c
@@ -97,6 +97,7 @@ static int wm8350_i2c_remove(struct i2c_client *i2c)
 
 static const struct i2c_device_id wm8350_i2c_id[] = {
        { "wm8350", 0 },
+       { "wm8351", 0 },
        { "wm8352", 0 },
        { }
 };
diff --git a/drivers/mfd/wm8350-regmap.c b/drivers/mfd/wm8350-regmap.c
index 3e2cc37961f3..68887b817d17 100644
--- a/drivers/mfd/wm8350-regmap.c
+++ b/drivers/mfd/wm8350-regmap.c
@@ -1074,6 +1074,1050 @@ const u16 wm8350_mode3_defaults[] = {
 };
 #endif
 
+#ifdef CONFIG_MFD_WM8351_CONFIG_MODE_0
+
+#undef WM8350_HAVE_CONFIG_MODE
+#define WM8350_HAVE_CONFIG_MODE
+
+const u16 wm8351_mode0_defaults[] = {
+	0x6143,     /* R0   - Reset/ID */
+	0x0000,     /* R1   - ID */
+	0x0001,     /* R2   - Revision */
+	0x1C02,     /* R3   - System Control 1 */
+	0x0004,     /* R4   - System Control 2 */
+	0x0000,     /* R5   - System Hibernate */
+	0x8A00,     /* R6   - Interface Control */
+	0x0000,     /* R7 */
+	0x8000,     /* R8   - Power mgmt (1) */
+	0x0000,     /* R9   - Power mgmt (2) */
+	0x0000,     /* R10  - Power mgmt (3) */
+	0x2000,     /* R11  - Power mgmt (4) */
+	0x0E00,     /* R12  - Power mgmt (5) */
+	0x0000,     /* R13  - Power mgmt (6) */
+	0x0000,     /* R14  - Power mgmt (7) */
+	0x0000,     /* R15 */
+	0x0000,     /* R16  - RTC Seconds/Minutes */
+	0x0100,     /* R17  - RTC Hours/Day */
+	0x0101,     /* R18  - RTC Date/Month */
+	0x1400,     /* R19  - RTC Year */
+	0x0000,     /* R20  - Alarm Seconds/Minutes */
+	0x0000,     /* R21  - Alarm Hours/Day */
+	0x0000,     /* R22  - Alarm Date/Month */
+	0x0320,     /* R23  - RTC Time Control */
+	0x0000,     /* R24  - System Interrupts */
+	0x0000,     /* R25  - Interrupt Status 1 */
+	0x0000,     /* R26  - Interrupt Status 2 */
+	0x0000,     /* R27 */
+	0x0000,     /* R28  - Under Voltage Interrupt status */
+	0x0000,     /* R29  - Over Current Interrupt status */
+	0x0000,     /* R30  - GPIO Interrupt Status */
+	0x0000,     /* R31  - Comparator Interrupt Status */
+	0x3FFF,     /* R32  - System Interrupts Mask */
+	0x0000,     /* R33  - Interrupt Status 1 Mask */
+	0x0000,     /* R34  - Interrupt Status 2 Mask */
+	0x0000,     /* R35 */
+	0x0000,     /* R36  - Under Voltage Interrupt status Mask */
+	0x0000,     /* R37  - Over Current Interrupt status Mask */
+	0x0000,     /* R38  - GPIO Interrupt Status Mask */
+	0x0000,     /* R39  - Comparator Interrupt Status Mask */
+	0x0040,     /* R40  - Clock Control 1 */
+	0x0000,     /* R41  - Clock Control 2 */
+	0x3A00,     /* R42  - FLL Control 1 */
+	0x7086,     /* R43  - FLL Control 2 */
+	0xC226,     /* R44  - FLL Control 3 */
+	0x0000,     /* R45  - FLL Control 4 */
+	0x0000,     /* R46 */
+	0x0000,     /* R47 */
+	0x0000,     /* R48  - DAC Control */
+	0x0000,     /* R49 */
+	0x00C0,     /* R50  - DAC Digital Volume L */
+	0x00C0,     /* R51  - DAC Digital Volume R */
+	0x0000,     /* R52 */
+	0x0040,     /* R53  - DAC LR Rate */
+	0x0000,     /* R54  - DAC Clock Control */
+	0x0000,     /* R55 */
+	0x0000,     /* R56 */
+	0x0000,     /* R57 */
+	0x4000,     /* R58  - DAC Mute */
+	0x0000,     /* R59  - DAC Mute Volume */
+	0x0000,     /* R60  - DAC Side */
+	0x0000,     /* R61 */
+	0x0000,     /* R62 */
+	0x0000,     /* R63 */
+	0x8000,     /* R64  - ADC Control */
+	0x0000,     /* R65 */
+	0x00C0,     /* R66  - ADC Digital Volume L */
+	0x00C0,     /* R67  - ADC Digital Volume R */
+	0x0000,     /* R68  - ADC Divider */
+	0x0000,     /* R69 */
+	0x0040,     /* R70  - ADC LR Rate */
+	0x0000,     /* R71 */
+	0x0303,     /* R72  - Input Control */
+	0x0000,     /* R73  - IN3 Input Control */
+	0x0000,     /* R74  - Mic Bias Control */
+	0x0000,     /* R75 */
+	0x0000,     /* R76  - Output Control */
+	0x0000,     /* R77  - Jack Detect */
+	0x0000,     /* R78  - Anti Pop Control */
+	0x0000,     /* R79 */
+	0x0040,     /* R80  - Left Input Volume */
+	0x0040,     /* R81  - Right Input Volume */
+	0x0000,     /* R82 */
+	0x0000,     /* R83 */
+	0x0000,     /* R84 */
+	0x0000,     /* R85 */
+	0x0000,     /* R86 */
+	0x0000,     /* R87 */
+	0x0800,     /* R88  - Left Mixer Control */
+	0x1000,     /* R89  - Right Mixer Control */
+	0x0000,     /* R90 */
+	0x0000,     /* R91 */
+	0x0000,     /* R92  - OUT3 Mixer Control */
+	0x0000,     /* R93  - OUT4 Mixer Control */
+	0x0000,     /* R94 */
+	0x0000,     /* R95 */
+	0x0000,     /* R96  - Output Left Mixer Volume */
+	0x0000,     /* R97  - Output Right Mixer Volume */
+	0x0000,     /* R98  - Input Mixer Volume L */
+	0x0000,     /* R99  - Input Mixer Volume R */
+	0x0000,     /* R100 - Input Mixer Volume */
+	0x0000,     /* R101 */
+	0x0000,     /* R102 */
+	0x0000,     /* R103 */
+	0x00E4,     /* R104 - OUT1L Volume */
+	0x00E4,     /* R105 - OUT1R Volume */
+	0x00E4,     /* R106 - OUT2L Volume */
+	0x02E4,     /* R107 - OUT2R Volume */
+	0x0000,     /* R108 */
+	0x0000,     /* R109 */
+	0x0000,     /* R110 */
+	0x0000,     /* R111 - BEEP Volume */
+	0x0A00,     /* R112 - AI Formating */
+	0x0000,     /* R113 - ADC DAC COMP */
+	0x0020,     /* R114 - AI ADC Control */
+	0x0020,     /* R115 - AI DAC Control */
+	0x0000,     /* R116 */
+	0x0000,     /* R117 */
+	0x0000,     /* R118 */
+	0x0000,     /* R119 */
+	0x0000,     /* R120 */
+	0x0000,     /* R121 */
+	0x0000,     /* R122 */
+	0x0000,     /* R123 */
+	0x0000,     /* R124 */
+	0x0000,     /* R125 */
+	0x0000,     /* R126 */
+	0x0000,     /* R127 */
+	0x1FFF,     /* R128 - GPIO Debounce */
+	0x0000,     /* R129 - GPIO Pin pull up Control */
+	0x0000,     /* R130 - GPIO Pull down Control */
+	0x0000,     /* R131 - GPIO Interrupt Mode */
+	0x0000,     /* R132 */
+	0x0000,     /* R133 - GPIO Control */
+	0x0FFC,     /* R134 - GPIO Configuration (i/o) */
+	0x0FFC,     /* R135 - GPIO Pin Polarity / Type */
+	0x0000,     /* R136 */
+	0x0000,     /* R137 */
+	0x0000,     /* R138 */
+	0x0000,     /* R139 */
+	0x0013,     /* R140 - GPIO Function Select 1 */
+	0x0000,     /* R141 - GPIO Function Select 2 */
+	0x0000,     /* R142 - GPIO Function Select 3 */
+	0x0003,     /* R143 - GPIO Function Select 4 */
+	0x0000,     /* R144 - Digitiser Control (1) */
+	0x0002,     /* R145 - Digitiser Control (2) */
+	0x0000,     /* R146 */
+	0x0000,     /* R147 */
+	0x0000,     /* R148 */
+	0x0000,     /* R149 */
+	0x0000,     /* R150 */
+	0x0000,     /* R151 */
+	0x7000,     /* R152 - AUX1 Readback */
+	0x7000,     /* R153 - AUX2 Readback */
+	0x7000,     /* R154 - AUX3 Readback */
+	0x7000,     /* R155 - AUX4 Readback */
+	0x0000,     /* R156 - USB Voltage Readback */
+	0x0000,     /* R157 - LINE Voltage Readback */
+	0x0000,     /* R158 - BATT Voltage Readback */
+	0x0000,     /* R159 - Chip Temp Readback */
+	0x0000,     /* R160 */
+	0x0000,     /* R161 */
+	0x0000,     /* R162 */
+	0x0000,     /* R163 - Generic Comparator Control */
+	0x0000,     /* R164 - Generic comparator 1 */
+	0x0000,     /* R165 - Generic comparator 2 */
+	0x0000,     /* R166 - Generic comparator 3 */
+	0x0000,     /* R167 - Generic comparator 4 */
+	0xA00F,     /* R168 - Battery Charger Control 1 */
+	0x0B06,     /* R169 - Battery Charger Control 2 */
+	0x0000,     /* R170 - Battery Charger Control 3 */
+	0x0000,     /* R171 */
+	0x0000,     /* R172 - Current Sink Driver A */
+	0x0000,     /* R173 - CSA Flash control */
+	0x0000,     /* R174 */
+	0x0000,     /* R175 */
+	0x0000,     /* R176 - DCDC/LDO requested */
+	0x032D,     /* R177 - DCDC Active options */
+	0x0000,     /* R178 - DCDC Sleep options */
+	0x0025,     /* R179 - Power-check comparator */
+	0x000E,     /* R180 - DCDC1 Control */
+	0x0000,     /* R181 - DCDC1 Timeouts */
+	0x1006,     /* R182 - DCDC1 Low Power */
+	0x0018,     /* R183 - DCDC2 Control */
+	0x0000,     /* R184 - DCDC2 Timeouts */
+	0x0000,     /* R185 */
+	0x0000,     /* R186 - DCDC3 Control */
+	0x0000,     /* R187 - DCDC3 Timeouts */
+	0x0006,     /* R188 - DCDC3 Low Power */
+	0x0000,     /* R189 - DCDC4 Control */
+	0x0000,     /* R190 - DCDC4 Timeouts */
+	0x0006,     /* R191 - DCDC4 Low Power */
+	0x0008,     /* R192 */
+	0x0000,     /* R193 */
+	0x0000,     /* R194 */
+	0x0000,     /* R195 */
+	0x0000,     /* R196 */
+	0x0006,     /* R197 */
+	0x0000,     /* R198 */
+	0x0003,     /* R199 - Limit Switch Control */
+	0x001C,     /* R200 - LDO1 Control */
+	0x0000,     /* R201 - LDO1 Timeouts */
+	0x001C,     /* R202 - LDO1 Low Power */
+	0x001B,     /* R203 - LDO2 Control */
+	0x0000,     /* R204 - LDO2 Timeouts */
+	0x001C,     /* R205 - LDO2 Low Power */
+	0x001B,     /* R206 - LDO3 Control */
+	0x0000,     /* R207 - LDO3 Timeouts */
+	0x001C,     /* R208 - LDO3 Low Power */
+	0x001B,     /* R209 - LDO4 Control */
+	0x0000,     /* R210 - LDO4 Timeouts */
+	0x001C,     /* R211 - LDO4 Low Power */
+	0x0000,     /* R212 */
+	0x0000,     /* R213 */
+	0x0000,     /* R214 */
+	0x0000,     /* R215 - VCC_FAULT Masks */
+	0x001F,     /* R216 - Main Bandgap Control */
+	0x0000,     /* R217 - OSC Control */
+	0x9000,     /* R218 - RTC Tick Control */
+	0x0000,     /* R219 - Security1 */
+	0x4000,     /* R220 */
+	0x0000,     /* R221 */
+	0x0000,     /* R222 */
+	0x0000,     /* R223 */
+	0x0000,     /* R224 - Signal overrides */
+	0x0000,     /* R225 - DCDC/LDO status */
+	0x0000,     /* R226 - Charger Overides/status */
+	0x0000,     /* R227 - misc overrides */
+	0x0000,     /* R228 - Supply overrides/status 1 */
+	0x0000,     /* R229 - Supply overrides/status 2 */
+	0xE000,     /* R230 - GPIO Pin Status */
+	0x0000,     /* R231 - comparotor overrides */
+	0x0000,     /* R232 */
+	0x0000,     /* R233 - State Machine status */
+	0x1200,     /* R234 - FLL Test 1 */
+	0x0000,     /* R235 */
+	0x8000,     /* R236 */
+	0x0000,     /* R237 */
+	0x0000,     /* R238 */
+	0x0000,     /* R239 */
+	0x0003,     /* R240 */
+	0x0000,     /* R241 */
+	0x0000,     /* R242 */
+	0x0004,     /* R243 */
+	0x0300,     /* R244 */
+	0x0000,     /* R245 */
+	0x0200,     /* R246 */
+	0x0000,     /* R247 */
+	0x1000,     /* R248 - DCDC1 Test Controls */
+	0x1000,     /* R249 */
+	0x1000,     /* R250 - DCDC3 Test Controls */
+	0x1000,     /* R251 - DCDC4 Test Controls */
+};
+#endif
+
+#ifdef CONFIG_MFD_WM8351_CONFIG_MODE_1
+
+#undef WM8350_HAVE_CONFIG_MODE
+#define WM8350_HAVE_CONFIG_MODE
+
+const u16 wm8351_mode1_defaults[] = {
+	0x6143,     /* R0   - Reset/ID */
+	0x0000,     /* R1   - ID */
+	0x0001,     /* R2   - Revision */
+	0x1C02,     /* R3   - System Control 1 */
+	0x0204,     /* R4   - System Control 2 */
+	0x0000,     /* R5   - System Hibernate */
+	0x8A00,     /* R6   - Interface Control */
+	0x0000,     /* R7 */
+	0x8000,     /* R8   - Power mgmt (1) */
+	0x0000,     /* R9   - Power mgmt (2) */
+	0x0000,     /* R10  - Power mgmt (3) */
+	0x2000,     /* R11  - Power mgmt (4) */
+	0x0E00,     /* R12  - Power mgmt (5) */
+	0x0000,     /* R13  - Power mgmt (6) */
+	0x0000,     /* R14  - Power mgmt (7) */
+	0x0000,     /* R15 */
+	0x0000,     /* R16  - RTC Seconds/Minutes */
+	0x0100,     /* R17  - RTC Hours/Day */
+	0x0101,     /* R18  - RTC Date/Month */
+	0x1400,     /* R19  - RTC Year */
+	0x0000,     /* R20  - Alarm Seconds/Minutes */
+	0x0000,     /* R21  - Alarm Hours/Day */
+	0x0000,     /* R22  - Alarm Date/Month */
+	0x0320,     /* R23  - RTC Time Control */
+	0x0000,     /* R24  - System Interrupts */
+	0x0000,     /* R25  - Interrupt Status 1 */
+	0x0000,     /* R26  - Interrupt Status 2 */
+	0x0000,     /* R27 */
+	0x0000,     /* R28  - Under Voltage Interrupt status */
+	0x0000,     /* R29  - Over Current Interrupt status */
+	0x0000,     /* R30  - GPIO Interrupt Status */
+	0x0000,     /* R31  - Comparator Interrupt Status */
+	0x3FFF,     /* R32  - System Interrupts Mask */
+	0x0000,     /* R33  - Interrupt Status 1 Mask */
+	0x0000,     /* R34  - Interrupt Status 2 Mask */
+	0x0000,     /* R35 */
+	0x0000,     /* R36  - Under Voltage Interrupt status Mask */
+	0x0000,     /* R37  - Over Current Interrupt status Mask */
+	0x0000,     /* R38  - GPIO Interrupt Status Mask */
+	0x0000,     /* R39  - Comparator Interrupt Status Mask */
+	0x0040,     /* R40  - Clock Control 1 */
+	0x0000,     /* R41  - Clock Control 2 */
+	0x3A00,     /* R42  - FLL Control 1 */
+	0x7086,     /* R43  - FLL Control 2 */
+	0xC226,     /* R44  - FLL Control 3 */
+	0x0000,     /* R45  - FLL Control 4 */
+	0x0000,     /* R46 */
+	0x0000,     /* R47 */
+	0x0000,     /* R48  - DAC Control */
+	0x0000,     /* R49 */
+	0x00C0,     /* R50  - DAC Digital Volume L */
+	0x00C0,     /* R51  - DAC Digital Volume R */
+	0x0000,     /* R52 */
+	0x0040,     /* R53  - DAC LR Rate */
+	0x0000,     /* R54  - DAC Clock Control */
+	0x0000,     /* R55 */
+	0x0000,     /* R56 */
+	0x0000,     /* R57 */
+	0x4000,     /* R58  - DAC Mute */
+	0x0000,     /* R59  - DAC Mute Volume */
+	0x0000,     /* R60  - DAC Side */
+	0x0000,     /* R61 */
+	0x0000,     /* R62 */
+	0x0000,     /* R63 */
+	0x8000,     /* R64  - ADC Control */
+	0x0000,     /* R65 */
+	0x00C0,     /* R66  - ADC Digital Volume L */
+	0x00C0,     /* R67  - ADC Digital Volume R */
+	0x0000,     /* R68  - ADC Divider */
+	0x0000,     /* R69 */
+	0x0040,     /* R70  - ADC LR Rate */
+	0x0000,     /* R71 */
+	0x0303,     /* R72  - Input Control */
+	0x0000,     /* R73  - IN3 Input Control */
+	0x0000,     /* R74  - Mic Bias Control */
+	0x0000,     /* R75 */
+	0x0000,     /* R76  - Output Control */
+	0x0000,     /* R77  - Jack Detect */
+	0x0000,     /* R78  - Anti Pop Control */
+	0x0000,     /* R79 */
+	0x0040,     /* R80  - Left Input Volume */
+	0x0040,     /* R81  - Right Input Volume */
+	0x0000,     /* R82 */
+	0x0000,     /* R83 */
+	0x0000,     /* R84 */
+	0x0000,     /* R85 */
+	0x0000,     /* R86 */
+	0x0000,     /* R87 */
+	0x0800,     /* R88  - Left Mixer Control */
+	0x1000,     /* R89  - Right Mixer Control */
+	0x0000,     /* R90 */
+	0x0000,     /* R91 */
+	0x0000,     /* R92  - OUT3 Mixer Control */
+	0x0000,     /* R93  - OUT4 Mixer Control */
+	0x0000,     /* R94 */
+	0x0000,     /* R95 */
+	0x0000,     /* R96  - Output Left Mixer Volume */
+	0x0000,     /* R97  - Output Right Mixer Volume */
+	0x0000,     /* R98  - Input Mixer Volume L */
+	0x0000,     /* R99  - Input Mixer Volume R */
+	0x0000,     /* R100 - Input Mixer Volume */
+	0x0000,     /* R101 */
+	0x0000,     /* R102 */
+	0x0000,     /* R103 */
+	0x00E4,     /* R104 - OUT1L Volume */
+	0x00E4,     /* R105 - OUT1R Volume */
+	0x00E4,     /* R106 - OUT2L Volume */
+	0x02E4,     /* R107 - OUT2R Volume */
+	0x0000,     /* R108 */
+	0x0000,     /* R109 */
+	0x0000,     /* R110 */
+	0x0000,     /* R111 - BEEP Volume */
+	0x0A00,     /* R112 - AI Formating */
+	0x0000,     /* R113 - ADC DAC COMP */
+	0x0020,     /* R114 - AI ADC Control */
+	0x0020,     /* R115 - AI DAC Control */
+	0x0000,     /* R116 */
+	0x0000,     /* R117 */
+	0x0000,     /* R118 */
+	0x0000,     /* R119 */
+	0x0000,     /* R120 */
+	0x0000,     /* R121 */
+	0x0000,     /* R122 */
+	0x0000,     /* R123 */
+	0x0000,     /* R124 */
+	0x0000,     /* R125 */
+	0x0000,     /* R126 */
+	0x0000,     /* R127 */
+	0x1FFF,     /* R128 - GPIO Debounce */
+	0x0000,     /* R129 - GPIO Pin pull up Control */
+	0x0000,     /* R130 - GPIO Pull down Control */
+	0x0000,     /* R131 - GPIO Interrupt Mode */
+	0x0000,     /* R132 */
+	0x0000,     /* R133 - GPIO Control */
+	0x0CFB,     /* R134 - GPIO Configuration (i/o) */
+	0x0C1F,     /* R135 - GPIO Pin Polarity / Type */
+	0x0000,     /* R136 */
+	0x0000,     /* R137 */
+	0x0000,     /* R138 */
+	0x0000,     /* R139 */
+	0x0300,     /* R140 - GPIO Function Select 1 */
+	0x1110,     /* R141 - GPIO Function Select 2 */
+	0x0013,     /* R142 - GPIO Function Select 3 */
+	0x0003,     /* R143 - GPIO Function Select 4 */
+	0x0000,     /* R144 - Digitiser Control (1) */
+	0x0002,     /* R145 - Digitiser Control (2) */
+	0x0000,     /* R146 */
+	0x0000,     /* R147 */
+	0x0000,     /* R148 */
+	0x0000,     /* R149 */
+	0x0000,     /* R150 */
+	0x0000,     /* R151 */
+	0x7000,     /* R152 - AUX1 Readback */
+	0x7000,     /* R153 - AUX2 Readback */
+	0x7000,     /* R154 - AUX3 Readback */
+	0x7000,     /* R155 - AUX4 Readback */
+	0x0000,     /* R156 - USB Voltage Readback */
+	0x0000,     /* R157 - LINE Voltage Readback */
+	0x0000,     /* R158 - BATT Voltage Readback */
+	0x0000,     /* R159 - Chip Temp Readback */
+	0x0000,     /* R160 */
+	0x0000,     /* R161 */
+	0x0000,     /* R162 */
+	0x0000,     /* R163 - Generic Comparator Control */
+	0x0000,     /* R164 - Generic comparator 1 */
+	0x0000,     /* R165 - Generic comparator 2 */
+	0x0000,     /* R166 - Generic comparator 3 */
+	0x0000,     /* R167 - Generic comparator 4 */
+	0xA00F,     /* R168 - Battery Charger Control 1 */
+	0x0B06,     /* R169 - Battery Charger Control 2 */
+	0x0000,     /* R170 - Battery Charger Control 3 */
+	0x0000,     /* R171 */
+	0x0000,     /* R172 - Current Sink Driver A */
+	0x0000,     /* R173 - CSA Flash control */
+	0x0000,     /* R174 */
+	0x0000,     /* R175 */
+	0x0000,     /* R176 - DCDC/LDO requested */
+	0x032D,     /* R177 - DCDC Active options */
+	0x0000,     /* R178 - DCDC Sleep options */
+	0x0025,     /* R179 - Power-check comparator */
+	0x000E,     /* R180 - DCDC1 Control */
+	0x0C00,     /* R181 - DCDC1 Timeouts */
+	0x1006,     /* R182 - DCDC1 Low Power */
+	0x0018,     /* R183 - DCDC2 Control */
+	0x0000,     /* R184 - DCDC2 Timeouts */
+	0x0000,     /* R185 */
+	0x0026,     /* R186 - DCDC3 Control */
+	0x0400,     /* R187 - DCDC3 Timeouts */
+	0x0006,     /* R188 - DCDC3 Low Power */
+	0x0062,     /* R189 - DCDC4 Control */
+	0x0800,     /* R190 - DCDC4 Timeouts */
+	0x0006,     /* R191 - DCDC4 Low Power */
+	0x0008,     /* R192 */
+	0x0000,     /* R193 */
+	0x0000,     /* R194 */
+	0x000A,     /* R195 */
+	0x1000,     /* R196 */
+	0x0006,     /* R197 */
+	0x0000,     /* R198 */
+	0x0003,     /* R199 - Limit Switch Control */
+	0x0006,     /* R200 - LDO1 Control */
+	0x0000,     /* R201 - LDO1 Timeouts */
+	0x001C,     /* R202 - LDO1 Low Power */
+	0x0010,     /* R203 - LDO2 Control */
+	0x0C00,     /* R204 - LDO2 Timeouts */
+	0x001C,     /* R205 - LDO2 Low Power */
+	0x001F,     /* R206 - LDO3 Control */
+	0x0800,     /* R207 - LDO3 Timeouts */
+	0x001C,     /* R208 - LDO3 Low Power */
+	0x000A,     /* R209 - LDO4 Control */
+	0x0800,     /* R210 - LDO4 Timeouts */
+	0x001C,     /* R211 - LDO4 Low Power */
+	0x0000,     /* R212 */
+	0x0000,     /* R213 */
+	0x0000,     /* R214 */
+	0x0000,     /* R215 - VCC_FAULT Masks */
+	0x001F,     /* R216 - Main Bandgap Control */
+	0x0000,     /* R217 - OSC Control */
+	0x9000,     /* R218 - RTC Tick Control */
+	0x0000,     /* R219 - Security1 */
+	0x4000,     /* R220 */
+	0x0000,     /* R221 */
+	0x0000,     /* R222 */
+	0x0000,     /* R223 */
+	0x0000,     /* R224 - Signal overrides */
+	0x0000,     /* R225 - DCDC/LDO status */
+	0x0000,     /* R226 - Charger Overides/status */
+	0x0000,     /* R227 - misc overrides */
+	0x0000,     /* R228 - Supply overrides/status 1 */
+	0x0000,     /* R229 - Supply overrides/status 2 */
+	0xE000,     /* R230 - GPIO Pin Status */
+	0x0000,     /* R231 - comparotor overrides */
+	0x0000,     /* R232 */
+	0x0000,     /* R233 - State Machine status */
+	0x1200,     /* R234 - FLL Test 1 */
+	0x0000,     /* R235 */
+	0x8000,     /* R236 */
+	0x0000,     /* R237 */
+	0x0000,     /* R238 */
+	0x0000,     /* R239 */
+	0x0003,     /* R240 */
+	0x0000,     /* R241 */
+	0x0000,     /* R242 */
+	0x0004,     /* R243 */
+	0x0300,     /* R244 */
+	0x0000,     /* R245 */
+	0x0200,     /* R246 */
+	0x1000,     /* R247 */
+	0x1000,     /* R248 - DCDC1 Test Controls */
+	0x1000,     /* R249 */
+	0x1000,     /* R250 - DCDC3 Test Controls */
+	0x1000,     /* R251 - DCDC4 Test Controls */
+};
+#endif
+
+#ifdef CONFIG_MFD_WM8351_CONFIG_MODE_2
+
+#undef WM8350_HAVE_CONFIG_MODE
+#define WM8350_HAVE_CONFIG_MODE
+
+const u16 wm8351_mode2_defaults[] = {
+	0x6143,     /* R0   - Reset/ID */
+	0x0000,     /* R1   - ID */
+	0x0001,     /* R2   - Revision */
+	0x1C02,     /* R3   - System Control 1 */
+	0x0214,     /* R4   - System Control 2 */
+	0x0000,     /* R5   - System Hibernate */
+	0x8A00,     /* R6   - Interface Control */
+	0x0000,     /* R7 */
+	0x8000,     /* R8   - Power mgmt (1) */
+	0x0000,     /* R9   - Power mgmt (2) */
+	0x0000,     /* R10  - Power mgmt (3) */
+	0x2000,     /* R11  - Power mgmt (4) */
+	0x0E00,     /* R12  - Power mgmt (5) */
+	0x0000,     /* R13  - Power mgmt (6) */
+	0x0000,     /* R14  - Power mgmt (7) */
+	0x0000,     /* R15 */
+	0x0000,     /* R16  - RTC Seconds/Minutes */
+	0x0100,     /* R17  - RTC Hours/Day */
+	0x0101,     /* R18  - RTC Date/Month */
+	0x1400,     /* R19  - RTC Year */
+	0x0000,     /* R20  - Alarm Seconds/Minutes */
+	0x0000,     /* R21  - Alarm Hours/Day */
+	0x0000,     /* R22  - Alarm Date/Month */
+	0x0320,     /* R23  - RTC Time Control */
+	0x0000,     /* R24  - System Interrupts */
+	0x0000,     /* R25  - Interrupt Status 1 */
+	0x0000,     /* R26  - Interrupt Status 2 */
+	0x0000,     /* R27 */
+	0x0000,     /* R28  - Under Voltage Interrupt status */
+	0x0000,     /* R29  - Over Current Interrupt status */
+	0x0000,     /* R30  - GPIO Interrupt Status */
+	0x0000,     /* R31  - Comparator Interrupt Status */
+	0x3FFF,     /* R32  - System Interrupts Mask */
+	0x0000,     /* R33  - Interrupt Status 1 Mask */
+	0x0000,     /* R34  - Interrupt Status 2 Mask */
+	0x0000,     /* R35 */
+	0x0000,     /* R36  - Under Voltage Interrupt status Mask */
+	0x0000,     /* R37  - Over Current Interrupt status Mask */
+	0x0000,     /* R38  - GPIO Interrupt Status Mask */
+	0x0000,     /* R39  - Comparator Interrupt Status Mask */
+	0x0040,     /* R40  - Clock Control 1 */
+	0x0000,     /* R41  - Clock Control 2 */
+	0x3A00,     /* R42  - FLL Control 1 */
+	0x7086,     /* R43  - FLL Control 2 */
+	0xC226,     /* R44  - FLL Control 3 */
+	0x0000,     /* R45  - FLL Control 4 */
+	0x0000,     /* R46 */
+	0x0000,     /* R47 */
+	0x0000,     /* R48  - DAC Control */
+	0x0000,     /* R49 */
+	0x00C0,     /* R50  - DAC Digital Volume L */
+	0x00C0,     /* R51  - DAC Digital Volume R */
+	0x0000,     /* R52 */
+	0x0040,     /* R53  - DAC LR Rate */
+	0x0000,     /* R54  - DAC Clock Control */
+	0x0000,     /* R55 */
+	0x0000,     /* R56 */
+	0x0000,     /* R57 */
+	0x4000,     /* R58  - DAC Mute */
+	0x0000,     /* R59  - DAC Mute Volume */
+	0x0000,     /* R60  - DAC Side */
+	0x0000,     /* R61 */
+	0x0000,     /* R62 */
+	0x0000,     /* R63 */
+	0x8000,     /* R64  - ADC Control */
+	0x0000,     /* R65 */
+	0x00C0,     /* R66  - ADC Digital Volume L */
+	0x00C0,     /* R67  - ADC Digital Volume R */
+	0x0000,     /* R68  - ADC Divider */
+	0x0000,     /* R69 */
+	0x0040,     /* R70  - ADC LR Rate */
+	0x0000,     /* R71 */
+	0x0303,     /* R72  - Input Control */
+	0x0000,     /* R73  - IN3 Input Control */
+	0x0000,     /* R74  - Mic Bias Control */
+	0x0000,     /* R75 */
+	0x0000,     /* R76  - Output Control */
+	0x0000,     /* R77  - Jack Detect */
+	0x0000,     /* R78  - Anti Pop Control */
+	0x0000,     /* R79 */
+	0x0040,     /* R80  - Left Input Volume */
+	0x0040,     /* R81  - Right Input Volume */
+	0x0000,     /* R82 */
+	0x0000,     /* R83 */
+	0x0000,     /* R84 */
+	0x0000,     /* R85 */
+	0x0000,     /* R86 */
+	0x0000,     /* R87 */
+	0x0800,     /* R88  - Left Mixer Control */
+	0x1000,     /* R89  - Right Mixer Control */
+	0x0000,     /* R90 */
+	0x0000,     /* R91 */
+	0x0000,     /* R92  - OUT3 Mixer Control */
+	0x0000,     /* R93  - OUT4 Mixer Control */
+	0x0000,     /* R94 */
+	0x0000,     /* R95 */
+	0x0000,     /* R96  - Output Left Mixer Volume */
+	0x0000,     /* R97  - Output Right Mixer Volume */
+	0x0000,     /* R98  - Input Mixer Volume L */
+	0x0000,     /* R99  - Input Mixer Volume R */
+	0x0000,     /* R100 - Input Mixer Volume */
+	0x0000,     /* R101 */
+	0x0000,     /* R102 */
+	0x0000,     /* R103 */
+	0x00E4,     /* R104 - OUT1L Volume */
+	0x00E4,     /* R105 - OUT1R Volume */
+	0x00E4,     /* R106 - OUT2L Volume */
+	0x02E4,     /* R107 - OUT2R Volume */
+	0x0000,     /* R108 */
+	0x0000,     /* R109 */
+	0x0000,     /* R110 */
+	0x0000,     /* R111 - BEEP Volume */
+	0x0A00,     /* R112 - AI Formating */
+	0x0000,     /* R113 - ADC DAC COMP */
+	0x0020,     /* R114 - AI ADC Control */
+	0x0020,     /* R115 - AI DAC Control */
+	0x0000,     /* R116 */
+	0x0000,     /* R117 */
+	0x0000,     /* R118 */
+	0x0000,     /* R119 */
+	0x0000,     /* R120 */
+	0x0000,     /* R121 */
+	0x0000,     /* R122 */
+	0x0000,     /* R123 */
+	0x0000,     /* R124 */
+	0x0000,     /* R125 */
+	0x0000,     /* R126 */
+	0x0000,     /* R127 */
+	0x1FFF,     /* R128 - GPIO Debounce */
+	0x0000,     /* R129 - GPIO Pin pull up Control */
+	0x0110,     /* R130 - GPIO Pull down Control */
+	0x0000,     /* R131 - GPIO Interrupt Mode */
+	0x0000,     /* R132 */
+	0x0000,     /* R133 - GPIO Control */
+	0x09FA,     /* R134 - GPIO Configuration (i/o) */
+	0x0DF6,     /* R135 - GPIO Pin Polarity / Type */
+	0x0000,     /* R136 */
+	0x0000,     /* R137 */
+	0x0000,     /* R138 */
+	0x0000,     /* R139 */
+	0x1310,     /* R140 - GPIO Function Select 1 */
+	0x0003,     /* R141 - GPIO Function Select 2 */
+	0x2000,     /* R142 - GPIO Function Select 3 */
+	0x0000,     /* R143 - GPIO Function Select 4 */
+	0x0000,     /* R144 - Digitiser Control (1) */
+	0x0002,     /* R145 - Digitiser Control (2) */
+	0x0000,     /* R146 */
+	0x0000,     /* R147 */
+	0x0000,     /* R148 */
+	0x0000,     /* R149 */
+	0x0000,     /* R150 */
+	0x0000,     /* R151 */
+	0x7000,     /* R152 - AUX1 Readback */
+	0x7000,     /* R153 - AUX2 Readback */
+	0x7000,     /* R154 - AUX3 Readback */
+	0x7000,     /* R155 - AUX4 Readback */
+	0x0000,     /* R156 - USB Voltage Readback */
+	0x0000,     /* R157 - LINE Voltage Readback */
+	0x0000,     /* R158 - BATT Voltage Readback */
+	0x0000,     /* R159 - Chip Temp Readback */
+	0x0000,     /* R160 */
+	0x0000,     /* R161 */
+	0x0000,     /* R162 */
+	0x0000,     /* R163 - Generic Comparator Control */
+	0x0000,     /* R164 - Generic comparator 1 */
+	0x0000,     /* R165 - Generic comparator 2 */
+	0x0000,     /* R166 - Generic comparator 3 */
+	0x0000,     /* R167 - Generic comparator 4 */
+	0xA00F,     /* R168 - Battery Charger Control 1 */
+	0x0B06,     /* R169 - Battery Charger Control 2 */
+	0x0000,     /* R170 - Battery Charger Control 3 */
+	0x0000,     /* R171 */
+	0x0000,     /* R172 - Current Sink Driver A */
+	0x0000,     /* R173 - CSA Flash control */
+	0x0000,     /* R174 */
+	0x0000,     /* R175 */
+	0x0000,     /* R176 - DCDC/LDO requested */
+	0x032D,     /* R177 - DCDC Active options */
+	0x0000,     /* R178 - DCDC Sleep options */
+	0x0025,     /* R179 - Power-check comparator */
+	0x001A,     /* R180 - DCDC1 Control */
+	0x0800,     /* R181 - DCDC1 Timeouts */
+	0x1006,     /* R182 - DCDC1 Low Power */
+	0x0018,     /* R183 - DCDC2 Control */
+	0x0000,     /* R184 - DCDC2 Timeouts */
+	0x0000,     /* R185 */
+	0x0056,     /* R186 - DCDC3 Control */
+	0x0400,     /* R187 - DCDC3 Timeouts */
+	0x0006,     /* R188 - DCDC3 Low Power */
+	0x0026,     /* R189 - DCDC4 Control */
+	0x0C00,     /* R190 - DCDC4 Timeouts */
+	0x0006,     /* R191 - DCDC4 Low Power */
+	0x0008,     /* R192 */
+	0x0000,     /* R193 */
+	0x0000,     /* R194 */
+	0x0026,     /* R195 */
+	0x0C00,     /* R196 */
+	0x0006,     /* R197 */
+	0x0000,     /* R198 */
+	0x0003,     /* R199 - Limit Switch Control */
+	0x001C,     /* R200 - LDO1 Control */
+	0x0400,     /* R201 - LDO1 Timeouts */
+	0x001C,     /* R202 - LDO1 Low Power */
+	0x0010,     /* R203 - LDO2 Control */
+	0x0C00,     /* R204 - LDO2 Timeouts */
+	0x001C,     /* R205 - LDO2 Low Power */
+	0x0015,     /* R206 - LDO3 Control */
+	0x0000,     /* R207 - LDO3 Timeouts */
+	0x001C,     /* R208 - LDO3 Low Power */
+	0x001A,     /* R209 - LDO4 Control */
+	0x0000,     /* R210 - LDO4 Timeouts */
+	0x001C,     /* R211 - LDO4 Low Power */
+	0x0000,     /* R212 */
+	0x0000,     /* R213 */
+	0x0000,     /* R214 */
+	0x0000,     /* R215 - VCC_FAULT Masks */
+	0x001F,     /* R216 - Main Bandgap Control */
+	0x0000,     /* R217 - OSC Control */
+	0x9000,     /* R218 - RTC Tick Control */
+	0x0000,     /* R219 - Security1 */
+	0x4000,     /* R220 */
+	0x0000,     /* R221 */
+	0x0000,     /* R222 */
+	0x0000,     /* R223 */
+	0x0000,     /* R224 - Signal overrides */
+	0x0000,     /* R225 - DCDC/LDO status */
+	0x0000,     /* R226 - Charger Overides/status */
+	0x0000,     /* R227 - misc overrides */
+	0x0000,     /* R228 - Supply overrides/status 1 */
+	0x0000,     /* R229 - Supply overrides/status 2 */
+	0xE000,     /* R230 - GPIO Pin Status */
+	0x0000,     /* R231 - comparotor overrides */
+	0x0000,     /* R232 */
+	0x0000,     /* R233 - State Machine status */
+	0x1200,     /* R234 - FLL Test 1 */
+	0x0000,     /* R235 */
+	0x8000,     /* R236 */
+	0x0000,     /* R237 */
+	0x0000,     /* R238 */
+	0x0000,     /* R239 */
+	0x0003,     /* R240 */
+	0x0000,     /* R241 */
+	0x0000,     /* R242 */
+	0x0004,     /* R243 */
+	0x0300,     /* R244 */
+	0x0000,     /* R245 */
+	0x0200,     /* R246 */
+	0x0000,     /* R247 */
+	0x1000,     /* R248 - DCDC1 Test Controls */
+	0x1000,     /* R249 */
+	0x1000,     /* R250 - DCDC3 Test Controls */
+	0x1000,     /* R251 - DCDC4 Test Controls */
+};
+#endif
+
+#ifdef CONFIG_MFD_WM8351_CONFIG_MODE_3
+
+#undef WM8350_HAVE_CONFIG_MODE
+#define WM8350_HAVE_CONFIG_MODE
+
+const u16 wm8351_mode3_defaults[] = {
+	0x6143,     /* R0   - Reset/ID */
+	0x0000,     /* R1   - ID */
+	0x0001,     /* R2   - Revision */
+	0x1C02,     /* R3   - System Control 1 */
+	0x0204,     /* R4   - System Control 2 */
+	0x0000,     /* R5   - System Hibernate */
+	0x8A00,     /* R6   - Interface Control */
+	0x0000,     /* R7 */
+	0x8000,     /* R8   - Power mgmt (1) */
+	0x0000,     /* R9   - Power mgmt (2) */
+	0x0000,     /* R10  - Power mgmt (3) */
+	0x2000,     /* R11  - Power mgmt (4) */
+	0x0E00,     /* R12  - Power mgmt (5) */
+	0x0000,     /* R13  - Power mgmt (6) */
+	0x0000,     /* R14  - Power mgmt (7) */
+	0x0000,     /* R15 */
+	0x0000,     /* R16  - RTC Seconds/Minutes */
+	0x0100,     /* R17  - RTC Hours/Day */
+	0x0101,     /* R18  - RTC Date/Month */
+	0x1400,     /* R19  - RTC Year */
+	0x0000,     /* R20  - Alarm Seconds/Minutes */
+	0x0000,     /* R21  - Alarm Hours/Day */
+	0x0000,     /* R22  - Alarm Date/Month */
+	0x0320,     /* R23  - RTC Time Control */
+	0x0000,     /* R24  - System Interrupts */
+	0x0000,     /* R25  - Interrupt Status 1 */
+	0x0000,     /* R26  - Interrupt Status 2 */
+	0x0000,     /* R27 */
+	0x0000,     /* R28  - Under Voltage Interrupt status */
+	0x0000,     /* R29  - Over Current Interrupt status */
+	0x0000,     /* R30  - GPIO Interrupt Status */
+	0x0000,     /* R31  - Comparator Interrupt Status */
+	0x3FFF,     /* R32  - System Interrupts Mask */
+	0x0000,     /* R33  - Interrupt Status 1 Mask */
+	0x0000,     /* R34  - Interrupt Status 2 Mask */
+	0x0000,     /* R35 */
+	0x0000,     /* R36  - Under Voltage Interrupt status Mask */
+	0x0000,     /* R37  - Over Current Interrupt status Mask */
+	0x0000,     /* R38  - GPIO Interrupt Status Mask */
+	0x0000,     /* R39  - Comparator Interrupt Status Mask */
+	0x0040,     /* R40  - Clock Control 1 */
+	0x0000,     /* R41  - Clock Control 2 */
+	0x3A00,     /* R42  - FLL Control 1 */
+	0x7086,     /* R43  - FLL Control 2 */
+	0xC226,     /* R44  - FLL Control 3 */
+	0x0000,     /* R45  - FLL Control 4 */
+	0x0000,     /* R46 */
+	0x0000,     /* R47 */
+	0x0000,     /* R48  - DAC Control */
+	0x0000,     /* R49 */
+	0x00C0,     /* R50  - DAC Digital Volume L */
+	0x00C0,     /* R51  - DAC Digital Volume R */
+	0x0000,     /* R52 */
+	0x0040,     /* R53  - DAC LR Rate */
+	0x0000,     /* R54  - DAC Clock Control */
+	0x0000,     /* R55 */
+	0x0000,     /* R56 */
+	0x0000,     /* R57 */
+	0x4000,     /* R58  - DAC Mute */
+	0x0000,     /* R59  - DAC Mute Volume */
+	0x0000,     /* R60  - DAC Side */
+	0x0000,     /* R61 */
+	0x0000,     /* R62 */
+	0x0000,     /* R63 */
+	0x8000,     /* R64  - ADC Control */
+	0x0000,     /* R65 */
+	0x00C0,     /* R66  - ADC Digital Volume L */
+	0x00C0,     /* R67  - ADC Digital Volume R */
+	0x0000,     /* R68  - ADC Divider */
+	0x0000,     /* R69 */
+	0x0040,     /* R70  - ADC LR Rate */
+	0x0000,     /* R71 */
+	0x0303,     /* R72  - Input Control */
+	0x0000,     /* R73  - IN3 Input Control */
+	0x0000,     /* R74  - Mic Bias Control */
+	0x0000,     /* R75 */
+	0x0000,     /* R76  - Output Control */
+	0x0000,     /* R77  - Jack Detect */
+	0x0000,     /* R78  - Anti Pop Control */
+	0x0000,     /* R79 */
+	0x0040,     /* R80  - Left Input Volume */
+	0x0040,     /* R81  - Right Input Volume */
+	0x0000,     /* R82 */
+	0x0000,     /* R83 */
+	0x0000,     /* R84 */
+	0x0000,     /* R85 */
+	0x0000,     /* R86 */
+	0x0000,     /* R87 */
+	0x0800,     /* R88  - Left Mixer Control */
+	0x1000,     /* R89  - Right Mixer Control */
+	0x0000,     /* R90 */
+	0x0000,     /* R91 */
+	0x0000,     /* R92  - OUT3 Mixer Control */
+	0x0000,     /* R93  - OUT4 Mixer Control */
+	0x0000,     /* R94 */
+	0x0000,     /* R95 */
+	0x0000,     /* R96  - Output Left Mixer Volume */
+	0x0000,     /* R97  - Output Right Mixer Volume */
+	0x0000,     /* R98  - Input Mixer Volume L */
+	0x0000,     /* R99  - Input Mixer Volume R */
+	0x0000,     /* R100 - Input Mixer Volume */
+	0x0000,     /* R101 */
+	0x0000,     /* R102 */
+	0x0000,     /* R103 */
+	0x00E4,     /* R104 - OUT1L Volume */
+	0x00E4,     /* R105 - OUT1R Volume */
+	0x00E4,     /* R106 - OUT2L Volume */
+	0x02E4,     /* R107 - OUT2R Volume */
+	0x0000,     /* R108 */
+	0x0000,     /* R109 */
+	0x0000,     /* R110 */
+	0x0000,     /* R111 - BEEP Volume */
+	0x0A00,     /* R112 - AI Formating */
+	0x0000,     /* R113 - ADC DAC COMP */
+	0x0020,     /* R114 - AI ADC Control */
+	0x0020,     /* R115 - AI DAC Control */
+	0x0000,     /* R116 */
+	0x0000,     /* R117 */
+	0x0000,     /* R118 */
+	0x0000,     /* R119 */
+	0x0000,     /* R120 */
+	0x0000,     /* R121 */
+	0x0000,     /* R122 */
+	0x0000,     /* R123 */
+	0x0000,     /* R124 */
+	0x0000,     /* R125 */
+	0x0000,     /* R126 */
+	0x0000,     /* R127 */
+	0x1FFF,     /* R128 - GPIO Debounce */
+	0x0010,     /* R129 - GPIO Pin pull up Control */
+	0x0000,     /* R130 - GPIO Pull down Control */
+	0x0000,     /* R131 - GPIO Interrupt Mode */
+	0x0000,     /* R132 */
+	0x0000,     /* R133 - GPIO Control */
+	0x0BFB,     /* R134 - GPIO Configuration (i/o) */
+	0x0FFD,     /* R135 - GPIO Pin Polarity / Type */
+	0x0000,     /* R136 */
+	0x0000,     /* R137 */
+	0x0000,     /* R138 */
+	0x0000,     /* R139 */
+	0x0310,     /* R140 - GPIO Function Select 1 */
+	0x0001,     /* R141 - GPIO Function Select 2 */
+	0x2300,     /* R142 - GPIO Function Select 3 */
+	0x0003,     /* R143 - GPIO Function Select 4 */
+	0x0000,     /* R144 - Digitiser Control (1) */
+	0x0002,     /* R145 - Digitiser Control (2) */
+	0x0000,     /* R146 */
+	0x0000,     /* R147 */
+	0x0000,     /* R148 */
+	0x0000,     /* R149 */
+	0x0000,     /* R150 */
+	0x0000,     /* R151 */
+	0x7000,     /* R152 - AUX1 Readback */
+	0x7000,     /* R153 - AUX2 Readback */
+	0x7000,     /* R154 - AUX3 Readback */
+	0x7000,     /* R155 - AUX4 Readback */
+	0x0000,     /* R156 - USB Voltage Readback */
+	0x0000,     /* R157 - LINE Voltage Readback */
+	0x0000,     /* R158 - BATT Voltage Readback */
+	0x0000,     /* R159 - Chip Temp Readback */
+	0x0000,     /* R160 */
+	0x0000,     /* R161 */
+	0x0000,     /* R162 */
+	0x0000,     /* R163 - Generic Comparator Control */
+	0x0000,     /* R164 - Generic comparator 1 */
+	0x0000,     /* R165 - Generic comparator 2 */
+	0x0000,     /* R166 - Generic comparator 3 */
+	0x0000,     /* R167 - Generic comparator 4 */
+	0xA00F,     /* R168 - Battery Charger Control 1 */
+	0x0B06,     /* R169 - Battery Charger Control 2 */
+	0x0000,     /* R170 - Battery Charger Control 3 */
+	0x0000,     /* R171 */
+	0x0000,     /* R172 - Current Sink Driver A */
+	0x0000,     /* R173 - CSA Flash control */
+	0x0000,     /* R174 */
+	0x0000,     /* R175 */
+	0x0000,     /* R176 - DCDC/LDO requested */
+	0x032D,     /* R177 - DCDC Active options */
+	0x0000,     /* R178 - DCDC Sleep options */
+	0x0025,     /* R179 - Power-check comparator */
+	0x000E,     /* R180 - DCDC1 Control */
+	0x0400,     /* R181 - DCDC1 Timeouts */
+	0x1006,     /* R182 - DCDC1 Low Power */
+	0x0018,     /* R183 - DCDC2 Control */
+	0x0000,     /* R184 - DCDC2 Timeouts */
+	0x0000,     /* R185 */
+	0x0026,     /* R186 - DCDC3 Control */
+	0x0800,     /* R187 - DCDC3 Timeouts */
+	0x0006,     /* R188 - DCDC3 Low Power */
+	0x0062,     /* R189 - DCDC4 Control */
+	0x1400,     /* R190 - DCDC4 Timeouts */
+	0x0006,     /* R191 - DCDC4 Low Power */
+	0x0008,     /* R192 */
+	0x0000,     /* R193 */
+	0x0000,     /* R194 */
+	0x0026,     /* R195 */
+	0x0400,     /* R196 */
+	0x0006,     /* R197 */
+	0x0000,     /* R198 */
+	0x0003,     /* R199 - Limit Switch Control */
+	0x0006,     /* R200 - LDO1 Control */
+	0x0C00,     /* R201 - LDO1 Timeouts */
+	0x001C,     /* R202 - LDO1 Low Power */
+	0x0016,     /* R203 - LDO2 Control */
+	0x0000,     /* R204 - LDO2 Timeouts */
+	0x001C,     /* R205 - LDO2 Low Power */
+	0x0019,     /* R206 - LDO3 Control */
+	0x0000,     /* R207 - LDO3 Timeouts */
+	0x001C,     /* R208 - LDO3 Low Power */
+	0x001A,     /* R209 - LDO4 Control */
+	0x1000,     /* R210 - LDO4 Timeouts */
+	0x001C,     /* R211 - LDO4 Low Power */
+	0x0000,     /* R212 */
+	0x0000,     /* R213 */
+	0x0000,     /* R214 */
+	0x0000,     /* R215 - VCC_FAULT Masks */
+	0x001F,     /* R216 - Main Bandgap Control */
+	0x0000,     /* R217 - OSC Control */
+	0x9000,     /* R218 - RTC Tick Control */
+	0x0000,     /* R219 - Security1 */
+	0x4000,     /* R220 */
+	0x0000,     /* R221 */
+	0x0000,     /* R222 */
+	0x0000,     /* R223 */
+	0x0000,     /* R224 - Signal overrides */
+	0x0000,     /* R225 - DCDC/LDO status */
+	0x0000,     /* R226 - Charger Overides/status */
+	0x0000,     /* R227 - misc overrides */
+	0x0000,     /* R228 - Supply overrides/status 1 */
+	0x0000,     /* R229 - Supply overrides/status 2 */
+	0xE000,     /* R230 - GPIO Pin Status */
+	0x0000,     /* R231 - comparotor overrides */
+	0x0000,     /* R232 */
+	0x0000,     /* R233 - State Machine status */
+	0x1200,     /* R234 - FLL Test 1 */
+	0x0000,     /* R235 */
+	0x8000,     /* R236 */
+	0x0000,     /* R237 */
+	0x0000,     /* R238 */
+	0x0000,     /* R239 */
+	0x0003,     /* R240 */
+	0x0000,     /* R241 */
+	0x0000,     /* R242 */
+	0x0004,     /* R243 */
+	0x0300,     /* R244 */
+	0x0000,     /* R245 */
+	0x0200,     /* R246 */
+	0x0000,     /* R247 */
+	0x1000,     /* R248 - DCDC1 Test Controls */
+	0x1000,     /* R249 */
+	0x1000,     /* R250 - DCDC3 Test Controls */
+	0x1000,     /* R251 - DCDC4 Test Controls */
+};
+#endif
+
 #ifdef CONFIG_MFD_WM8352_CONFIG_MODE_0
 
 #undef WM8350_HAVE_CONFIG_MODE
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index 737579086d01..980669d50dca 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -589,6 +589,10 @@ extern const u16 wm8350_mode0_defaults[];
 extern const u16 wm8350_mode1_defaults[];
 extern const u16 wm8350_mode2_defaults[];
 extern const u16 wm8350_mode3_defaults[];
+extern const u16 wm8351_mode0_defaults[];
+extern const u16 wm8351_mode1_defaults[];
+extern const u16 wm8351_mode2_defaults[];
+extern const u16 wm8351_mode3_defaults[];
 extern const u16 wm8352_mode0_defaults[];
 extern const u16 wm8352_mode1_defaults[];
 extern const u16 wm8352_mode2_defaults[];
-- 
cgit v1.2.3-70-g09d2


From 0931a4c6dbfab03f2bfd22a9170130f7b155d53a Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Mon, 22 Dec 2008 12:05:27 +0100
Subject: mfd: dm355evm msp430 driver

Basic MFD framework for the MSP430 microcontroller firmware used
on the dm355evm board:

 - Provides an interface for other drivers: register read/write
   utilities, and register declarations.

 - Directly exports:
     * Many signals through the GPIO framework
         + LEDs
         + SW6 through gpio sysfs
	 + NTSC/nPAL jumper through gpio sysfs
	 + ... more could be added later, e.g. MMC signals
     * Child devices:
	+ LEDs, via leds-gpio child (and default triggers)
	+ RTC, via rtc-dm355evm child device
	+ Buttons and IR control, via dm355evm_keys

 - Supports power-off system call.  Use the reset button to power
   the board back up; the power supply LED will be on, but the
   MSP430 waits to re-activate the regulators.

 - On probe() this:
     * Announces firmware revision
     * Turns off the banked LEDs
     * Exports the resources noted above
     * Hooks the power-off support
     * Muxes tvp5146 -or- imager for video input

Unless the new tvp514x driver (tracked for mainline) is configured,
this assumes that some custom imager driver handles video-in.

This completely ignores the registers reporting the output voltages
on the various power supplies.  Someone could add a hwmon interface
if that seems useful.

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/Kconfig              |   8 +
 drivers/mfd/Makefile             |   2 +
 drivers/mfd/dm355evm_msp.c       | 420 +++++++++++++++++++++++++++++++++++++++
 include/linux/i2c/dm355evm_msp.h |  79 ++++++++
 4 files changed, 509 insertions(+)
 create mode 100644 drivers/mfd/dm355evm_msp.c
 create mode 100644 include/linux/i2c/dm355evm_msp.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 781a27955ff5..02e9146ca44a 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -34,6 +34,14 @@ config MFD_ASIC3
 	  This driver supports the ASIC3 multifunction chip found on many
 	  PDAs (mainly iPAQ and HTC based ones)
 
+config MFD_DM355EVM_MSP
+	bool "DaVinci DM355 EVM microcontroller"
+	depends on I2C && MACH_DAVINCI_DM355_EVM
+	help
+	  This driver supports the MSP430 microcontroller used on these
+	  boards.  MSP430 firmware manages resets and power sequencing,
+	  inputs from buttons and the IR remote, LEDs, an RTC, and more.
+
 config HTC_EGPIO
 	bool "HTC EGPIO support"
 	depends on GENERIC_HARDIRQS && GPIOLIB && ARM
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 9a5ad8af9116..8f6cd5c48930 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -8,6 +8,8 @@ obj-$(CONFIG_MFD_ASIC3)		+= asic3.o
 obj-$(CONFIG_HTC_EGPIO)		+= htc-egpio.o
 obj-$(CONFIG_HTC_PASIC3)	+= htc-pasic3.o
 
+obj-$(CONFIG_MFD_DM355EVM_MSP)	+= dm355evm_msp.o
+
 obj-$(CONFIG_MFD_T7L66XB)	+= t7l66xb.o
 obj-$(CONFIG_MFD_TC6387XB)	+= tc6387xb.o
 obj-$(CONFIG_MFD_TC6393XB)	+= tc6393xb.o
diff --git a/drivers/mfd/dm355evm_msp.c b/drivers/mfd/dm355evm_msp.c
new file mode 100644
index 000000000000..4214b3f72426
--- /dev/null
+++ b/drivers/mfd/dm355evm_msp.c
@@ -0,0 +1,420 @@
+/*
+ * dm355evm_msp.c - driver for MSP430 firmware on DM355EVM board
+ *
+ * Copyright (C) 2008 David Brownell
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/leds.h>
+#include <linux/i2c.h>
+#include <linux/i2c/dm355evm_msp.h>
+
+
+/*
+ * The DM355 is a DaVinci chip with video support but no C64+ DSP.  Its
+ * EVM board has an MSP430 programmed with firmware for various board
+ * support functions.  This driver exposes some of them directly, and
+ * supports other drivers (e.g. RTC, input) for more complex access.
+ *
+ * Because this firmware is entirely board-specific, this file embeds
+ * knowledge that would be passed as platform_data in a generic driver.
+ *
+ * This driver was tested with firmware revision A4.
+ */
+
+#if defined(CONFIG_KEYBOARD_DM355EVM) \
+		|| defined(CONFIG_KEYBOARD_DM355EVM_MODULE)
+#define msp_has_keyboard()	true
+#else
+#define msp_has_keyboard()	false
+#endif
+
+#if defined(CONFIG_LEDS_GPIO) || defined(CONFIG_LEDS_GPIO_MODULE)
+#define msp_has_leds()		true
+#else
+#define msp_has_leds()		false
+#endif
+
+#if defined(CONFIG_RTC_DRV_DM355EVM) || defined(CONFIG_RTC_DRV_DM355EVM_MODULE)
+#define msp_has_rtc()		true
+#else
+#define msp_has_rtc()		false
+#endif
+
+#if defined(CONFIG_VIDEO_TVP514X) || defined(CONFIG_VIDEO_TVP514X_MODULE)
+#define msp_has_tvp()		true
+#else
+#define msp_has_tvp()		false
+#endif
+
+
+/*----------------------------------------------------------------------*/
+
+/* REVISIT for paranoia's sake, retry reads/writes on error */
+
+static struct i2c_client *msp430;
+
+/**
+ * dm355evm_msp_write - Writes a register in dm355evm_msp
+ * @value: the value to be written
+ * @reg: register address
+ *
+ * Returns result of operation - 0 is success, else negative errno
+ */
+int dm355evm_msp_write(u8 value, u8 reg)
+{
+	return i2c_smbus_write_byte_data(msp430, reg, value);
+}
+EXPORT_SYMBOL(dm355evm_msp_write);
+
+/**
+ * dm355evm_msp_read - Reads a register from dm355evm_msp
+ * @reg: register address
+ *
+ * Returns result of operation - value, or negative errno
+ */
+int dm355evm_msp_read(u8 reg)
+{
+	return i2c_smbus_read_byte_data(msp430, reg);
+}
+EXPORT_SYMBOL(dm355evm_msp_read);
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Many of the msp430 pins are just used as fixed-direction GPIOs.
+ * We could export a few more of them this way, if we wanted.
+ */
+#define MSP_GPIO(bit,reg)	((DM355EVM_MSP_ ## reg) << 3 | (bit))
+
+static const u8 msp_gpios[] = {
+	/* eight leds */
+	MSP_GPIO(0, LED), MSP_GPIO(1, LED),
+	MSP_GPIO(2, LED), MSP_GPIO(3, LED),
+	MSP_GPIO(4, LED), MSP_GPIO(5, LED),
+	MSP_GPIO(6, LED), MSP_GPIO(7, LED),
+	/* SW6 and the NTSC/nPAL jumper */
+	MSP_GPIO(0, SWITCH1), MSP_GPIO(1, SWITCH1),
+	MSP_GPIO(2, SWITCH1), MSP_GPIO(3, SWITCH1),
+	MSP_GPIO(4, SWITCH1),
+};
+
+#define MSP_GPIO_REG(offset)	(msp_gpios[(offset)] >> 3)
+#define MSP_GPIO_MASK(offset)	BIT(msp_gpios[(offset)] & 0x07)
+
+static int msp_gpio_in(struct gpio_chip *chip, unsigned offset)
+{
+	switch (MSP_GPIO_REG(offset)) {
+	case DM355EVM_MSP_SWITCH1:
+	case DM355EVM_MSP_SWITCH2:
+	case DM355EVM_MSP_SDMMC:
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static u8 msp_led_cache;
+
+static int msp_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	int reg, status;
+
+	reg = MSP_GPIO_REG(offset);
+	status = dm355evm_msp_read(reg);
+	if (status < 0)
+		return status;
+	if (reg == DM355EVM_MSP_LED)
+		msp_led_cache = status;
+	return status & MSP_GPIO_MASK(offset);
+}
+
+static int msp_gpio_out(struct gpio_chip *chip, unsigned offset, int value)
+{
+	int mask, bits;
+
+	/* NOTE:  there are some other signals that could be
+	 * packaged as output GPIOs, but they aren't as useful
+	 * as the LEDs ... so for now we don't.
+	 */
+	if (MSP_GPIO_REG(offset) != DM355EVM_MSP_LED)
+		return -EINVAL;
+
+	mask = MSP_GPIO_MASK(offset);
+	bits = msp_led_cache;
+
+	bits &= ~mask;
+	if (value)
+		bits |= mask;
+	msp_led_cache = bits;
+
+	return dm355evm_msp_write(bits, DM355EVM_MSP_LED);
+}
+
+static void msp_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	msp_gpio_out(chip, offset, value);
+}
+
+static struct gpio_chip dm355evm_msp_gpio = {
+	.label			= "dm355evm_msp",
+	.owner			= THIS_MODULE,
+	.direction_input	= msp_gpio_in,
+	.get			= msp_gpio_get,
+	.direction_output	= msp_gpio_out,
+	.set			= msp_gpio_set,
+	.base			= -EINVAL,		/* dynamic assignment */
+	.ngpio			= ARRAY_SIZE(msp_gpios),
+	.can_sleep		= true,
+};
+
+/*----------------------------------------------------------------------*/
+
+static struct device *add_child(struct i2c_client *client, const char *name,
+		void *pdata, unsigned pdata_len,
+		bool can_wakeup, int irq)
+{
+	struct platform_device	*pdev;
+	int			status;
+
+	pdev = platform_device_alloc(name, -1);
+	if (!pdev) {
+		dev_dbg(&client->dev, "can't alloc dev\n");
+		status = -ENOMEM;
+		goto err;
+	}
+
+	device_init_wakeup(&pdev->dev, can_wakeup);
+	pdev->dev.parent = &client->dev;
+
+	if (pdata) {
+		status = platform_device_add_data(pdev, pdata, pdata_len);
+		if (status < 0) {
+			dev_dbg(&pdev->dev, "can't add platform_data\n");
+			goto err;
+		}
+	}
+
+	if (irq) {
+		struct resource r = {
+			.start = irq,
+			.flags = IORESOURCE_IRQ,
+		};
+
+		status = platform_device_add_resources(pdev, &r, 1);
+		if (status < 0) {
+			dev_dbg(&pdev->dev, "can't add irq\n");
+			goto err;
+		}
+	}
+
+	status = platform_device_add(pdev);
+
+err:
+	if (status < 0) {
+		platform_device_put(pdev);
+		dev_err(&client->dev, "can't add %s dev\n", name);
+		return ERR_PTR(status);
+	}
+	return &pdev->dev;
+}
+
+static int add_children(struct i2c_client *client)
+{
+	static const struct {
+		int offset;
+		char *label;
+	} config_inputs[] = {
+		/* 8 == right after the LEDs */
+		{ 8 + 0, "sw6_1", },
+		{ 8 + 1, "sw6_2", },
+		{ 8 + 2, "sw6_3", },
+		{ 8 + 3, "sw6_4", },
+		{ 8 + 4, "NTSC/nPAL", },
+	};
+
+	struct device	*child;
+	int		status;
+	int		i;
+
+	/* GPIO-ish stuff */
+	dm355evm_msp_gpio.dev = &client->dev;
+	status = gpiochip_add(&dm355evm_msp_gpio);
+	if (status < 0)
+		return status;
+
+	/* LED output */
+	if (msp_has_leds()) {
+#define GPIO_LED(l)	.name = l, .active_low = true
+		static struct gpio_led evm_leds[] = {
+			{ GPIO_LED("dm355evm::ds14"),
+				.default_trigger = "heartbeat", },
+			{ GPIO_LED("dm355evm::ds15"),
+				.default_trigger = "mmc0", },
+			{ GPIO_LED("dm355evm::ds16"),
+				/* could also be a CE-ATA drive */
+				.default_trigger = "mmc1", },
+			{ GPIO_LED("dm355evm::ds17"),
+				.default_trigger = "nand-disk", },
+			{ GPIO_LED("dm355evm::ds18"), },
+			{ GPIO_LED("dm355evm::ds19"), },
+			{ GPIO_LED("dm355evm::ds20"), },
+			{ GPIO_LED("dm355evm::ds21"), },
+		};
+#undef GPIO_LED
+
+		struct gpio_led_platform_data evm_led_data = {
+			.num_leds	= ARRAY_SIZE(evm_leds),
+			.leds		= evm_leds,
+		};
+
+		for (i = 0; i < ARRAY_SIZE(evm_leds); i++)
+			evm_leds[i].gpio = i + dm355evm_msp_gpio.base;
+
+		/* NOTE:  these are the only fully programmable LEDs
+		 * on the board, since GPIO-61/ds22 (and many signals
+		 * going to DC7) must be used for AEMIF address lines
+		 * unless the top 1 GB of NAND is unused...
+		 */
+		child = add_child(client, "leds-gpio",
+				&evm_led_data, sizeof(evm_led_data),
+				false, 0);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+	}
+
+	/* configuration inputs */
+	for (i = 0; i < ARRAY_SIZE(config_inputs); i++) {
+		int gpio = dm355evm_msp_gpio.base + config_inputs[i].offset;
+
+		gpio_request(gpio, config_inputs[i].label);
+		gpio_direction_input(gpio);
+
+		/* make it easy for userspace to see these */
+		gpio_export(gpio, false);
+	}
+
+	/* RTC is a 32 bit counter, no alarm */
+	if (msp_has_rtc()) {
+		child = add_child(client, "rtc-dm355evm",
+				NULL, 0, false, 0);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+	}
+
+	/* input from buttons and IR remote (uses the IRQ) */
+	if (msp_has_keyboard()) {
+		child = add_child(client, "dm355evm_keys",
+				NULL, 0, true, client->irq);
+		if (IS_ERR(child))
+			return PTR_ERR(child);
+	}
+
+	return 0;
+}
+
+/*----------------------------------------------------------------------*/
+
+static void dm355evm_command(unsigned command)
+{
+	int status;
+
+	status = dm355evm_msp_write(command, DM355EVM_MSP_COMMAND);
+	if (status < 0)
+		dev_err(&msp430->dev, "command %d failure %d\n",
+				command, status);
+}
+
+static void dm355evm_power_off(void)
+{
+	dm355evm_command(MSP_COMMAND_POWEROFF);
+}
+
+static int dm355evm_msp_remove(struct i2c_client *client)
+{
+	pm_power_off = NULL;
+	msp430 = NULL;
+	return 0;
+}
+
+static int
+dm355evm_msp_probe(struct i2c_client *client, const struct i2c_device_id *id)
+{
+	int		status;
+	const char	*video = msp_has_tvp() ? "TVP5146" : "imager";
+
+	if (msp430)
+		return -EBUSY;
+	msp430 = client;
+
+	/* display revision status; doubles as sanity check */
+	status = dm355evm_msp_read(DM355EVM_MSP_FIRMREV);
+	if (status < 0)
+		goto fail;
+	dev_info(&client->dev, "firmware v.%02X, %s as video-in\n",
+			status, video);
+
+	/* mux video input:  either tvp5146 or some external imager */
+	status = dm355evm_msp_write(msp_has_tvp() ? 0 : MSP_VIDEO_IMAGER,
+			DM355EVM_MSP_VIDEO_IN);
+	if (status < 0)
+		dev_warn(&client->dev, "error %d muxing %s as video-in\n",
+			status, video);
+
+	/* init LED cache, and turn off the LEDs */
+	msp_led_cache = 0xff;
+	dm355evm_msp_write(msp_led_cache, DM355EVM_MSP_LED);
+
+	/* export capabilities we support */
+	status = add_children(client);
+	if (status < 0)
+		goto fail;
+
+	/* PM hookup */
+	pm_power_off = dm355evm_power_off;
+
+	return 0;
+
+fail:
+	/* FIXME remove children ... */
+	dm355evm_msp_remove(client);
+	return status;
+}
+
+static const struct i2c_device_id dm355evm_msp_ids[] = {
+	{ "dm355evm_msp", 0 },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(i2c, dm355evm_msp_ids);
+
+static struct i2c_driver dm355evm_msp_driver = {
+	.driver.name	= "dm355evm_msp",
+	.id_table	= dm355evm_msp_ids,
+	.probe		= dm355evm_msp_probe,
+	.remove		= dm355evm_msp_remove,
+};
+
+static int __init dm355evm_msp_init(void)
+{
+	return i2c_add_driver(&dm355evm_msp_driver);
+}
+subsys_initcall(dm355evm_msp_init);
+
+static void __exit dm355evm_msp_exit(void)
+{
+	i2c_del_driver(&dm355evm_msp_driver);
+}
+module_exit(dm355evm_msp_exit);
+
+MODULE_DESCRIPTION("Interface to MSP430 firmware on DM355EVM");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/i2c/dm355evm_msp.h b/include/linux/i2c/dm355evm_msp.h
new file mode 100644
index 000000000000..372470350fab
--- /dev/null
+++ b/include/linux/i2c/dm355evm_msp.h
@@ -0,0 +1,79 @@
+/*
+ * dm355evm_msp.h - support MSP430 microcontroller on DM355EVM board
+ */
+#ifndef __LINUX_I2C_DM355EVM_MSP
+#define __LINUX_I2C_DM355EVM_MSP
+
+/*
+ * Written against Spectrum's writeup for the A4 firmware revision,
+ * and tweaked to match source and rev D2 schematics by removing CPLD
+ * and NOR flash hooks (which were last appropriate in rev B boards).
+ *
+ * Note that the firmware supports a flavor of write posting ... to be
+ * sure a write completes, issue another read or write.
+ */
+
+/* utilities to access "registers" emulated by msp430 firmware */
+extern int dm355evm_msp_write(u8 value, u8 reg);
+extern int dm355evm_msp_read(u8 reg);
+
+
+/* command/control registers */
+#define DM355EVM_MSP_COMMAND		0x00
+#	define MSP_COMMAND_NULL		0
+#	define MSP_COMMAND_RESET_COLD	1
+#	define MSP_COMMAND_RESET_WARM	2
+#	define MSP_COMMAND_RESET_WARM_I	3
+#	define MSP_COMMAND_POWEROFF	4
+#	define MSP_COMMAND_IR_REINIT	5
+#define DM355EVM_MSP_STATUS		0x01
+#	define MSP_STATUS_BAD_OFFSET	BIT(0)
+#	define MSP_STATUS_BAD_COMMAND	BIT(1)
+#	define MSP_STATUS_POWER_ERROR	BIT(2)
+#	define MSP_STATUS_RXBUF_OVERRUN	BIT(3)
+#define DM355EVM_MSP_RESET		0x02	/* 0 bits == in reset */
+#	define MSP_RESET_DC5		BIT(0)
+#	define MSP_RESET_TVP5154	BIT(2)
+#	define MSP_RESET_IMAGER		BIT(3)
+#	define MSP_RESET_ETHERNET	BIT(4)
+#	define MSP_RESET_SYS		BIT(5)
+#	define MSP_RESET_AIC33		BIT(7)
+
+/* GPIO registers ... bit patterns mostly match the source MSP ports */
+#define DM355EVM_MSP_LED		0x03	/* active low (MSP P4) */
+#define DM355EVM_MSP_SWITCH1		0x04	/* (MSP P5, masked) */
+#	define MSP_SWITCH1_SW6_1	BIT(0)
+#	define MSP_SWITCH1_SW6_2	BIT(1)
+#	define MSP_SWITCH1_SW6_3	BIT(2)
+#	define MSP_SWITCH1_SW6_4	BIT(3)
+#	define MSP_SWITCH1_J1		BIT(4)	/* NTSC/PAL */
+#	define MSP_SWITCH1_MSP_INT	BIT(5)	/* active low */
+#define DM355EVM_MSP_SWITCH2		0x05	/* (MSP P6, masked) */
+#	define MSP_SWITCH2_SW10		BIT(3)
+#	define MSP_SWITCH2_SW11		BIT(4)
+#	define MSP_SWITCH2_SW12		BIT(5)
+#	define MSP_SWITCH2_SW13		BIT(6)
+#	define MSP_SWITCH2_SW14		BIT(7)
+#define DM355EVM_MSP_SDMMC		0x06	/* (MSP P2, masked) */
+#	define MSP_SDMMC_0_WP		BIT(1)
+#	define MSP_SDMMC_0_CD		BIT(2)	/* active low */
+#	define MSP_SDMMC_1_WP		BIT(3)
+#	define MSP_SDMMC_1_CD		BIT(4)	/* active low */
+#define DM355EVM_MSP_FIRMREV		0x07	/* not a GPIO (out of order) */
+#define DM355EVM_MSP_VIDEO_IN		0x08	/* (MSP P3, masked) */
+#	define MSP_VIDEO_IMAGER		BIT(7)	/* low == tvp5146 */
+
+/* power supply registers are currently omitted */
+
+/* RTC registers */
+#define DM355EVM_MSP_RTC_0		0x12	/* LSB */
+#define DM355EVM_MSP_RTC_1		0x13
+#define DM355EVM_MSP_RTC_2		0x14
+#define DM355EVM_MSP_RTC_3		0x15	/* MSB */
+
+/* input event queue registers; code == ((HIGH << 8) | LOW) */
+#define DM355EVM_MSP_INPUT_COUNT	0x16	/* decrement by reading LOW */
+#define DM355EVM_MSP_INPUT_HIGH		0x17
+#define DM355EVM_MSP_INPUT_LOW		0x18
+
+#endif /* __LINUX_I2C_DM355EVM_MSP */
-- 
cgit v1.2.3-70-g09d2


From f3298dc4f2277874d40cb4fc3a6e277317d6603b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2008 03:16:51 -0500
Subject: sanitize audit_socketcall

* don't bother with allocations
* now that it can't fail, make it return void

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  4 ++--
 kernel/auditsc.c      | 66 +++++++++++++++++++++++++++++----------------------
 net/socket.c          |  4 +---
 3 files changed, 41 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 26c4f6f65a46..466a953d4bf6 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -446,7 +446,7 @@ extern void audit_log_task_context(struct audit_buffer *ab);
 extern int __audit_ipc_obj(struct kern_ipc_perm *ipcp);
 extern int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode);
 extern int audit_bprm(struct linux_binprm *bprm);
-extern int audit_socketcall(int nargs, unsigned long *args);
+extern void audit_socketcall(int nargs, unsigned long *args);
 extern int audit_sockaddr(int len, void *addr);
 extern int __audit_fd_pair(int fd1, int fd2);
 extern int audit_set_macxattr(const char *name);
@@ -549,7 +549,7 @@ extern int audit_signals;
 #define audit_ipc_obj(i) ({ 0; })
 #define audit_ipc_set_perm(q,u,g,m) ({ 0; })
 #define audit_bprm(p) ({ 0; })
-#define audit_socketcall(n,a) ({ 0; })
+#define audit_socketcall(n,a) ((void)0)
 #define audit_fd_pair(n,a) ({ 0; })
 #define audit_sockaddr(len, addr) ({ 0; })
 #define audit_set_macxattr(n) do { ; } while (0)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index c2e43ebb1b68..5cda66466e14 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -168,12 +168,6 @@ struct audit_aux_data_execve {
 	struct mm_struct *mm;
 };
 
-struct audit_aux_data_socketcall {
-	struct audit_aux_data	d;
-	int			nargs;
-	unsigned long		args[0];
-};
-
 struct audit_aux_data_fd_pair {
 	struct	audit_aux_data d;
 	int	fd[2];
@@ -247,6 +241,14 @@ struct audit_context {
 	struct audit_tree_refs *trees, *first_trees;
 	int tree_count;
 
+	int type;
+	union {
+		struct {
+			int nargs;
+			long args[6];
+		} socketcall;
+	};
+
 #if AUDIT_DEBUG
 	int		    put_count;
 	int		    ino_count;
@@ -1226,6 +1228,27 @@ static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
 		audit_log_format(ab, " cap_fe=%d cap_fver=%x", name->fcap.fE, name->fcap_ver);
 }
 
+static void show_special(struct audit_context *context)
+{
+	struct audit_buffer *ab;
+	int i;
+
+	ab = audit_log_start(context, GFP_KERNEL, context->type);
+	if (!ab)
+		return;
+
+	switch (context->type) {
+	case AUDIT_SOCKETCALL: {
+		int nargs = context->socketcall.nargs;
+		audit_log_format(ab, "nargs=%d", nargs);
+		for (i = 0; i < nargs; i++)
+			audit_log_format(ab, " a%d=%lx", i,
+				context->socketcall.args[i]);
+		break; }
+	}
+	audit_log_end(ab);
+}
+
 static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
 {
 	const struct cred *cred;
@@ -1372,13 +1395,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			audit_log_execve_info(context, &ab, axi);
 			break; }
 
-		case AUDIT_SOCKETCALL: {
-			struct audit_aux_data_socketcall *axs = (void *)aux;
-			audit_log_format(ab, "nargs=%d", axs->nargs);
-			for (i=0; i<axs->nargs; i++)
-				audit_log_format(ab, " a%d=%lx", i, axs->args[i]);
-			break; }
-
 		case AUDIT_FD_PAIR: {
 			struct audit_aux_data_fd_pair *axs = (void *)aux;
 			audit_log_format(ab, "fd0=%d fd1=%d", axs->fd[0], axs->fd[1]);
@@ -1410,6 +1426,9 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		audit_log_end(ab);
 	}
 
+	if (context->type)
+		show_special(context);
+
 	if (context->sockaddr_len) {
 		ab = audit_log_start(context, GFP_KERNEL, AUDIT_SOCKADDR);
 		if (ab) {
@@ -1689,6 +1708,7 @@ void audit_syscall_exit(int valid, long return_code)
 		context->target_pid = 0;
 		context->target_sid = 0;
 		context->sockaddr_len = 0;
+		context->type = 0;
 		kfree(context->filterkey);
 		context->filterkey = NULL;
 		tsk->audit_context = context;
@@ -2406,27 +2426,17 @@ int audit_bprm(struct linux_binprm *bprm)
  * @nargs: number of args
  * @args: args array
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int audit_socketcall(int nargs, unsigned long *args)
+void audit_socketcall(int nargs, unsigned long *args)
 {
-	struct audit_aux_data_socketcall *ax;
 	struct audit_context *context = current->audit_context;
 
 	if (likely(!context || context->dummy))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax) + nargs * sizeof(unsigned long), GFP_KERNEL);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->nargs = nargs;
-	memcpy(ax->args, args, nargs * sizeof(unsigned long));
+		return;
 
-	ax->d.type = AUDIT_SOCKETCALL;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->type = AUDIT_SOCKETCALL;
+	context->socketcall.nargs = nargs;
+	memcpy(context->socketcall.args, args, nargs * sizeof(unsigned long));
 }
 
 /**
diff --git a/net/socket.c b/net/socket.c
index 2c730fc718ab..b41a92093e40 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2065,9 +2065,7 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args)
 	if (copy_from_user(a, args, nargs[call]))
 		return -EFAULT;
 
-	err = audit_socketcall(nargs[call] / sizeof(unsigned long), a);
-	if (err)
-		return err;
+	audit_socketcall(nargs[call] / sizeof(unsigned long), a);
 
 	a0 = a[0];
 	a1 = a[1];
-- 
cgit v1.2.3-70-g09d2


From a33e6751003c5ade603737d828b1519d980ce392 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2008 03:40:06 -0500
Subject: sanitize audit_ipc_obj()

* get rid of allocations
* make it return void
* simplify callers

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  9 +++---
 ipc/shm.c             |  4 +--
 ipc/util.c            |  9 ++----
 kernel/auditsc.c      | 88 ++++++++++++++++++++++-----------------------------
 4 files changed, 45 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 466a953d4bf6..f8578b9088e1 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -443,7 +443,7 @@ extern int  audit_set_loginuid(struct task_struct *task, uid_t loginuid);
 #define audit_get_loginuid(t) ((t)->loginuid)
 #define audit_get_sessionid(t) ((t)->sessionid)
 extern void audit_log_task_context(struct audit_buffer *ab);
-extern int __audit_ipc_obj(struct kern_ipc_perm *ipcp);
+extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp);
 extern int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode);
 extern int audit_bprm(struct linux_binprm *bprm);
 extern void audit_socketcall(int nargs, unsigned long *args);
@@ -460,11 +460,10 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
 				  const struct cred *old);
 extern int __audit_log_capset(pid_t pid, const struct cred *new, const struct cred *old);
 
-static inline int audit_ipc_obj(struct kern_ipc_perm *ipcp)
+static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_ipc_obj(ipcp);
-	return 0;
+		__audit_ipc_obj(ipcp);
 }
 static inline int audit_fd_pair(int fd1, int fd2)
 {
@@ -546,7 +545,7 @@ extern int audit_signals;
 #define audit_get_loginuid(t) (-1)
 #define audit_get_sessionid(t) (-1)
 #define audit_log_task_context(b) do { ; } while (0)
-#define audit_ipc_obj(i) ({ 0; })
+#define audit_ipc_obj(i) ((void)0)
 #define audit_ipc_set_perm(q,u,g,m) ({ 0; })
 #define audit_bprm(p) ({ 0; })
 #define audit_socketcall(n,a) ((void)0)
diff --git a/ipc/shm.c b/ipc/shm.c
index 38a055758a9b..57dd50046cef 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -747,9 +747,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf)
 			goto out;
 		}
 
-		err = audit_ipc_obj(&(shp->shm_perm));
-		if (err)
-			goto out_unlock;
+		audit_ipc_obj(&(shp->shm_perm));
 
 		if (!capable(CAP_IPC_LOCK)) {
 			uid_t euid = current_euid();
diff --git a/ipc/util.c b/ipc/util.c
index 5a1808c774a2..579552abd50a 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -624,10 +624,9 @@ void ipc_rcu_putref(void *ptr)
 int ipcperms (struct kern_ipc_perm *ipcp, short flag)
 {	/* flag will most probably be 0 or S_...UGO from <linux/stat.h> */
 	uid_t euid = current_euid();
-	int requested_mode, granted_mode, err;
+	int requested_mode, granted_mode;
 
-	if (unlikely((err = audit_ipc_obj(ipcp))))
-		return err;
+	audit_ipc_obj(ipcp);
 	requested_mode = (flag >> 6) | (flag >> 3) | flag;
 	granted_mode = ipcp->mode;
 	if (euid == ipcp->cuid ||
@@ -803,9 +802,7 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
 		goto out_up;
 	}
 
-	err = audit_ipc_obj(ipcp);
-	if (err)
-		goto out_unlock;
+	audit_ipc_obj(ipcp);
 
 	if (cmd == IPC_SET) {
 		err = audit_ipc_set_perm(extra_perm, perm->uid,
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 5cda66466e14..73504313264f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -247,6 +247,12 @@ struct audit_context {
 			int nargs;
 			long args[6];
 		} socketcall;
+		struct {
+			uid_t			uid;
+			gid_t			gid;
+			mode_t			mode;
+			u32			osid;
+		} ipc;
 	};
 
 #if AUDIT_DEBUG
@@ -605,19 +611,12 @@ static int audit_filter_rules(struct task_struct *tsk,
 					}
 				}
 				/* Find ipc objects that match */
-				if (ctx) {
-					struct audit_aux_data *aux;
-					for (aux = ctx->aux; aux;
-					     aux = aux->next) {
-						if (aux->type == AUDIT_IPC) {
-							struct audit_aux_data_ipcctl *axi = (void *)aux;
-							if (security_audit_rule_match(axi->osid, f->type, f->op, f->lsm_rule, ctx)) {
-								++result;
-								break;
-							}
-						}
-					}
-				}
+				if (!ctx || ctx->type != AUDIT_IPC)
+					break;
+				if (security_audit_rule_match(ctx->ipc.osid,
+							      f->type, f->op,
+							      f->lsm_rule, ctx))
+					++result;
 			}
 			break;
 		case AUDIT_ARG0:
@@ -1228,7 +1227,7 @@ static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
 		audit_log_format(ab, " cap_fe=%d cap_fver=%x", name->fcap.fE, name->fcap_ver);
 }
 
-static void show_special(struct audit_context *context)
+static void show_special(struct audit_context *context, int *call_panic)
 {
 	struct audit_buffer *ab;
 	int i;
@@ -1245,6 +1244,23 @@ static void show_special(struct audit_context *context)
 			audit_log_format(ab, " a%d=%lx", i,
 				context->socketcall.args[i]);
 		break; }
+	case AUDIT_IPC: {
+		u32 osid = context->ipc.osid;
+
+		audit_log_format(ab, "ouid=%u ogid=%u mode=%#o",
+			 context->ipc.uid, context->ipc.gid, context->ipc.mode);
+		if (osid) {
+			char *ctx = NULL;
+			u32 len;
+			if (security_secid_to_secctx(osid, &ctx, &len)) {
+				audit_log_format(ab, " osid=%u", osid);
+				*call_panic = 1;
+			} else {
+				audit_log_format(ab, " obj=%s", ctx);
+				security_release_secctx(ctx, len);
+			}
+		}
+		break; }
 	}
 	audit_log_end(ab);
 }
@@ -1363,26 +1379,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 				axi->mqstat.mq_msgsize, axi->mqstat.mq_curmsgs);
 			break; }
 
-		case AUDIT_IPC: {
-			struct audit_aux_data_ipcctl *axi = (void *)aux;
-			audit_log_format(ab, 
-				 "ouid=%u ogid=%u mode=%#o",
-				 axi->uid, axi->gid, axi->mode);
-			if (axi->osid != 0) {
-				char *ctx = NULL;
-				u32 len;
-				if (security_secid_to_secctx(
-						axi->osid, &ctx, &len)) {
-					audit_log_format(ab, " osid=%u",
-							axi->osid);
-					call_panic = 1;
-				} else {
-					audit_log_format(ab, " obj=%s", ctx);
-					security_release_secctx(ctx, len);
-				}
-			}
-			break; }
-
 		case AUDIT_IPC_SET_PERM: {
 			struct audit_aux_data_ipcctl *axi = (void *)aux;
 			audit_log_format(ab,
@@ -1427,7 +1423,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 	}
 
 	if (context->type)
-		show_special(context);
+		show_special(context, &call_panic);
 
 	if (context->sockaddr_len) {
 		ab = audit_log_start(context, GFP_KERNEL, AUDIT_SOCKADDR);
@@ -2349,25 +2345,15 @@ int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
  * audit_ipc_obj - record audit data for ipc object
  * @ipcp: ipc permissions
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_ipc_obj(struct kern_ipc_perm *ipcp)
+void __audit_ipc_obj(struct kern_ipc_perm *ipcp)
 {
-	struct audit_aux_data_ipcctl *ax;
 	struct audit_context *context = current->audit_context;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->uid = ipcp->uid;
-	ax->gid = ipcp->gid;
-	ax->mode = ipcp->mode;
-	security_ipc_getsecid(ipcp, &ax->osid);
-	ax->d.type = AUDIT_IPC;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->ipc.uid = ipcp->uid;
+	context->ipc.gid = ipcp->gid;
+	context->ipc.mode = ipcp->mode;
+	security_ipc_getsecid(ipcp, &context->ipc.osid);
+	context->type = AUDIT_IPC;
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From e816f370cbadd2afea9f1a42f232d0636137d563 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2008 03:47:15 -0500
Subject: sanitize audit_ipc_set_perm()

* get rid of allocations
* make it return void
* simplify callers

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  9 ++++----
 ipc/util.c            |  9 ++------
 kernel/auditsc.c      | 59 +++++++++++++++++++++++----------------------------
 3 files changed, 32 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index f8578b9088e1..b7abfe0d6737 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -444,7 +444,7 @@ extern int  audit_set_loginuid(struct task_struct *task, uid_t loginuid);
 #define audit_get_sessionid(t) ((t)->sessionid)
 extern void audit_log_task_context(struct audit_buffer *ab);
 extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp);
-extern int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode);
+extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode);
 extern int audit_bprm(struct linux_binprm *bprm);
 extern void audit_socketcall(int nargs, unsigned long *args);
 extern int audit_sockaddr(int len, void *addr);
@@ -471,11 +471,10 @@ static inline int audit_fd_pair(int fd1, int fd2)
 		return __audit_fd_pair(fd1, fd2);
 	return 0;
 }
-static inline int audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
+static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_ipc_set_perm(qbytes, uid, gid, mode);
-	return 0;
+		__audit_ipc_set_perm(qbytes, uid, gid, mode);
 }
 static inline int audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr)
 {
@@ -546,7 +545,7 @@ extern int audit_signals;
 #define audit_get_sessionid(t) (-1)
 #define audit_log_task_context(b) do { ; } while (0)
 #define audit_ipc_obj(i) ((void)0)
-#define audit_ipc_set_perm(q,u,g,m) ({ 0; })
+#define audit_ipc_set_perm(q,u,g,m) ((void)0)
 #define audit_bprm(p) ({ 0; })
 #define audit_socketcall(n,a) ((void)0)
 #define audit_fd_pair(n,a) ({ 0; })
diff --git a/ipc/util.c b/ipc/util.c
index 579552abd50a..7585a72e259b 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -803,13 +803,9 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
 	}
 
 	audit_ipc_obj(ipcp);
-
-	if (cmd == IPC_SET) {
-		err = audit_ipc_set_perm(extra_perm, perm->uid,
+	if (cmd == IPC_SET)
+		audit_ipc_set_perm(extra_perm, perm->uid,
 					 perm->gid, perm->mode);
-		if (err)
-			goto out_unlock;
-	}
 
 	euid = current_euid();
 	if (euid == ipcp->cuid ||
@@ -817,7 +813,6 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
 		return ipcp;
 
 	err = -EPERM;
-out_unlock:
 	ipc_unlock(ipcp);
 out_up:
 	up_write(&ids->rw_mutex);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 73504313264f..fbed62e05bce 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -151,16 +151,6 @@ struct audit_aux_data_mq_getsetattr {
 	struct mq_attr 		mqstat;
 };
 
-struct audit_aux_data_ipcctl {
-	struct audit_aux_data	d;
-	struct ipc_perm		p;
-	unsigned long		qbytes;
-	uid_t			uid;
-	gid_t			gid;
-	mode_t			mode;
-	u32			osid;
-};
-
 struct audit_aux_data_execve {
 	struct audit_aux_data	d;
 	int argc;
@@ -252,6 +242,11 @@ struct audit_context {
 			gid_t			gid;
 			mode_t			mode;
 			u32			osid;
+			int			has_perm;
+			uid_t			perm_uid;
+			gid_t			perm_gid;
+			mode_t			perm_mode;
+			unsigned long		qbytes;
 		} ipc;
 	};
 
@@ -1260,6 +1255,19 @@ static void show_special(struct audit_context *context, int *call_panic)
 				security_release_secctx(ctx, len);
 			}
 		}
+		if (context->ipc.has_perm) {
+			audit_log_end(ab);
+			ab = audit_log_start(context, GFP_KERNEL,
+					     AUDIT_IPC_SET_PERM);
+			audit_log_format(ab,
+				"qbytes=%lx ouid=%u ogid=%u mode=%#o",
+				context->ipc.qbytes,
+				context->ipc.perm_uid,
+				context->ipc.perm_gid,
+				context->ipc.perm_mode);
+			if (!ab)
+				return;
+		}
 		break; }
 	}
 	audit_log_end(ab);
@@ -1379,13 +1387,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 				axi->mqstat.mq_msgsize, axi->mqstat.mq_curmsgs);
 			break; }
 
-		case AUDIT_IPC_SET_PERM: {
-			struct audit_aux_data_ipcctl *axi = (void *)aux;
-			audit_log_format(ab,
-				"qbytes=%lx ouid=%u ogid=%u mode=%#o",
-				axi->qbytes, axi->uid, axi->gid, axi->mode);
-			break; }
-
 		case AUDIT_EXECVE: {
 			struct audit_aux_data_execve *axi = (void *)aux;
 			audit_log_execve_info(context, &ab, axi);
@@ -2352,6 +2353,7 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp)
 	context->ipc.uid = ipcp->uid;
 	context->ipc.gid = ipcp->gid;
 	context->ipc.mode = ipcp->mode;
+	context->ipc.has_perm = 0;
 	security_ipc_getsecid(ipcp, &context->ipc.osid);
 	context->type = AUDIT_IPC;
 }
@@ -2363,26 +2365,17 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp)
  * @gid: msgq group id
  * @mode: msgq mode (permissions)
  *
- * Returns 0 for success or NULL context or < 0 on error.
+ * Called only after audit_ipc_obj().
  */
-int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
+void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
 {
-	struct audit_aux_data_ipcctl *ax;
 	struct audit_context *context = current->audit_context;
 
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->qbytes = qbytes;
-	ax->uid = uid;
-	ax->gid = gid;
-	ax->mode = mode;
-
-	ax->d.type = AUDIT_IPC_SET_PERM;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->ipc.qbytes = qbytes;
+	context->ipc.perm_uid = uid;
+	context->ipc.perm_gid = gid;
+	context->ipc.perm_mode = mode;
+	context->ipc.has_perm = 1;
 }
 
 int audit_bprm(struct linux_binprm *bprm)
-- 
cgit v1.2.3-70-g09d2


From 7392906ea915b9a2c14dea32b3604b4e178f82f7 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2008 06:58:59 -0500
Subject: sanitize audit_mq_getsetattr()

* get rid of allocations
* make it return void
* don't duplicate parts of audit_dummy_context()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  9 ++++-----
 ipc/mqueue.c          |  6 +-----
 kernel/auditsc.c      | 54 ++++++++++++++++-----------------------------------
 3 files changed, 22 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index b7abfe0d6737..b7707e577b80 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -454,7 +454,7 @@ extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr
 extern int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout);
 extern int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout);
 extern int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification);
-extern int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat);
+extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat);
 extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
 				  const struct cred *new,
 				  const struct cred *old);
@@ -500,11 +500,10 @@ static inline int audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_n
 		return __audit_mq_notify(mqdes, u_notification);
 	return 0;
 }
-static inline int audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
+static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_mq_getsetattr(mqdes, mqstat);
-	return 0;
+		__audit_mq_getsetattr(mqdes, mqstat);
 }
 
 static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm,
@@ -555,7 +554,7 @@ extern int audit_signals;
 #define audit_mq_timedsend(d,l,p,t) ({ 0; })
 #define audit_mq_timedreceive(d,l,p,t) ({ 0; })
 #define audit_mq_notify(d,n) ({ 0; })
-#define audit_mq_getsetattr(d,s) ({ 0; })
+#define audit_mq_getsetattr(d,s) ((void)0)
 #define audit_log_bprm_fcaps(b, ncr, ocr) ({ 0; })
 #define audit_log_capset(pid, ncr, ocr) ({ 0; })
 #define audit_ptrace(t) ((void)0)
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index d9393f8e4c3e..7563611c6615 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1150,11 +1150,7 @@ asmlinkage long sys_mq_getsetattr(mqd_t mqdes,
 	omqstat = info->attr;
 	omqstat.mq_flags = filp->f_flags & O_NONBLOCK;
 	if (u_mqstat) {
-		ret = audit_mq_getsetattr(mqdes, &mqstat);
-		if (ret != 0) {
-			spin_unlock(&info->lock);
-			goto out_fput;
-		}
+		audit_mq_getsetattr(mqdes, &mqstat);
 		if (mqstat.mq_flags & O_NONBLOCK)
 			filp->f_flags |= O_NONBLOCK;
 		else
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fbed62e05bce..c50178c7e245 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -145,12 +145,6 @@ struct audit_aux_data_mq_notify {
 	struct sigevent 	notification;
 };
 
-struct audit_aux_data_mq_getsetattr {
-	struct audit_aux_data	d;
-	mqd_t			mqdes;
-	struct mq_attr 		mqstat;
-};
-
 struct audit_aux_data_execve {
 	struct audit_aux_data	d;
 	int argc;
@@ -248,6 +242,10 @@ struct audit_context {
 			mode_t			perm_mode;
 			unsigned long		qbytes;
 		} ipc;
+		struct {
+			mqd_t			mqdes;
+			struct mq_attr 		mqstat;
+		} mq_getsetattr;
 	};
 
 #if AUDIT_DEBUG
@@ -1269,6 +1267,15 @@ static void show_special(struct audit_context *context, int *call_panic)
 				return;
 		}
 		break; }
+	case AUDIT_MQ_GETSETATTR: {
+		struct mq_attr *attr = &context->mq_getsetattr.mqstat;
+		audit_log_format(ab,
+			"mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld "
+			"mq_curmsgs=%ld ",
+			context->mq_getsetattr.mqdes,
+			attr->mq_flags, attr->mq_maxmsg,
+			attr->mq_msgsize, attr->mq_curmsgs);
+		break; }
 	}
 	audit_log_end(ab);
 }
@@ -1377,16 +1384,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 				axi->notification.sigev_signo);
 			break; }
 
-		case AUDIT_MQ_GETSETATTR: {
-			struct audit_aux_data_mq_getsetattr *axi = (void *)aux;
-			audit_log_format(ab,
-				"mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld "
-				"mq_curmsgs=%ld ",
-				axi->mqdes,
-				axi->mqstat.mq_flags, axi->mqstat.mq_maxmsg,
-				axi->mqstat.mq_msgsize, axi->mqstat.mq_curmsgs);
-			break; }
-
 		case AUDIT_EXECVE: {
 			struct audit_aux_data_execve *axi = (void *)aux;
 			audit_log_execve_info(context, &ab, axi);
@@ -2316,30 +2313,13 @@ int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification)
  * @mqdes: MQ descriptor
  * @mqstat: MQ flags
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
+void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
 {
-	struct audit_aux_data_mq_getsetattr *ax;
 	struct audit_context *context = current->audit_context;
-
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->mqdes = mqdes;
-	ax->mqstat = *mqstat;
-
-	ax->d.type = AUDIT_MQ_GETSETATTR;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->mq_getsetattr.mqdes = mqdes;
+	context->mq_getsetattr.mqstat = *mqstat;
+	context->type = AUDIT_MQ_GETSETATTR;
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 20114f71b27cafeb7c7e41d2b0f0b68c3fbb022b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2008 07:16:12 -0500
Subject: sanitize audit_mq_notify()

* don't copy_from_user() twice
* don't bother with allocations
* don't duplicate parts of audit_dummy_context()
* make it return void

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  9 ++++-----
 ipc/mqueue.c          | 14 ++++++-------
 kernel/auditsc.c      | 56 +++++++++++++++------------------------------------
 3 files changed, 27 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index b7707e577b80..8101d2c4a995 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -453,7 +453,7 @@ extern int audit_set_macxattr(const char *name);
 extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr);
 extern int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout);
 extern int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout);
-extern int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification);
+extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification);
 extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat);
 extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
 				  const struct cred *new,
@@ -494,11 +494,10 @@ static inline int audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned in
 		return __audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout);
 	return 0;
 }
-static inline int audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification)
+static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_mq_notify(mqdes, u_notification);
-	return 0;
+		__audit_mq_notify(mqdes, notification);
 }
 static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
 {
@@ -553,7 +552,7 @@ extern int audit_signals;
 #define audit_mq_open(o,m,a) ({ 0; })
 #define audit_mq_timedsend(d,l,p,t) ({ 0; })
 #define audit_mq_timedreceive(d,l,p,t) ({ 0; })
-#define audit_mq_notify(d,n) ({ 0; })
+#define audit_mq_notify(d,n) ((void)0)
 #define audit_mq_getsetattr(d,s) ((void)0)
 #define audit_log_bprm_fcaps(b, ncr, ocr) ({ 0; })
 #define audit_log_capset(pid, ncr, ocr) ({ 0; })
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 7563611c6615..e7b2f68f8d77 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1003,17 +1003,17 @@ asmlinkage long sys_mq_notify(mqd_t mqdes,
 	struct mqueue_inode_info *info;
 	struct sk_buff *nc;
 
-	ret = audit_mq_notify(mqdes, u_notification);
-	if (ret != 0)
-		return ret;
-
-	nc = NULL;
-	sock = NULL;
-	if (u_notification != NULL) {
+	if (u_notification) {
 		if (copy_from_user(&notification, u_notification,
 					sizeof(struct sigevent)))
 			return -EFAULT;
+	}
+
+	audit_mq_notify(mqdes, u_notification ? &notification : NULL);
 
+	nc = NULL;
+	sock = NULL;
+	if (u_notification != NULL) {
 		if (unlikely(notification.sigev_notify != SIGEV_NONE &&
 			     notification.sigev_notify != SIGEV_SIGNAL &&
 			     notification.sigev_notify != SIGEV_THREAD))
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index c50178c7e245..3ece960de894 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -139,12 +139,6 @@ struct audit_aux_data_mq_sendrecv {
 	struct timespec		abs_timeout;
 };
 
-struct audit_aux_data_mq_notify {
-	struct audit_aux_data	d;
-	mqd_t			mqdes;
-	struct sigevent 	notification;
-};
-
 struct audit_aux_data_execve {
 	struct audit_aux_data	d;
 	int argc;
@@ -246,6 +240,10 @@ struct audit_context {
 			mqd_t			mqdes;
 			struct mq_attr 		mqstat;
 		} mq_getsetattr;
+		struct {
+			mqd_t			mqdes;
+			int			sigev_signo;
+		} mq_notify;
 	};
 
 #if AUDIT_DEBUG
@@ -1267,6 +1265,11 @@ static void show_special(struct audit_context *context, int *call_panic)
 				return;
 		}
 		break; }
+	case AUDIT_MQ_NOTIFY: {
+		audit_log_format(ab, "mqdes=%d sigev_signo=%d",
+				context->mq_notify.mqdes,
+				context->mq_notify.sigev_signo);
+		break; }
 	case AUDIT_MQ_GETSETATTR: {
 		struct mq_attr *attr = &context->mq_getsetattr.mqstat;
 		audit_log_format(ab,
@@ -1376,14 +1379,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 				axi->abs_timeout.tv_sec, axi->abs_timeout.tv_nsec);
 			break; }
 
-		case AUDIT_MQ_NOTIFY: {
-			struct audit_aux_data_mq_notify *axi = (void *)aux;
-			audit_log_format(ab,
-				"mqdes=%d sigev_signo=%d",
-				axi->mqdes,
-				axi->notification.sigev_signo);
-			break; }
-
 		case AUDIT_EXECVE: {
 			struct audit_aux_data_execve *axi = (void *)aux;
 			audit_log_execve_info(context, &ab, axi);
@@ -2274,38 +2269,19 @@ int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len,
  * @mqdes: MQ descriptor
  * @u_notification: Notification event
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
 
-int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification)
+void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification)
 {
-	struct audit_aux_data_mq_notify *ax;
 	struct audit_context *context = current->audit_context;
 
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	if (u_notification != NULL) {
-		if (copy_from_user(&ax->notification, u_notification, sizeof(ax->notification))) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		memset(&ax->notification, 0, sizeof(ax->notification));
-
-	ax->mqdes = mqdes;
+	if (notification)
+		context->mq_notify.sigev_signo = notification->sigev_signo;
+	else
+		context->mq_notify.sigev_signo = 0;
 
-	ax->d.type = AUDIT_MQ_NOTIFY;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->mq_notify.mqdes = mqdes;
+	context->type = AUDIT_MQ_NOTIFY;
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From c32c8af43b9adde8d6f938d8e6328c13b8de79ac Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 14 Dec 2008 03:46:48 -0500
Subject: sanitize AUDIT_MQ_SENDRECV

* logging the original value of *msg_prio in mq_timedreceive(2)
  is insane - the argument is write-only (i.e. syscall always
  ignores the original value and only overwrites it).
* merge __audit_mq_timed{send,receive}
* don't do copy_from_user() twice
* don't mess with allocations in auditsc part
* ... and don't bother checking !audit_enabled and !context in there -
  we'd already checked for audit_dummy_context().

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  17 ++-----
 ipc/mqueue.c          |  54 +++++++++++----------
 kernel/auditsc.c      | 127 ++++++++++++--------------------------------------
 3 files changed, 63 insertions(+), 135 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 8101d2c4a995..67f0cdd991ba 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -451,8 +451,7 @@ extern int audit_sockaddr(int len, void *addr);
 extern int __audit_fd_pair(int fd1, int fd2);
 extern int audit_set_macxattr(const char *name);
 extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr);
-extern int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout);
-extern int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout);
+extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout);
 extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification);
 extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat);
 extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
@@ -482,17 +481,10 @@ static inline int audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u
 		return __audit_mq_open(oflag, mode, u_attr);
 	return 0;
 }
-static inline int audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec __user *u_abs_timeout)
+static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_mq_timedsend(mqdes, msg_len, msg_prio, u_abs_timeout);
-	return 0;
-}
-static inline int audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout)
-{
-	if (unlikely(!audit_dummy_context()))
-		return __audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout);
-	return 0;
+		__audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout);
 }
 static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification)
 {
@@ -550,8 +542,7 @@ extern int audit_signals;
 #define audit_sockaddr(len, addr) ({ 0; })
 #define audit_set_macxattr(n) do { ; } while (0)
 #define audit_mq_open(o,m,a) ({ 0; })
-#define audit_mq_timedsend(d,l,p,t) ({ 0; })
-#define audit_mq_timedreceive(d,l,p,t) ({ 0; })
+#define audit_mq_sendrecv(d,l,p,t) ((void)0)
 #define audit_mq_notify(d,n) ((void)0)
 #define audit_mq_getsetattr(d,s) ((void)0)
 #define audit_log_bprm_fcaps(b, ncr, ocr) ({ 0; })
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index e7b2f68f8d77..192da806c283 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -524,31 +524,27 @@ static void __do_notify(struct mqueue_inode_info *info)
 	wake_up(&info->wait_q);
 }
 
-static long prepare_timeout(const struct timespec __user *u_arg)
+static long prepare_timeout(struct timespec *p)
 {
-	struct timespec ts, nowts;
+	struct timespec nowts;
 	long timeout;
 
-	if (u_arg) {
-		if (unlikely(copy_from_user(&ts, u_arg,
-					sizeof(struct timespec))))
-			return -EFAULT;
-
-		if (unlikely(ts.tv_nsec < 0 || ts.tv_sec < 0
-			|| ts.tv_nsec >= NSEC_PER_SEC))
+	if (p) {
+		if (unlikely(p->tv_nsec < 0 || p->tv_sec < 0
+			|| p->tv_nsec >= NSEC_PER_SEC))
 			return -EINVAL;
 		nowts = CURRENT_TIME;
 		/* first subtract as jiffies can't be too big */
-		ts.tv_sec -= nowts.tv_sec;
-		if (ts.tv_nsec < nowts.tv_nsec) {
-			ts.tv_nsec += NSEC_PER_SEC;
-			ts.tv_sec--;
+		p->tv_sec -= nowts.tv_sec;
+		if (p->tv_nsec < nowts.tv_nsec) {
+			p->tv_nsec += NSEC_PER_SEC;
+			p->tv_sec--;
 		}
-		ts.tv_nsec -= nowts.tv_nsec;
-		if (ts.tv_sec < 0)
+		p->tv_nsec -= nowts.tv_nsec;
+		if (p->tv_sec < 0)
 			return 0;
 
-		timeout = timespec_to_jiffies(&ts) + 1;
+		timeout = timespec_to_jiffies(p) + 1;
 	} else
 		return MAX_SCHEDULE_TIMEOUT;
 
@@ -829,17 +825,22 @@ asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
 	struct ext_wait_queue *receiver;
 	struct msg_msg *msg_ptr;
 	struct mqueue_inode_info *info;
+	struct timespec ts, *p = NULL;
 	long timeout;
 	int ret;
 
-	ret = audit_mq_timedsend(mqdes, msg_len, msg_prio, u_abs_timeout);
-	if (ret != 0)
-		return ret;
+	if (u_abs_timeout) {
+		if (copy_from_user(&ts, u_abs_timeout, 
+					sizeof(struct timespec)))
+			return -EFAULT;
+		p = &ts;
+	}
 
 	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
 		return -EINVAL;
 
-	timeout = prepare_timeout(u_abs_timeout);
+	audit_mq_sendrecv(mqdes, msg_len, msg_prio, p);
+	timeout = prepare_timeout(p);
 
 	ret = -EBADF;
 	filp = fget(mqdes);
@@ -918,12 +919,17 @@ asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
 	struct inode *inode;
 	struct mqueue_inode_info *info;
 	struct ext_wait_queue wait;
+	struct timespec ts, *p = NULL;
 
-	ret = audit_mq_timedreceive(mqdes, msg_len, u_msg_prio, u_abs_timeout);
-	if (ret != 0)
-		return ret;
+	if (u_abs_timeout) {
+		if (copy_from_user(&ts, u_abs_timeout, 
+					sizeof(struct timespec)))
+			return -EFAULT;
+		p = &ts;
+	}
 
-	timeout = prepare_timeout(u_abs_timeout);
+	audit_mq_sendrecv(mqdes, msg_len, 0, p);
+	timeout = prepare_timeout(p);
 
 	ret = -EBADF;
 	filp = fget(mqdes);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 3ece960de894..140c47453470 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -131,14 +131,6 @@ struct audit_aux_data_mq_open {
 	struct mq_attr		attr;
 };
 
-struct audit_aux_data_mq_sendrecv {
-	struct audit_aux_data	d;
-	mqd_t			mqdes;
-	size_t			msg_len;
-	unsigned int		msg_prio;
-	struct timespec		abs_timeout;
-};
-
 struct audit_aux_data_execve {
 	struct audit_aux_data	d;
 	int argc;
@@ -244,6 +236,12 @@ struct audit_context {
 			mqd_t			mqdes;
 			int			sigev_signo;
 		} mq_notify;
+		struct {
+			mqd_t			mqdes;
+			size_t			msg_len;
+			unsigned int		msg_prio;
+			struct timespec		abs_timeout;
+		} mq_sendrecv;
 	};
 
 #if AUDIT_DEBUG
@@ -1265,6 +1263,16 @@ static void show_special(struct audit_context *context, int *call_panic)
 				return;
 		}
 		break; }
+	case AUDIT_MQ_SENDRECV: {
+		audit_log_format(ab,
+			"mqdes=%d msg_len=%zd msg_prio=%u "
+			"abs_timeout_sec=%ld abs_timeout_nsec=%ld",
+			context->mq_sendrecv.mqdes,
+			context->mq_sendrecv.msg_len,
+			context->mq_sendrecv.msg_prio,
+			context->mq_sendrecv.abs_timeout.tv_sec,
+			context->mq_sendrecv.abs_timeout.tv_nsec);
+		break; }
 	case AUDIT_MQ_NOTIFY: {
 		audit_log_format(ab, "mqdes=%d sigev_signo=%d",
 				context->mq_notify.mqdes,
@@ -1370,15 +1378,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 				axi->attr.mq_curmsgs);
 			break; }
 
-		case AUDIT_MQ_SENDRECV: {
-			struct audit_aux_data_mq_sendrecv *axi = (void *)aux;
-			audit_log_format(ab,
-				"mqdes=%d msg_len=%zd msg_prio=%u "
-				"abs_timeout_sec=%ld abs_timeout_nsec=%ld",
-				axi->mqdes, axi->msg_len, axi->msg_prio,
-				axi->abs_timeout.tv_sec, axi->abs_timeout.tv_nsec);
-			break; }
-
 		case AUDIT_EXECVE: {
 			struct audit_aux_data_execve *axi = (void *)aux;
 			audit_log_execve_info(context, &ab, axi);
@@ -2171,97 +2170,29 @@ int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr)
 }
 
 /**
- * __audit_mq_timedsend - record audit data for a POSIX MQ timed send
+ * __audit_mq_sendrecv - record audit data for a POSIX MQ timed send/receive
  * @mqdes: MQ descriptor
  * @msg_len: Message length
  * @msg_prio: Message priority
- * @u_abs_timeout: Message timeout in absolute time
- *
- * Returns 0 for success or NULL context or < 0 on error.
- */
-int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
-			const struct timespec __user *u_abs_timeout)
-{
-	struct audit_aux_data_mq_sendrecv *ax;
-	struct audit_context *context = current->audit_context;
-
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	if (u_abs_timeout != NULL) {
-		if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout));
-
-	ax->mqdes = mqdes;
-	ax->msg_len = msg_len;
-	ax->msg_prio = msg_prio;
-
-	ax->d.type = AUDIT_MQ_SENDRECV;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
-}
-
-/**
- * __audit_mq_timedreceive - record audit data for a POSIX MQ timed receive
- * @mqdes: MQ descriptor
- * @msg_len: Message length
- * @u_msg_prio: Message priority
- * @u_abs_timeout: Message timeout in absolute time
+ * @abs_timeout: Message timeout in absolute time
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len,
-				unsigned int __user *u_msg_prio,
-				const struct timespec __user *u_abs_timeout)
+void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
+			const struct timespec *abs_timeout)
 {
-	struct audit_aux_data_mq_sendrecv *ax;
 	struct audit_context *context = current->audit_context;
+	struct timespec *p = &context->mq_sendrecv.abs_timeout;
 
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	if (u_msg_prio != NULL) {
-		if (get_user(ax->msg_prio, u_msg_prio)) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		ax->msg_prio = 0;
-
-	if (u_abs_timeout != NULL) {
-		if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout));
+	if (abs_timeout)
+		memcpy(p, abs_timeout, sizeof(struct timespec));
+	else
+		memset(p, 0, sizeof(struct timespec));
 
-	ax->mqdes = mqdes;
-	ax->msg_len = msg_len;
+	context->mq_sendrecv.mqdes = mqdes;
+	context->mq_sendrecv.msg_len = msg_len;
+	context->mq_sendrecv.msg_prio = msg_prio;
 
-	ax->d.type = AUDIT_MQ_SENDRECV;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->type = AUDIT_MQ_SENDRECV;
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 564f6993ffef656aebaf46cf2f1f6cb4f5c97207 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 14 Dec 2008 04:02:26 -0500
Subject: sanitize audit_mq_open()

* don't bother with allocations
* don't do double copy_from_user()
* don't duplicate parts of check for audit_dummy_context()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  9 ++++---
 ipc/mqueue.c          | 23 +++++++++---------
 kernel/auditsc.c      | 65 ++++++++++++++++++---------------------------------
 3 files changed, 38 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 67f0cdd991ba..54978bdd2bd4 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -450,7 +450,7 @@ extern void audit_socketcall(int nargs, unsigned long *args);
 extern int audit_sockaddr(int len, void *addr);
 extern int __audit_fd_pair(int fd1, int fd2);
 extern int audit_set_macxattr(const char *name);
-extern int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr);
+extern void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr);
 extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout);
 extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification);
 extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat);
@@ -475,11 +475,10 @@ static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid
 	if (unlikely(!audit_dummy_context()))
 		__audit_ipc_set_perm(qbytes, uid, gid, mode);
 }
-static inline int audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr)
+static inline void audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_mq_open(oflag, mode, u_attr);
-	return 0;
+		__audit_mq_open(oflag, mode, attr);
 }
 static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout)
 {
@@ -541,7 +540,7 @@ extern int audit_signals;
 #define audit_fd_pair(n,a) ({ 0; })
 #define audit_sockaddr(len, addr) ({ 0; })
 #define audit_set_macxattr(n) do { ; } while (0)
-#define audit_mq_open(o,m,a) ({ 0; })
+#define audit_mq_open(o,m,a) ((void)0)
 #define audit_mq_sendrecv(d,l,p,t) ((void)0)
 #define audit_mq_notify(d,n) ((void)0)
 #define audit_mq_getsetattr(d,s) ((void)0)
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 192da806c283..d448b69672b5 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -588,22 +588,18 @@ static int mq_attr_ok(struct mq_attr *attr)
  * Invoked when creating a new queue via sys_mq_open
  */
 static struct file *do_create(struct dentry *dir, struct dentry *dentry,
-			int oflag, mode_t mode, struct mq_attr __user *u_attr)
+			int oflag, mode_t mode, struct mq_attr *attr)
 {
 	const struct cred *cred = current_cred();
-	struct mq_attr attr;
 	struct file *result;
 	int ret;
 
-	if (u_attr) {
-		ret = -EFAULT;
-		if (copy_from_user(&attr, u_attr, sizeof(attr)))
-			goto out;
+	if (attr) {
 		ret = -EINVAL;
-		if (!mq_attr_ok(&attr))
+		if (!mq_attr_ok(attr))
 			goto out;
 		/* store for use during create */
-		dentry->d_fsdata = &attr;
+		dentry->d_fsdata = attr;
 	}
 
 	mode &= ~current->fs->umask;
@@ -660,11 +656,13 @@ asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode,
 	struct dentry *dentry;
 	struct file *filp;
 	char *name;
+	struct mq_attr attr;
 	int fd, error;
 
-	error = audit_mq_open(oflag, mode, u_attr);
-	if (error != 0)
-		return error;
+	if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
+		return -EFAULT;
+
+	audit_mq_open(oflag, mode, u_attr ? &attr : NULL);
 
 	if (IS_ERR(name = getname(u_name)))
 		return PTR_ERR(name);
@@ -690,7 +688,8 @@ asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode,
 			filp = do_open(dentry, oflag);
 		} else {
 			filp = do_create(mqueue_mnt->mnt_root, dentry,
-						oflag, mode, u_attr);
+						oflag, mode,
+						u_attr ? &attr : NULL);
 		}
 	} else {
 		error = -ENOENT;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 140c47453470..83e946f1cdde 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -124,13 +124,6 @@ struct audit_aux_data {
 /* Number of target pids per aux struct. */
 #define AUDIT_AUX_PIDS	16
 
-struct audit_aux_data_mq_open {
-	struct audit_aux_data	d;
-	int			oflag;
-	mode_t			mode;
-	struct mq_attr		attr;
-};
-
 struct audit_aux_data_execve {
 	struct audit_aux_data	d;
 	int argc;
@@ -242,6 +235,11 @@ struct audit_context {
 			unsigned int		msg_prio;
 			struct timespec		abs_timeout;
 		} mq_sendrecv;
+		struct {
+			int			oflag;
+			mode_t			mode;
+			struct mq_attr		attr;
+		} mq_open;
 	};
 
 #if AUDIT_DEBUG
@@ -1263,6 +1261,16 @@ static void show_special(struct audit_context *context, int *call_panic)
 				return;
 		}
 		break; }
+	case AUDIT_MQ_OPEN: {
+		audit_log_format(ab,
+			"oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld "
+			"mq_msgsize=%ld mq_curmsgs=%ld",
+			context->mq_open.oflag, context->mq_open.mode,
+			context->mq_open.attr.mq_flags,
+			context->mq_open.attr.mq_maxmsg,
+			context->mq_open.attr.mq_msgsize,
+			context->mq_open.attr.mq_curmsgs);
+		break; }
 	case AUDIT_MQ_SENDRECV: {
 		audit_log_format(ab,
 			"mqdes=%d msg_len=%zd msg_prio=%u "
@@ -1368,15 +1376,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			continue; /* audit_panic has been called */
 
 		switch (aux->type) {
-		case AUDIT_MQ_OPEN: {
-			struct audit_aux_data_mq_open *axi = (void *)aux;
-			audit_log_format(ab,
-				"oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld "
-				"mq_msgsize=%ld mq_curmsgs=%ld",
-				axi->oflag, axi->mode, axi->attr.mq_flags,
-				axi->attr.mq_maxmsg, axi->attr.mq_msgsize,
-				axi->attr.mq_curmsgs);
-			break; }
 
 		case AUDIT_EXECVE: {
 			struct audit_aux_data_execve *axi = (void *)aux;
@@ -2135,38 +2134,20 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
  * @mode: mode bits
  * @u_attr: queue attributes
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr)
+void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr)
 {
-	struct audit_aux_data_mq_open *ax;
 	struct audit_context *context = current->audit_context;
 
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	if (u_attr != NULL) {
-		if (copy_from_user(&ax->attr, u_attr, sizeof(ax->attr))) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		memset(&ax->attr, 0, sizeof(ax->attr));
+	if (attr)
+		memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr));
+	else
+		memset(&context->mq_open.attr, 0, sizeof(struct mq_attr));
 
-	ax->oflag = oflag;
-	ax->mode = mode;
+	context->mq_open.oflag = oflag;
+	context->mq_open.mode = mode;
 
-	ax->d.type = AUDIT_MQ_OPEN;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->type = AUDIT_MQ_OPEN;
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 157cf649a735a2f7e8dba0ed08e6e38b6c30d886 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 14 Dec 2008 04:57:47 -0500
Subject: sanitize audit_fd_pair()

* no allocations
* return void

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/pipe.c             |  7 +------
 include/linux/audit.h |  9 ++++-----
 kernel/auditsc.c      | 44 ++++++++++++++------------------------------
 net/socket.c          |  9 +--------
 4 files changed, 20 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/fs/pipe.c b/fs/pipe.c
index aaf797bd57b9..891697112f66 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1016,10 +1016,7 @@ int do_pipe_flags(int *fd, int flags)
 		goto err_fdr;
 	fdw = error;
 
-	error = audit_fd_pair(fdr, fdw);
-	if (error < 0)
-		goto err_fdw;
-
+	audit_fd_pair(fdr, fdw);
 	fd_install(fdr, fr);
 	fd_install(fdw, fw);
 	fd[0] = fdr;
@@ -1027,8 +1024,6 @@ int do_pipe_flags(int *fd, int flags)
 
 	return 0;
 
- err_fdw:
-	put_unused_fd(fdw);
  err_fdr:
 	put_unused_fd(fdr);
  err_read_pipe:
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 54978bdd2bd4..bd59cd1e3219 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -448,7 +448,7 @@ extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mod
 extern int audit_bprm(struct linux_binprm *bprm);
 extern void audit_socketcall(int nargs, unsigned long *args);
 extern int audit_sockaddr(int len, void *addr);
-extern int __audit_fd_pair(int fd1, int fd2);
+extern void __audit_fd_pair(int fd1, int fd2);
 extern int audit_set_macxattr(const char *name);
 extern void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr);
 extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout);
@@ -464,11 +464,10 @@ static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp)
 	if (unlikely(!audit_dummy_context()))
 		__audit_ipc_obj(ipcp);
 }
-static inline int audit_fd_pair(int fd1, int fd2)
+static inline void audit_fd_pair(int fd1, int fd2)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_fd_pair(fd1, fd2);
-	return 0;
+		__audit_fd_pair(fd1, fd2);
 }
 static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
 {
@@ -537,7 +536,7 @@ extern int audit_signals;
 #define audit_ipc_set_perm(q,u,g,m) ((void)0)
 #define audit_bprm(p) ({ 0; })
 #define audit_socketcall(n,a) ((void)0)
-#define audit_fd_pair(n,a) ({ 0; })
+#define audit_fd_pair(n,a) ((void)0)
 #define audit_sockaddr(len, addr) ({ 0; })
 #define audit_set_macxattr(n) do { ; } while (0)
 #define audit_mq_open(o,m,a) ((void)0)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 83e946f1cdde..327e65d50674 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -131,11 +131,6 @@ struct audit_aux_data_execve {
 	struct mm_struct *mm;
 };
 
-struct audit_aux_data_fd_pair {
-	struct	audit_aux_data d;
-	int	fd[2];
-};
-
 struct audit_aux_data_pids {
 	struct audit_aux_data	d;
 	pid_t			target_pid[AUDIT_AUX_PIDS];
@@ -241,6 +236,7 @@ struct audit_context {
 			struct mq_attr		attr;
 		} mq_open;
 	};
+	int fds[2];
 
 #if AUDIT_DEBUG
 	int		    put_count;
@@ -1382,11 +1378,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			audit_log_execve_info(context, &ab, axi);
 			break; }
 
-		case AUDIT_FD_PAIR: {
-			struct audit_aux_data_fd_pair *axs = (void *)aux;
-			audit_log_format(ab, "fd0=%d fd1=%d", axs->fd[0], axs->fd[1]);
-			break; }
-
 		case AUDIT_BPRM_FCAPS: {
 			struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
 			audit_log_format(ab, "fver=%x", axs->fcap_ver);
@@ -1416,6 +1407,15 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 	if (context->type)
 		show_special(context, &call_panic);
 
+	if (context->fds[0] >= 0) {
+		ab = audit_log_start(context, GFP_KERNEL, AUDIT_FD_PAIR);
+		if (ab) {
+			audit_log_format(ab, "fd0=%d fd1=%d",
+					context->fds[0], context->fds[1]);
+			audit_log_end(ab);
+		}
+	}
+
 	if (context->sockaddr_len) {
 		ab = audit_log_start(context, GFP_KERNEL, AUDIT_SOCKADDR);
 		if (ab) {
@@ -1696,6 +1696,7 @@ void audit_syscall_exit(int valid, long return_code)
 		context->target_sid = 0;
 		context->sockaddr_len = 0;
 		context->type = 0;
+		context->fds[0] = -1;
 		kfree(context->filterkey);
 		context->filterkey = NULL;
 		tsk->audit_context = context;
@@ -2291,29 +2292,12 @@ void audit_socketcall(int nargs, unsigned long *args)
  * @fd1: the first file descriptor
  * @fd2: the second file descriptor
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_fd_pair(int fd1, int fd2)
+void __audit_fd_pair(int fd1, int fd2)
 {
 	struct audit_context *context = current->audit_context;
-	struct audit_aux_data_fd_pair *ax;
-
-	if (likely(!context)) {
-		return 0;
-	}
-
-	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
-	if (!ax) {
-		return -ENOMEM;
-	}
-
-	ax->fd[0] = fd1;
-	ax->fd[1] = fd2;
-
-	ax->d.type = AUDIT_FD_PAIR;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->fds[0] = fd1;
+	context->fds[1] = fd2;
 }
 
 /**
diff --git a/net/socket.c b/net/socket.c
index b41a92093e40..06603d73c411 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1313,13 +1313,7 @@ asmlinkage long sys_socketpair(int family, int type, int protocol,
 		goto out_fd1;
 	}
 
-	err = audit_fd_pair(fd1, fd2);
-	if (err < 0) {
-		fput(newfile1);
-		fput(newfile2);
-		goto out_fd;
-	}
-
+	audit_fd_pair(fd1, fd2);
 	fd_install(fd1, newfile1);
 	fd_install(fd2, newfile2);
 	/* fd1 and fd2 may be already another descriptors.
@@ -1349,7 +1343,6 @@ out_fd2:
 out_fd1:
 	put_filp(newfile2);
 	sock_release(sock2);
-out_fd:
 	put_unused_fd(fd1);
 	put_unused_fd(fd2);
 	goto out;
-- 
cgit v1.2.3-70-g09d2


From 57f71a0af4244d9ba3c0bce74b1d2e66e8d520bd Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 4 Jan 2009 14:52:57 -0500
Subject: sanitize audit_log_capset()

* no allocations
* return void
* don't duplicate checked for dummy context

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  9 ++++-----
 kernel/auditsc.c      | 44 ++++++++++++++++----------------------------
 kernel/capability.c   |  4 +---
 3 files changed, 21 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index bd59cd1e3219..7ddcb6a29eb1 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -457,7 +457,7 @@ extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat);
 extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
 				  const struct cred *new,
 				  const struct cred *old);
-extern int __audit_log_capset(pid_t pid, const struct cred *new, const struct cred *old);
+extern void __audit_log_capset(pid_t pid, const struct cred *new, const struct cred *old);
 
 static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp)
 {
@@ -504,12 +504,11 @@ static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm,
 	return 0;
 }
 
-static inline int audit_log_capset(pid_t pid, const struct cred *new,
+static inline void audit_log_capset(pid_t pid, const struct cred *new,
 				   const struct cred *old)
 {
 	if (unlikely(!audit_dummy_context()))
-		return __audit_log_capset(pid, new, old);
-	return 0;
+		__audit_log_capset(pid, new, old);
 }
 
 extern int audit_n_rules;
@@ -544,7 +543,7 @@ extern int audit_signals;
 #define audit_mq_notify(d,n) ((void)0)
 #define audit_mq_getsetattr(d,s) ((void)0)
 #define audit_log_bprm_fcaps(b, ncr, ocr) ({ 0; })
-#define audit_log_capset(pid, ncr, ocr) ({ 0; })
+#define audit_log_capset(pid, ncr, ocr) ((void)0)
 #define audit_ptrace(t) ((void)0)
 #define audit_n_rules 0
 #define audit_signals 0
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 327e65d50674..c76a58215f54 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -235,6 +235,10 @@ struct audit_context {
 			mode_t			mode;
 			struct mq_attr		attr;
 		} mq_open;
+		struct {
+			pid_t			pid;
+			struct audit_cap_data	cap;
+		} capset;
 	};
 	int fds[2];
 
@@ -1291,6 +1295,12 @@ static void show_special(struct audit_context *context, int *call_panic)
 			attr->mq_flags, attr->mq_maxmsg,
 			attr->mq_msgsize, attr->mq_curmsgs);
 		break; }
+	case AUDIT_CAPSET: {
+		audit_log_format(ab, "pid=%d", context->capset.pid);
+		audit_log_cap(ab, "cap_pi", &context->capset.cap.inheritable);
+		audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted);
+		audit_log_cap(ab, "cap_pe", &context->capset.cap.effective);
+		break; }
 	}
 	audit_log_end(ab);
 }
@@ -1392,14 +1402,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			audit_log_cap(ab, "new_pe", &axs->new_pcap.effective);
 			break; }
 
-		case AUDIT_CAPSET: {
-			struct audit_aux_data_capset *axs = (void *)aux;
-			audit_log_format(ab, "pid=%d", axs->pid);
-			audit_log_cap(ab, "cap_pi", &axs->cap.inheritable);
-			audit_log_cap(ab, "cap_pp", &axs->cap.permitted);
-			audit_log_cap(ab, "cap_pe", &axs->cap.effective);
-			break; }
-
 		}
 		audit_log_end(ab);
 	}
@@ -2456,29 +2458,15 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
  * Record the aguments userspace sent to sys_capset for later printing by the
  * audit system if applicable
  */
-int __audit_log_capset(pid_t pid,
+void __audit_log_capset(pid_t pid,
 		       const struct cred *new, const struct cred *old)
 {
-	struct audit_aux_data_capset *ax;
 	struct audit_context *context = current->audit_context;
-
-	if (likely(!audit_enabled || !context || context->dummy))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->d.type = AUDIT_CAPSET;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-
-	ax->pid = pid;
-	ax->cap.effective   = new->cap_effective;
-	ax->cap.inheritable = new->cap_effective;
-	ax->cap.permitted   = new->cap_permitted;
-
-	return 0;
+	context->capset.pid = pid;
+	context->capset.cap.effective   = new->cap_effective;
+	context->capset.cap.inheritable = new->cap_effective;
+	context->capset.cap.permitted   = new->cap_permitted;
+	context->type = AUDIT_CAPSET;
 }
 
 /**
diff --git a/kernel/capability.c b/kernel/capability.c
index 36b4b4daebec..c598d9d5be4f 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -280,9 +280,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
 	if (ret < 0)
 		goto error;
 
-	ret = audit_log_capset(pid, new, current_cred());
-	if (ret < 0)
-		return ret;
+	audit_log_capset(pid, new, current_cred());
 
 	return commit_creds(new);
 
-- 
cgit v1.2.3-70-g09d2


From 0590b9335a1c72a3f0defcc6231287f7817e07c8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 14 Dec 2008 23:45:27 -0500
Subject: fixing audit rule ordering mess, part 1

Problem: ordering between the rules on exit chain is currently lost;
all watch and inode rules are listed after everything else _and_
exit,never on one kind doesn't stop exit,always on another from
being matched.

Solution: assign priorities to rules, keep track of the current
highest-priority matching rule and its result (always/never).

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  1 +
 kernel/audit.h        |  5 +---
 kernel/auditfilter.c  | 17 +++++++++--
 kernel/auditsc.c      | 79 ++++++++++++++++++++++++++++-----------------------
 4 files changed, 59 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 7ddcb6a29eb1..5b47eeb00d53 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -373,6 +373,7 @@ struct audit_krule {
 	struct audit_watch	*watch;	/* associated watch */
 	struct audit_tree	*tree;	/* associated watched tree */
 	struct list_head	rlist;	/* entry in audit_{watch,tree}.rules list */
+	u64			prio;
 };
 
 struct audit_field {
diff --git a/kernel/audit.h b/kernel/audit.h
index 9d6717412fec..16f18cac661b 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -159,11 +159,8 @@ static inline int audit_signal_info(int sig, struct task_struct *t)
 		return __audit_signal_info(sig, t);
 	return 0;
 }
-extern enum audit_state audit_filter_inodes(struct task_struct *,
-					    struct audit_context *);
-extern void audit_set_auditable(struct audit_context *);
+extern void audit_filter_inodes(struct task_struct *, struct audit_context *);
 #else
 #define audit_signal_info(s,t) AUDIT_DISABLED
 #define audit_filter_inodes(t,c) AUDIT_DISABLED
-#define audit_set_auditable(c)
 #endif
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 0febaa0f784c..995a2e86808d 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -919,6 +919,7 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old,
 	new->action = old->action;
 	for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
 		new->mask[i] = old->mask[i];
+	new->prio = old->prio;
 	new->buflen = old->buflen;
 	new->inode_f = old->inode_f;
 	new->watch = NULL;
@@ -987,9 +988,8 @@ static void audit_update_watch(struct audit_parent *parent,
 
 		/* If the update involves invalidating rules, do the inode-based
 		 * filtering now, so we don't omit records. */
-		if (invalidating && current->audit_context &&
-		    audit_filter_inodes(current, current->audit_context) == AUDIT_RECORD_CONTEXT)
-			audit_set_auditable(current->audit_context);
+		if (invalidating && current->audit_context)
+			audit_filter_inodes(current, current->audit_context);
 
 		nwatch = audit_dupe_watch(owatch);
 		if (IS_ERR(nwatch)) {
@@ -1258,6 +1258,9 @@ static int audit_add_watch(struct audit_krule *krule, struct nameidata *ndp,
 	return ret;
 }
 
+static u64 prio_low = ~0ULL/2;
+static u64 prio_high = ~0ULL/2 - 1;
+
 /* Add rule to given filterlist if not a duplicate. */
 static inline int audit_add_rule(struct audit_entry *entry,
 				 struct list_head *list)
@@ -1319,6 +1322,14 @@ static inline int audit_add_rule(struct audit_entry *entry,
 		}
 	}
 
+	entry->rule.prio = ~0ULL;
+	if (entry->rule.listnr == AUDIT_FILTER_EXIT) {
+		if (entry->rule.flags & AUDIT_FILTER_PREPEND)
+			entry->rule.prio = ++prio_high;
+		else
+			entry->rule.prio = --prio_low;
+	}
+
 	if (entry->rule.flags & AUDIT_FILTER_PREPEND) {
 		list_add_rcu(&entry->list, list);
 		entry->rule.flags &= ~AUDIT_FILTER_PREPEND;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index c76a58215f54..19d2c2747c8d 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -165,14 +165,14 @@ struct audit_tree_refs {
 struct audit_context {
 	int		    dummy;	/* must be the first element */
 	int		    in_syscall;	/* 1 if task is in a syscall */
-	enum audit_state    state;
+	enum audit_state    state, current_state;
 	unsigned int	    serial;     /* serial number for record */
 	struct timespec	    ctime;      /* time of syscall entry */
 	int		    major;      /* syscall number */
 	unsigned long	    argv[4];    /* syscall arguments */
 	int		    return_valid; /* return code is valid */
 	long		    return_code;/* syscall return code */
-	int		    auditable;  /* 1 if record should be written */
+	u64		    prio;
 	int		    name_count;
 	struct audit_names  names[AUDIT_NAMES];
 	char *		    filterkey;	/* key for rule that triggered record */
@@ -630,8 +630,16 @@ static int audit_filter_rules(struct task_struct *tsk,
 			return 0;
 		}
 	}
-	if (rule->filterkey && ctx)
-		ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
+
+	if (ctx) {
+		if (rule->prio <= ctx->prio)
+			return 0;
+		if (rule->filterkey) {
+			kfree(ctx->filterkey);
+			ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
+		}
+		ctx->prio = rule->prio;
+	}
 	switch (rule->action) {
 	case AUDIT_NEVER:    *state = AUDIT_DISABLED;	    break;
 	case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
@@ -685,6 +693,7 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
 					       &state)) {
 				rcu_read_unlock();
+				ctx->current_state = state;
 				return state;
 			}
 		}
@@ -698,15 +707,14 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
  * buckets applicable to the inode numbers in audit_names[].
  * Regarding audit_state, same rules apply as for audit_filter_syscall().
  */
-enum audit_state audit_filter_inodes(struct task_struct *tsk,
-				     struct audit_context *ctx)
+void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
 {
 	int i;
 	struct audit_entry *e;
 	enum audit_state state;
 
 	if (audit_pid && tsk->tgid == audit_pid)
-		return AUDIT_DISABLED;
+		return;
 
 	rcu_read_lock();
 	for (i = 0; i < ctx->name_count; i++) {
@@ -723,17 +731,20 @@ enum audit_state audit_filter_inodes(struct task_struct *tsk,
 			if ((e->rule.mask[word] & bit) == bit &&
 			    audit_filter_rules(tsk, &e->rule, ctx, n, &state)) {
 				rcu_read_unlock();
-				return state;
+				ctx->current_state = state;
+				return;
 			}
 		}
 	}
 	rcu_read_unlock();
-	return AUDIT_BUILD_CONTEXT;
 }
 
-void audit_set_auditable(struct audit_context *ctx)
+static void audit_set_auditable(struct audit_context *ctx)
 {
-	ctx->auditable = 1;
+	if (!ctx->prio) {
+		ctx->prio = 1;
+		ctx->current_state = AUDIT_RECORD_CONTEXT;
+	}
 }
 
 static inline struct audit_context *audit_get_context(struct task_struct *tsk,
@@ -764,23 +775,11 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk,
 	else
 		context->return_code  = return_code;
 
-	if (context->in_syscall && !context->dummy && !context->auditable) {
-		enum audit_state state;
-
-		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
-		if (state == AUDIT_RECORD_CONTEXT) {
-			context->auditable = 1;
-			goto get_context;
-		}
-
-		state = audit_filter_inodes(tsk, context);
-		if (state == AUDIT_RECORD_CONTEXT)
-			context->auditable = 1;
-
+	if (context->in_syscall && !context->dummy) {
+		audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
+		audit_filter_inodes(tsk, context);
 	}
 
-get_context:
-
 	tsk->audit_context = NULL;
 	return context;
 }
@@ -790,8 +789,7 @@ static inline void audit_free_names(struct audit_context *context)
 	int i;
 
 #if AUDIT_DEBUG == 2
-	if (context->auditable
-	    ||context->put_count + context->ino_count != context->name_count) {
+	if (context->put_count + context->ino_count != context->name_count) {
 		printk(KERN_ERR "%s:%d(:%d): major=%d in_syscall=%d"
 		       " name_count=%d put_count=%d"
 		       " ino_count=%d [NOT freeing]\n",
@@ -842,6 +840,7 @@ static inline void audit_zero_context(struct audit_context *context,
 {
 	memset(context, 0, sizeof(*context));
 	context->state      = state;
+	context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
 }
 
 static inline struct audit_context *audit_alloc_context(enum audit_state state)
@@ -1543,7 +1542,7 @@ void audit_free(struct task_struct *tsk)
 	 * We use GFP_ATOMIC here because we might be doing this
 	 * in the context of the idle thread */
 	/* that can happen only if we are called from do_exit() */
-	if (context->in_syscall && context->auditable)
+	if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
 		audit_log_exit(context, tsk);
 
 	audit_free_context(context);
@@ -1627,15 +1626,17 @@ void audit_syscall_entry(int arch, int major,
 
 	state = context->state;
 	context->dummy = !audit_n_rules;
-	if (!context->dummy && (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT))
+	if (!context->dummy && state == AUDIT_BUILD_CONTEXT) {
+		context->prio = 0;
 		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);
+	}
 	if (likely(state == AUDIT_DISABLED))
 		return;
 
 	context->serial     = 0;
 	context->ctime      = CURRENT_TIME;
 	context->in_syscall = 1;
-	context->auditable  = !!(state == AUDIT_RECORD_CONTEXT);
+	context->current_state  = state;
 	context->ppid       = 0;
 }
 
@@ -1643,17 +1644,20 @@ void audit_finish_fork(struct task_struct *child)
 {
 	struct audit_context *ctx = current->audit_context;
 	struct audit_context *p = child->audit_context;
-	if (!p || !ctx || !ctx->auditable)
+	if (!p || !ctx)
+		return;
+	if (!ctx->in_syscall || ctx->current_state != AUDIT_RECORD_CONTEXT)
 		return;
 	p->arch = ctx->arch;
 	p->major = ctx->major;
 	memcpy(p->argv, ctx->argv, sizeof(ctx->argv));
 	p->ctime = ctx->ctime;
 	p->dummy = ctx->dummy;
-	p->auditable = ctx->auditable;
 	p->in_syscall = ctx->in_syscall;
 	p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL);
 	p->ppid = current->pid;
+	p->prio = ctx->prio;
+	p->current_state = ctx->current_state;
 }
 
 /**
@@ -1677,11 +1681,11 @@ void audit_syscall_exit(int valid, long return_code)
 	if (likely(!context))
 		return;
 
-	if (context->in_syscall && context->auditable)
+	if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
 		audit_log_exit(context, tsk);
 
 	context->in_syscall = 0;
-	context->auditable  = 0;
+	context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
 
 	if (context->previous) {
 		struct audit_context *new_context = context->previous;
@@ -2091,7 +2095,10 @@ int auditsc_get_stamp(struct audit_context *ctx,
 	t->tv_sec  = ctx->ctime.tv_sec;
 	t->tv_nsec = ctx->ctime.tv_nsec;
 	*serial    = ctx->serial;
-	ctx->auditable = 1;
+	if (!ctx->prio) {
+		ctx->prio = 1;
+		ctx->current_state = AUDIT_RECORD_CONTEXT;
+	}
 	return 1;
 }
 
-- 
cgit v1.2.3-70-g09d2


From e45aa212ea81d39b38ba158df344dc3a500153e5 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 15 Dec 2008 01:17:50 -0500
Subject: audit rules ordering, part 2

Fix the actual rule listing; add per-type lists _not_ used for matching,
with all exit,... sitting on one such list.  Simplifies "do something
for all rules" logics, while we are at it...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h |  1 +
 kernel/audit_tree.c   |  1 +
 kernel/auditfilter.c  | 95 +++++++++++++++++++++------------------------------
 3 files changed, 41 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 5b47eeb00d53..cc71fdb56ae2 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -373,6 +373,7 @@ struct audit_krule {
 	struct audit_watch	*watch;	/* associated watch */
 	struct audit_tree	*tree;	/* associated watched tree */
 	struct list_head	rlist;	/* entry in audit_{watch,tree}.rules list */
+	struct list_head	list;	/* for AUDIT_LIST* purposes only */
 	u64			prio;
 };
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 8b509441f49a..48bddad2a3dc 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -450,6 +450,7 @@ static void kill_rules(struct audit_tree *tree)
 			audit_log_end(ab);
 			rule->tree = NULL;
 			list_del_rcu(&entry->list);
+			list_del(&entry->rule.list);
 			call_rcu(&entry->rcu, audit_free_rule_rcu);
 		}
 	}
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 995a2e86808d..5d4edc6f7a32 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -86,6 +86,14 @@ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = {
 #error Fix audit_filter_list initialiser
 #endif
 };
+static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = {
+	LIST_HEAD_INIT(audit_rules_list[0]),
+	LIST_HEAD_INIT(audit_rules_list[1]),
+	LIST_HEAD_INIT(audit_rules_list[2]),
+	LIST_HEAD_INIT(audit_rules_list[3]),
+	LIST_HEAD_INIT(audit_rules_list[4]),
+	LIST_HEAD_INIT(audit_rules_list[5]),
+};
 
 DEFINE_MUTEX(audit_filter_mutex);
 
@@ -1007,12 +1015,15 @@ static void audit_update_watch(struct audit_parent *parent,
 			list_del_rcu(&oentry->list);
 
 			nentry = audit_dupe_rule(&oentry->rule, nwatch);
-			if (IS_ERR(nentry))
+			if (IS_ERR(nentry)) {
+				list_del(&oentry->rule.list);
 				audit_panic("error updating watch, removing");
-			else {
+			} else {
 				int h = audit_hash_ino((u32)ino);
 				list_add(&nentry->rule.rlist, &nwatch->rules);
 				list_add_rcu(&nentry->list, &audit_inode_hash[h]);
+				list_replace(&oentry->rule.list,
+					     &nentry->rule.list);
 			}
 
 			call_rcu(&oentry->rcu, audit_free_rule_rcu);
@@ -1077,6 +1088,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 				audit_log_end(ab);
 			}
 			list_del(&r->rlist);
+			list_del(&r->list);
 			list_del_rcu(&e->list);
 			call_rcu(&e->rcu, audit_free_rule_rcu);
 		}
@@ -1331,9 +1343,13 @@ static inline int audit_add_rule(struct audit_entry *entry,
 	}
 
 	if (entry->rule.flags & AUDIT_FILTER_PREPEND) {
+		list_add(&entry->rule.list,
+			 &audit_rules_list[entry->rule.listnr]);
 		list_add_rcu(&entry->list, list);
 		entry->rule.flags &= ~AUDIT_FILTER_PREPEND;
 	} else {
+		list_add_tail(&entry->rule.list,
+			      &audit_rules_list[entry->rule.listnr]);
 		list_add_tail_rcu(&entry->list, list);
 	}
 #ifdef CONFIG_AUDITSYSCALL
@@ -1415,6 +1431,7 @@ static inline int audit_del_rule(struct audit_entry *entry,
 		audit_remove_tree_rule(&e->rule);
 
 	list_del_rcu(&e->list);
+	list_del(&e->rule.list);
 	call_rcu(&e->rcu, audit_free_rule_rcu);
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -1443,30 +1460,16 @@ out:
 static void audit_list(int pid, int seq, struct sk_buff_head *q)
 {
 	struct sk_buff *skb;
-	struct audit_entry *entry;
+	struct audit_krule *r;
 	int i;
 
 	/* This is a blocking read, so use audit_filter_mutex instead of rcu
 	 * iterator to sync with list writers. */
 	for (i=0; i<AUDIT_NR_FILTERS; i++) {
-		list_for_each_entry(entry, &audit_filter_list[i], list) {
-			struct audit_rule *rule;
-
-			rule = audit_krule_to_rule(&entry->rule);
-			if (unlikely(!rule))
-				break;
-			skb = audit_make_reply(pid, seq, AUDIT_LIST, 0, 1,
-					 rule, sizeof(*rule));
-			if (skb)
-				skb_queue_tail(q, skb);
-			kfree(rule);
-		}
-	}
-	for (i = 0; i < AUDIT_INODE_BUCKETS; i++) {
-		list_for_each_entry(entry, &audit_inode_hash[i], list) {
+		list_for_each_entry(r, &audit_rules_list[i], list) {
 			struct audit_rule *rule;
 
-			rule = audit_krule_to_rule(&entry->rule);
+			rule = audit_krule_to_rule(r);
 			if (unlikely(!rule))
 				break;
 			skb = audit_make_reply(pid, seq, AUDIT_LIST, 0, 1,
@@ -1485,30 +1488,16 @@ static void audit_list(int pid, int seq, struct sk_buff_head *q)
 static void audit_list_rules(int pid, int seq, struct sk_buff_head *q)
 {
 	struct sk_buff *skb;
-	struct audit_entry *e;
+	struct audit_krule *r;
 	int i;
 
 	/* This is a blocking read, so use audit_filter_mutex instead of rcu
 	 * iterator to sync with list writers. */
 	for (i=0; i<AUDIT_NR_FILTERS; i++) {
-		list_for_each_entry(e, &audit_filter_list[i], list) {
-			struct audit_rule_data *data;
-
-			data = audit_krule_to_data(&e->rule);
-			if (unlikely(!data))
-				break;
-			skb = audit_make_reply(pid, seq, AUDIT_LIST_RULES, 0, 1,
-					 data, sizeof(*data) + data->buflen);
-			if (skb)
-				skb_queue_tail(q, skb);
-			kfree(data);
-		}
-	}
-	for (i=0; i< AUDIT_INODE_BUCKETS; i++) {
-		list_for_each_entry(e, &audit_inode_hash[i], list) {
+		list_for_each_entry(r, &audit_rules_list[i], list) {
 			struct audit_rule_data *data;
 
-			data = audit_krule_to_data(&e->rule);
+			data = audit_krule_to_data(r);
 			if (unlikely(!data))
 				break;
 			skb = audit_make_reply(pid, seq, AUDIT_LIST_RULES, 0, 1,
@@ -1789,35 +1778,37 @@ unlock_and_return:
 	return result;
 }
 
-static int update_lsm_rule(struct audit_entry *entry)
+static int update_lsm_rule(struct audit_krule *r)
 {
+	struct audit_entry *entry = container_of(r, struct audit_entry, rule);
 	struct audit_entry *nentry;
 	struct audit_watch *watch;
 	struct audit_tree *tree;
 	int err = 0;
 
-	if (!security_audit_rule_known(&entry->rule))
+	if (!security_audit_rule_known(r))
 		return 0;
 
-	watch = entry->rule.watch;
-	tree = entry->rule.tree;
-	nentry = audit_dupe_rule(&entry->rule, watch);
+	watch = r->watch;
+	tree = r->tree;
+	nentry = audit_dupe_rule(r, watch);
 	if (IS_ERR(nentry)) {
 		/* save the first error encountered for the
 		 * return value */
 		err = PTR_ERR(nentry);
 		audit_panic("error updating LSM filters");
 		if (watch)
-			list_del(&entry->rule.rlist);
+			list_del(&r->rlist);
 		list_del_rcu(&entry->list);
+		list_del(&r->list);
 	} else {
 		if (watch) {
 			list_add(&nentry->rule.rlist, &watch->rules);
-			list_del(&entry->rule.rlist);
+			list_del(&r->rlist);
 		} else if (tree)
-			list_replace_init(&entry->rule.rlist,
-				     &nentry->rule.rlist);
+			list_replace_init(&r->rlist, &nentry->rule.rlist);
 		list_replace_rcu(&entry->list, &nentry->list);
+		list_replace(&r->list, &nentry->rule.list);
 	}
 	call_rcu(&entry->rcu, audit_free_rule_rcu);
 
@@ -1831,27 +1822,19 @@ static int update_lsm_rule(struct audit_entry *entry)
  * updated rule. */
 int audit_update_lsm_rules(void)
 {
-	struct audit_entry *e, *n;
+	struct audit_krule *r, *n;
 	int i, err = 0;
 
 	/* audit_filter_mutex synchronizes the writers */
 	mutex_lock(&audit_filter_mutex);
 
 	for (i = 0; i < AUDIT_NR_FILTERS; i++) {
-		list_for_each_entry_safe(e, n, &audit_filter_list[i], list) {
-			int res = update_lsm_rule(e);
-			if (!err)
-				err = res;
-		}
-	}
-	for (i=0; i< AUDIT_INODE_BUCKETS; i++) {
-		list_for_each_entry_safe(e, n, &audit_inode_hash[i], list) {
-			int res = update_lsm_rule(e);
+		list_for_each_entry_safe(r, n, &audit_rules_list[i], list) {
+			int res = update_lsm_rule(r);
 			if (!err)
 				err = res;
 		}
 	}
-
 	mutex_unlock(&audit_filter_mutex);
 
 	return err;
-- 
cgit v1.2.3-70-g09d2


From 5af75d8d58d0f9f7b7c0515b35786b22892d5f12 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 16 Dec 2008 05:59:26 -0500
Subject: audit: validate comparison operations, store them in sane form

Don't store the field->op in the messy (and very inconvenient for e.g.
audit_comparator()) form; translate to dense set of values and do full
validation of userland-submitted value while we are at it.

->audit_init_rule() and ->audit_match_rule() get new values now; in-tree
instances updated.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/audit.h          |  12 ++++
 kernel/audit_tree.c            |   2 +-
 kernel/auditfilter.c           | 132 ++++++++++++++++++++---------------------
 security/selinux/ss/services.c |  26 ++++----
 security/smack/smack_lsm.c     |   6 +-
 5 files changed, 94 insertions(+), 84 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index cc71fdb56ae2..67e5dbfc2961 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -247,6 +247,18 @@
 #define AUDIT_GREATER_THAN_OR_EQUAL	(AUDIT_GREATER_THAN|AUDIT_EQUAL)
 #define AUDIT_OPERATORS			(AUDIT_EQUAL|AUDIT_NOT_EQUAL|AUDIT_BIT_MASK)
 
+enum {
+	Audit_equal,
+	Audit_not_equal,
+	Audit_bitmask,
+	Audit_bittest,
+	Audit_lt,
+	Audit_gt,
+	Audit_le,
+	Audit_ge,
+	Audit_bad
+};
+
 /* Status symbols */
 				/* Mask values */
 #define AUDIT_STATUS_ENABLED		0x0001
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 48bddad2a3dc..8ad9545b8db9 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -618,7 +618,7 @@ int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
 
 	if (pathname[0] != '/' ||
 	    rule->listnr != AUDIT_FILTER_EXIT ||
-	    op & ~AUDIT_EQUAL ||
+	    op != Audit_equal ||
 	    rule->inode_f || rule->watch || rule->tree)
 		return -EINVAL;
 	rule->tree = alloc_tree(pathname);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index e6e3829cadd1..fbf24d121d97 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -252,7 +252,8 @@ static inline int audit_to_inode(struct audit_krule *krule,
 				 struct audit_field *f)
 {
 	if (krule->listnr != AUDIT_FILTER_EXIT ||
-	    krule->watch || krule->inode_f || krule->tree)
+	    krule->watch || krule->inode_f || krule->tree ||
+	    (f->op != Audit_equal && f->op != Audit_not_equal))
 		return -EINVAL;
 
 	krule->inode_f = f;
@@ -270,7 +271,7 @@ static int audit_to_watch(struct audit_krule *krule, char *path, int len,
 
 	if (path[0] != '/' || path[len-1] == '/' ||
 	    krule->listnr != AUDIT_FILTER_EXIT ||
-	    op & ~AUDIT_EQUAL ||
+	    op != Audit_equal ||
 	    krule->inode_f || krule->watch || krule->tree)
 		return -EINVAL;
 
@@ -420,12 +421,32 @@ exit_err:
 	return ERR_PTR(err);
 }
 
+static u32 audit_ops[] =
+{
+	[Audit_equal] = AUDIT_EQUAL,
+	[Audit_not_equal] = AUDIT_NOT_EQUAL,
+	[Audit_bitmask] = AUDIT_BIT_MASK,
+	[Audit_bittest] = AUDIT_BIT_TEST,
+	[Audit_lt] = AUDIT_LESS_THAN,
+	[Audit_gt] = AUDIT_GREATER_THAN,
+	[Audit_le] = AUDIT_LESS_THAN_OR_EQUAL,
+	[Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL,
+};
+
+static u32 audit_to_op(u32 op)
+{
+	u32 n;
+	for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++)
+		;
+	return n;
+}
+
+
 /* Translate struct audit_rule to kernel's rule respresentation.
  * Exists for backward compatibility with userspace. */
 static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 {
 	struct audit_entry *entry;
-	struct audit_field *ino_f;
 	int err = 0;
 	int i;
 
@@ -435,12 +456,28 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 
 	for (i = 0; i < rule->field_count; i++) {
 		struct audit_field *f = &entry->rule.fields[i];
+		u32 n;
+
+		n = rule->fields[i] & (AUDIT_NEGATE|AUDIT_OPERATORS);
+
+		/* Support for legacy operators where
+		 * AUDIT_NEGATE bit signifies != and otherwise assumes == */
+		if (n & AUDIT_NEGATE)
+			f->op = Audit_not_equal;
+		else if (!n)
+			f->op = Audit_equal;
+		else
+			f->op = audit_to_op(n);
+
+		entry->rule.vers_ops = (n & AUDIT_OPERATORS) ? 2 : 1;
 
-		f->op = rule->fields[i] & (AUDIT_NEGATE|AUDIT_OPERATORS);
 		f->type = rule->fields[i] & ~(AUDIT_NEGATE|AUDIT_OPERATORS);
 		f->val = rule->values[i];
 
 		err = -EINVAL;
+		if (f->op == Audit_bad)
+			goto exit_free;
+
 		switch(f->type) {
 		default:
 			goto exit_free;
@@ -462,11 +499,8 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 		case AUDIT_EXIT:
 		case AUDIT_SUCCESS:
 			/* bit ops are only useful on syscall args */
-			if (f->op == AUDIT_BIT_MASK ||
-						f->op == AUDIT_BIT_TEST) {
-				err = -EINVAL;
+			if (f->op == Audit_bitmask || f->op == Audit_bittest)
 				goto exit_free;
-			}
 			break;
 		case AUDIT_ARG0:
 		case AUDIT_ARG1:
@@ -475,11 +509,8 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 			break;
 		/* arch is only allowed to be = or != */
 		case AUDIT_ARCH:
-			if ((f->op != AUDIT_NOT_EQUAL) && (f->op != AUDIT_EQUAL)
-					&& (f->op != AUDIT_NEGATE) && (f->op)) {
-				err = -EINVAL;
+			if (f->op != Audit_not_equal && f->op != Audit_equal)
 				goto exit_free;
-			}
 			entry->rule.arch_f = f;
 			break;
 		case AUDIT_PERM:
@@ -496,33 +527,10 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 				goto exit_free;
 			break;
 		}
-
-		entry->rule.vers_ops = (f->op & AUDIT_OPERATORS) ? 2 : 1;
-
-		/* Support for legacy operators where
-		 * AUDIT_NEGATE bit signifies != and otherwise assumes == */
-		if (f->op & AUDIT_NEGATE)
-			f->op = AUDIT_NOT_EQUAL;
-		else if (!f->op)
-			f->op = AUDIT_EQUAL;
-		else if (f->op == AUDIT_OPERATORS) {
-			err = -EINVAL;
-			goto exit_free;
-		}
 	}
 
-	ino_f = entry->rule.inode_f;
-	if (ino_f) {
-		switch(ino_f->op) {
-		case AUDIT_NOT_EQUAL:
-			entry->rule.inode_f = NULL;
-		case AUDIT_EQUAL:
-			break;
-		default:
-			err = -EINVAL;
-			goto exit_free;
-		}
-	}
+	if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal)
+		entry->rule.inode_f = NULL;
 
 exit_nofree:
 	return entry;
@@ -538,7 +546,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 {
 	int err = 0;
 	struct audit_entry *entry;
-	struct audit_field *ino_f;
 	void *bufp;
 	size_t remain = datasz - sizeof(struct audit_rule_data);
 	int i;
@@ -554,11 +561,11 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		struct audit_field *f = &entry->rule.fields[i];
 
 		err = -EINVAL;
-		if (!(data->fieldflags[i] & AUDIT_OPERATORS) ||
-		    data->fieldflags[i] & ~AUDIT_OPERATORS)
+
+		f->op = audit_to_op(data->fieldflags[i]);
+		if (f->op == Audit_bad)
 			goto exit_free;
 
-		f->op = data->fieldflags[i] & AUDIT_OPERATORS;
 		f->type = data->fields[i];
 		f->val = data->values[i];
 		f->lsm_str = NULL;
@@ -670,18 +677,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		}
 	}
 
-	ino_f = entry->rule.inode_f;
-	if (ino_f) {
-		switch(ino_f->op) {
-		case AUDIT_NOT_EQUAL:
-			entry->rule.inode_f = NULL;
-		case AUDIT_EQUAL:
-			break;
-		default:
-			err = -EINVAL;
-			goto exit_free;
-		}
-	}
+	if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal)
+		entry->rule.inode_f = NULL;
 
 exit_nofree:
 	return entry;
@@ -721,10 +718,10 @@ static struct audit_rule *audit_krule_to_rule(struct audit_krule *krule)
 		rule->fields[i] = krule->fields[i].type;
 
 		if (krule->vers_ops == 1) {
-			if (krule->fields[i].op & AUDIT_NOT_EQUAL)
+			if (krule->fields[i].op == Audit_not_equal)
 				rule->fields[i] |= AUDIT_NEGATE;
 		} else {
-			rule->fields[i] |= krule->fields[i].op;
+			rule->fields[i] |= audit_ops[krule->fields[i].op];
 		}
 	}
 	for (i = 0; i < AUDIT_BITMASK_SIZE; i++) rule->mask[i] = krule->mask[i];
@@ -752,7 +749,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
 		struct audit_field *f = &krule->fields[i];
 
 		data->fields[i] = f->type;
-		data->fieldflags[i] = f->op;
+		data->fieldflags[i] = audit_ops[f->op];
 		switch(f->type) {
 		case AUDIT_SUBJ_USER:
 		case AUDIT_SUBJ_ROLE:
@@ -1626,28 +1623,29 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
 	return err;
 }
 
-int audit_comparator(const u32 left, const u32 op, const u32 right)
+int audit_comparator(u32 left, u32 op, u32 right)
 {
 	switch (op) {
-	case AUDIT_EQUAL:
+	case Audit_equal:
 		return (left == right);
-	case AUDIT_NOT_EQUAL:
+	case Audit_not_equal:
 		return (left != right);
-	case AUDIT_LESS_THAN:
+	case Audit_lt:
 		return (left < right);
-	case AUDIT_LESS_THAN_OR_EQUAL:
+	case Audit_le:
 		return (left <= right);
-	case AUDIT_GREATER_THAN:
+	case Audit_gt:
 		return (left > right);
-	case AUDIT_GREATER_THAN_OR_EQUAL:
+	case Audit_ge:
 		return (left >= right);
-	case AUDIT_BIT_MASK:
+	case Audit_bitmask:
 		return (left & right);
-	case AUDIT_BIT_TEST:
+	case Audit_bittest:
 		return ((left & right) == right);
+	default:
+		BUG();
+		return 0;
 	}
-	BUG();
-	return 0;
 }
 
 /* Compare given dentry name with last component in given path,
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 343c8ab14af0..c65e4fe4a0f1 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -2602,7 +2602,7 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
 	case AUDIT_OBJ_ROLE:
 	case AUDIT_OBJ_TYPE:
 		/* only 'equals' and 'not equals' fit user, role, and type */
-		if (op != AUDIT_EQUAL && op != AUDIT_NOT_EQUAL)
+		if (op != Audit_equal && op != Audit_not_equal)
 			return -EINVAL;
 		break;
 	case AUDIT_SUBJ_SEN:
@@ -2736,10 +2736,10 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule,
 	case AUDIT_SUBJ_USER:
 	case AUDIT_OBJ_USER:
 		switch (op) {
-		case AUDIT_EQUAL:
+		case Audit_equal:
 			match = (ctxt->user == rule->au_ctxt.user);
 			break;
-		case AUDIT_NOT_EQUAL:
+		case Audit_not_equal:
 			match = (ctxt->user != rule->au_ctxt.user);
 			break;
 		}
@@ -2747,10 +2747,10 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule,
 	case AUDIT_SUBJ_ROLE:
 	case AUDIT_OBJ_ROLE:
 		switch (op) {
-		case AUDIT_EQUAL:
+		case Audit_equal:
 			match = (ctxt->role == rule->au_ctxt.role);
 			break;
-		case AUDIT_NOT_EQUAL:
+		case Audit_not_equal:
 			match = (ctxt->role != rule->au_ctxt.role);
 			break;
 		}
@@ -2758,10 +2758,10 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule,
 	case AUDIT_SUBJ_TYPE:
 	case AUDIT_OBJ_TYPE:
 		switch (op) {
-		case AUDIT_EQUAL:
+		case Audit_equal:
 			match = (ctxt->type == rule->au_ctxt.type);
 			break;
-		case AUDIT_NOT_EQUAL:
+		case Audit_not_equal:
 			match = (ctxt->type != rule->au_ctxt.type);
 			break;
 		}
@@ -2774,31 +2774,31 @@ int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule,
 			  field == AUDIT_OBJ_LEV_LOW) ?
 			 &ctxt->range.level[0] : &ctxt->range.level[1]);
 		switch (op) {
-		case AUDIT_EQUAL:
+		case Audit_equal:
 			match = mls_level_eq(&rule->au_ctxt.range.level[0],
 					     level);
 			break;
-		case AUDIT_NOT_EQUAL:
+		case Audit_not_equal:
 			match = !mls_level_eq(&rule->au_ctxt.range.level[0],
 					      level);
 			break;
-		case AUDIT_LESS_THAN:
+		case Audit_lt:
 			match = (mls_level_dom(&rule->au_ctxt.range.level[0],
 					       level) &&
 				 !mls_level_eq(&rule->au_ctxt.range.level[0],
 					       level));
 			break;
-		case AUDIT_LESS_THAN_OR_EQUAL:
+		case Audit_le:
 			match = mls_level_dom(&rule->au_ctxt.range.level[0],
 					      level);
 			break;
-		case AUDIT_GREATER_THAN:
+		case Audit_gt:
 			match = (mls_level_dom(level,
 					      &rule->au_ctxt.range.level[0]) &&
 				 !mls_level_eq(level,
 					       &rule->au_ctxt.range.level[0]));
 			break;
-		case AUDIT_GREATER_THAN_OR_EQUAL:
+		case Audit_ge:
 			match = mls_level_dom(level,
 					      &rule->au_ctxt.range.level[0]);
 			break;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 1b5551dfc1f7..848212fd4845 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -2492,7 +2492,7 @@ static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule)
 	if (field != AUDIT_SUBJ_USER && field != AUDIT_OBJ_USER)
 		return -EINVAL;
 
-	if (op != AUDIT_EQUAL && op != AUDIT_NOT_EQUAL)
+	if (op != Audit_equal && op != Audit_not_equal)
 		return -EINVAL;
 
 	*rule = smk_import(rulestr, 0);
@@ -2556,9 +2556,9 @@ static int smack_audit_rule_match(u32 secid, u32 field, u32 op, void *vrule,
 	 * both pointers will point to the same smack_known
 	 * label.
 	 */
-	if (op == AUDIT_EQUAL)
+	if (op == Audit_equal)
 		return (rule == smack);
-	if (op == AUDIT_NOT_EQUAL)
+	if (op == Audit_not_equal)
 		return (rule != smack);
 
 	return 0;
-- 
cgit v1.2.3-70-g09d2


From 0a30c5cefa53cbac429dcb2de906c0637b646253 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <randy.dunlap@oracle.com>
Date: Sun, 4 Jan 2009 12:00:47 -0800
Subject: spi.h uses/needs device.h

Include header files as used/needed:

  In file included from drivers/leds/leds-dac124s085.c:16:
  include/linux/spi/spi.h:66: error: field 'dev' has incomplete type
  include/linux/spi/spi.h: In function 'to_spi_device':
  include/linux/spi/spi.h:100: warning: type defaults to 'int' in declaration of '__mptr'
  ...

Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/spi/spi.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 4be01bb44377..82229317753d 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -19,6 +19,8 @@
 #ifndef __LINUX_SPI_H
 #define __LINUX_SPI_H
 
+#include <linux/device.h>
+
 /*
  * INTERFACES between SPI master-side drivers and SPI infrastructure.
  * (There's no SPI slave support for Linux yet...)
-- 
cgit v1.2.3-70-g09d2


From c644f0e4b56f9a2fc066cd0d75a18074d130e4a3 Mon Sep 17 00:00:00 2001
From: Pekka Enberg <penberg@cs.helsinki.fi>
Date: Sun, 4 Jan 2009 12:00:48 -0800
Subject: fs: introduce bgl_lock_ptr()

As suggested by Andreas Dilger, introduce a bgl_lock_ptr() helper in
<linux/blockgroup_lock.h> and add separate sb_bgl_lock() helpers to
filesystem specific header files to break the hidden dependency to
struct ext[234]_sb_info.

Also, while at it, convert the macros to static inlines to try make up
for all the times I broke Andrew Morton's tree.

Acked-by: Andreas Dilger <adilger@sun.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ext4/ext4_sb.h               | 6 ++++++
 include/linux/blockgroup_lock.h | 7 +++++--
 include/linux/ext2_fs_sb.h      | 6 ++++++
 include/linux/ext3_fs_sb.h      | 6 ++++++
 4 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h
index 445fde603df8..b21f16713db0 100644
--- a/fs/ext4/ext4_sb.h
+++ b/fs/ext4/ext4_sb.h
@@ -146,4 +146,10 @@ struct ext4_sb_info {
 	struct flex_groups *s_flex_groups;
 };
 
+static inline spinlock_t *
+sb_bgl_lock(struct ext4_sb_info *sbi, unsigned int block_group)
+{
+	return bgl_lock_ptr(&sbi->s_blockgroup_lock, block_group);
+}
+
 #endif	/* _EXT4_SB */
diff --git a/include/linux/blockgroup_lock.h b/include/linux/blockgroup_lock.h
index 8607312983bd..e44b88ba552b 100644
--- a/include/linux/blockgroup_lock.h
+++ b/include/linux/blockgroup_lock.h
@@ -53,7 +53,10 @@ static inline void bgl_lock_init(struct blockgroup_lock *bgl)
  * The accessor is a macro so we can embed a blockgroup_lock into different
  * superblock types
  */
-#define sb_bgl_lock(sb, block_group) \
-	(&(sb)->s_blockgroup_lock.locks[(block_group) & (NR_BG_LOCKS-1)].lock)
+static inline spinlock_t *
+bgl_lock_ptr(struct blockgroup_lock *bgl, unsigned int block_group)
+{
+	return &bgl->locks[(block_group) & (NR_BG_LOCKS-1)].lock;
+}
 
 #endif
diff --git a/include/linux/ext2_fs_sb.h b/include/linux/ext2_fs_sb.h
index f273415ab6f1..dc541f3653d1 100644
--- a/include/linux/ext2_fs_sb.h
+++ b/include/linux/ext2_fs_sb.h
@@ -108,4 +108,10 @@ struct ext2_sb_info {
 	struct ext2_reserve_window_node s_rsv_window_head;
 };
 
+static inline spinlock_t *
+sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group)
+{
+	return bgl_lock_ptr(&sbi->s_blockgroup_lock, block_group);
+}
+
 #endif	/* _LINUX_EXT2_FS_SB */
diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h
index b65f0288b842..e024e38248ff 100644
--- a/include/linux/ext3_fs_sb.h
+++ b/include/linux/ext3_fs_sb.h
@@ -83,4 +83,10 @@ struct ext3_sb_info {
 #endif
 };
 
+static inline spinlock_t *
+sb_bgl_lock(struct ext3_sb_info *sbi, unsigned int block_group)
+{
+	return bgl_lock_ptr(&sbi->s_blockgroup_lock, block_group);
+}
+
 #endif	/* _LINUX_EXT3_FS_SB */
-- 
cgit v1.2.3-70-g09d2


From 54566b2c1594c2326a645a3551f9d989f7ba3c5e Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Sun, 4 Jan 2009 12:00:53 -0800
Subject: fs: symlink write_begin allocation context fix

With the write_begin/write_end aops, page_symlink was broken because it
could no longer pass a GFP_NOFS type mask into the point where the
allocations happened.  They are done in write_begin, which would always
assume that the filesystem can be entered from reclaim.  This bug could
cause filesystem deadlocks.

The funny thing with having a gfp_t mask there is that it doesn't really
allow the caller to arbitrarily tinker with the context in which it can be
called.  It couldn't ever be GFP_ATOMIC, for example, because it needs to
take the page lock.  The only thing any callers care about is __GFP_FS
anyway, so turn that into a single flag.

Add a new flag for write_begin, AOP_FLAG_NOFS.  Filesystems can now act on
this flag in their write_begin function.  Change __grab_cache_page to
accept a nofs argument as well, to honour that flag (while we're there,
change the name to grab_cache_page_write_begin which is more instructive
and does away with random leading underscores).

This is really a more flexible way to go in the end anyway -- if a
filesystem happens to want any extra allocations aside from the pagecache
ones in ints write_begin function, it may now use GFP_KERNEL (rather than
GFP_NOFS) for common case allocations (eg.  ocfs2_alloc_write_ctxt, for a
random example).

[kosaki.motohiro@jp.fujitsu.com: fix ubifs]
[kosaki.motohiro@jp.fujitsu.com: fix fuse]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: <stable@kernel.org>		[2.6.28.x]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ Cleaned up the calling convention: just pass in the AOP flags
  untouched to the grab_cache_page_write_begin() function.  That
  just simplifies everybody, and may even allow future expansion of the
  logic.   - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/affs/file.c          |  2 +-
 fs/afs/write.c          |  2 +-
 fs/buffer.c             |  4 ++--
 fs/cifs/file.c          |  2 +-
 fs/ecryptfs/mmap.c      |  2 +-
 fs/ext3/inode.c         |  2 +-
 fs/ext3/namei.c         |  3 +--
 fs/ext4/inode.c         |  4 ++--
 fs/ext4/namei.c         |  3 +--
 fs/fuse/file.c          |  4 ++--
 fs/gfs2/ops_address.c   |  2 +-
 fs/hostfs/hostfs_kern.c |  2 +-
 fs/jffs2/file.c         |  2 +-
 fs/libfs.c              |  2 +-
 fs/namei.c              | 13 +++++++++----
 fs/nfs/file.c           |  2 +-
 fs/reiserfs/inode.c     |  2 +-
 fs/smbfs/file.c         |  2 +-
 fs/ubifs/file.c         |  9 +++++----
 include/linux/fs.h      |  5 ++++-
 include/linux/pagemap.h |  3 ++-
 mm/filemap.c            | 13 +++++++++----
 22 files changed, 49 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/fs/affs/file.c b/fs/affs/file.c
index 1377b1240b6e..9246cb4aa018 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -628,7 +628,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 	}
 
 	index = pos >> PAGE_CACHE_SHIFT;
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index d6b85dab35fc..3fb36d433621 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -144,7 +144,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	candidate->state = AFS_WBACK_PENDING;
 	init_waitqueue_head(&candidate->waitq);
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page) {
 		kfree(candidate);
 		return -ENOMEM;
diff --git a/fs/buffer.c b/fs/buffer.c
index 776ae091d3b0..a13f09b696f7 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1996,7 +1996,7 @@ int block_write_begin(struct file *file, struct address_space *mapping,
 	page = *pagep;
 	if (page == NULL) {
 		ownpage = 1;
-		page = __grab_cache_page(mapping, index);
+		page = grab_cache_page_write_begin(mapping, index, flags);
 		if (!page) {
 			status = -ENOMEM;
 			goto out;
@@ -2502,7 +2502,7 @@ int nobh_write_begin(struct file *file, struct address_space *mapping,
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index b1e1fc6a6e6a..12bb656fbe75 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2074,7 +2074,7 @@ static int cifs_write_begin(struct file *file, struct address_space *mapping,
 
 	cFYI(1, ("write_begin from %lld len %d", (long long)pos, len));
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page) {
 		rc = -ENOMEM;
 		goto out;
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 04d7b3fa1ac6..46cec2b69796 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -288,7 +288,7 @@ static int ecryptfs_write_begin(struct file *file,
 	loff_t prev_page_end_size;
 	int rc = 0;
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index c4bdccf976b5..5fa453b49a64 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1161,7 +1161,7 @@ static int ext3_write_begin(struct file *file, struct address_space *mapping,
 	to = from + len;
 
 retry:
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 297ea8dfac7c..1dd2abe6313e 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -2175,8 +2175,7 @@ retry:
 		 * We have a transaction open.  All is sweetness.  It also sets
 		 * i_size in generic_commit_write().
 		 */
-		err = __page_symlink(inode, symname, l,
-				mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
+		err = __page_symlink(inode, symname, l, 1);
 		if (err) {
 			drop_nlink(inode);
 			unlock_new_inode(inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7c3325e0b005..6702a49992a6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1346,7 +1346,7 @@ retry:
 		goto out;
 	}
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page) {
 		ext4_journal_stop(handle);
 		ret = -ENOMEM;
@@ -2550,7 +2550,7 @@ retry:
 		goto out;
 	}
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page) {
 		ext4_journal_stop(handle);
 		ret = -ENOMEM;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index da98a9012fa5..9fd2a5e1be4d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2212,8 +2212,7 @@ retry:
 		 * We have a transaction open.  All is sweetness.  It also sets
 		 * i_size in generic_commit_write().
 		 */
-		err = __page_symlink(inode, symname, l,
-				mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
+		err = __page_symlink(inode, symname, l, 1);
 		if (err) {
 			clear_nlink(inode);
 			unlock_new_inode(inode);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 34930a964b82..4c9ee7011265 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -646,7 +646,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping,
 {
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 
-	*pagep = __grab_cache_page(mapping, index);
+	*pagep = grab_cache_page_write_begin(mapping, index, flags);
 	if (!*pagep)
 		return -ENOMEM;
 	return 0;
@@ -779,7 +779,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 			break;
 
 		err = -ENOMEM;
-		page = __grab_cache_page(mapping, index);
+		page = grab_cache_page_write_begin(mapping, index, 0);
 		if (!page)
 			break;
 
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index 27563816e1c5..15f710f2d4da 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -675,7 +675,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 		goto out_trans_fail;
 
 	error = -ENOMEM;
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	*pagep = page;
 	if (unlikely(!page))
 		goto out_endtrans;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 3a31451ac170..5c538e0ec14b 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -501,7 +501,7 @@ int hostfs_write_begin(struct file *file, struct address_space *mapping,
 {
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 
-	*pagep = __grab_cache_page(mapping, index);
+	*pagep = grab_cache_page_write_begin(mapping, index, flags);
 	if (!*pagep)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 5a98aa87c853..5edc2bf20581 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -132,7 +132,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	uint32_t pageofs = index << PAGE_CACHE_SHIFT;
 	int ret = 0;
 
-	pg = __grab_cache_page(mapping, index);
+	pg = grab_cache_page_write_begin(mapping, index, flags);
 	if (!pg)
 		return -ENOMEM;
 	*pagep = pg;
diff --git a/fs/libfs.c b/fs/libfs.c
index e960a8321902..bdaec17fa388 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -360,7 +360,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 	index = pos >> PAGE_CACHE_SHIFT;
 	from = pos & (PAGE_CACHE_SIZE - 1);
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 
diff --git a/fs/namei.c b/fs/namei.c
index dd5c9f0bf829..df2d3df4f049 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2817,18 +2817,23 @@ void page_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
 	}
 }
 
-int __page_symlink(struct inode *inode, const char *symname, int len,
-		gfp_t gfp_mask)
+/*
+ * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS
+ */
+int __page_symlink(struct inode *inode, const char *symname, int len, int nofs)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 	void *fsdata;
 	int err;
 	char *kaddr;
+	unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE;
+	if (nofs)
+		flags |= AOP_FLAG_NOFS;
 
 retry:
 	err = pagecache_write_begin(NULL, mapping, 0, len-1,
-				AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
+				flags, &page, &fsdata);
 	if (err)
 		goto fail;
 
@@ -2852,7 +2857,7 @@ fail:
 int page_symlink(struct inode *inode, const char *symname, int len)
 {
 	return __page_symlink(inode, symname, len,
-			mapping_gfp_mask(inode->i_mapping));
+			!(mapping_gfp_mask(inode->i_mapping) & __GFP_FS));
 }
 
 const struct inode_operations page_symlink_inode_operations = {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index d319b49f8f06..90f292b520d2 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -354,7 +354,7 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 		file->f_path.dentry->d_name.name,
 		mapping->host->i_ino, len, (long long) pos);
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 145c2d3e5e01..ed04f47007f8 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -2561,7 +2561,7 @@ static int reiserfs_write_begin(struct file *file,
 	}
 
 	index = pos >> PAGE_CACHE_SHIFT;
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
 	*pagep = page;
diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c
index e4f8d51a5553..92d5e8ffb639 100644
--- a/fs/smbfs/file.c
+++ b/fs/smbfs/file.c
@@ -297,7 +297,7 @@ static int smb_write_begin(struct file *file, struct address_space *mapping,
 			struct page **pagep, void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	*pagep = __grab_cache_page(mapping, index);
+	*pagep = grab_cache_page_write_begin(mapping, index, flags);
 	if (!*pagep)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index fe82d2464d46..bf37374567fa 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -219,7 +219,8 @@ static void release_existing_page_budget(struct ubifs_info *c)
 }
 
 static int write_begin_slow(struct address_space *mapping,
-			    loff_t pos, unsigned len, struct page **pagep)
+			    loff_t pos, unsigned len, struct page **pagep,
+			    unsigned flags)
 {
 	struct inode *inode = mapping->host;
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
@@ -247,7 +248,7 @@ static int write_begin_slow(struct address_space *mapping,
 	if (unlikely(err))
 		return err;
 
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (unlikely(!page)) {
 		ubifs_release_budget(c, &req);
 		return -ENOMEM;
@@ -438,7 +439,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
 		return -EROFS;
 
 	/* Try out the fast-path part first */
-	page = __grab_cache_page(mapping, index);
+	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (unlikely(!page))
 		return -ENOMEM;
 
@@ -483,7 +484,7 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping,
 		unlock_page(page);
 		page_cache_release(page);
 
-		return write_begin_slow(mapping, pos, len, pagep);
+		return write_begin_slow(mapping, pos, len, pagep, flags);
 	}
 
 	/*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e2170ee21e18..f2a3010140e3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -423,6 +423,9 @@ enum positive_aop_returns {
 
 #define AOP_FLAG_UNINTERRUPTIBLE	0x0001 /* will not do a short write */
 #define AOP_FLAG_CONT_EXPAND		0x0002 /* called from cont_expand */
+#define AOP_FLAG_NOFS			0x0004 /* used by filesystem to direct
+						* helper code (eg buffer layer)
+						* to clear GFP_FS from alloc */
 
 /*
  * oh the beauties of C type declarations.
@@ -2035,7 +2038,7 @@ extern int page_readlink(struct dentry *, char __user *, int);
 extern void *page_follow_link_light(struct dentry *, struct nameidata *);
 extern void page_put_link(struct dentry *, struct nameidata *, void *);
 extern int __page_symlink(struct inode *inode, const char *symname, int len,
-		gfp_t gfp_mask);
+		int nofs);
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern int generic_readlink(struct dentry *, char __user *, int);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 709742be02f0..01ca0856caff 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -241,7 +241,8 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
 unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
 			int tag, unsigned int nr_pages, struct page **pages);
 
-struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index);
+struct page *grab_cache_page_write_begin(struct address_space *mapping,
+			pgoff_t index, unsigned flags);
 
 /*
  * Returns locked page at given index in given cache, creating it if needed.
diff --git a/mm/filemap.c b/mm/filemap.c
index f3e5f8944d17..f8c69273c37f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2140,19 +2140,24 @@ EXPORT_SYMBOL(generic_file_direct_write);
  * Find or create a page at the given pagecache position. Return the locked
  * page. This function is specifically for buffered writes.
  */
-struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index)
+struct page *grab_cache_page_write_begin(struct address_space *mapping,
+					pgoff_t index, unsigned flags)
 {
 	int status;
 	struct page *page;
+	gfp_t gfp_notmask = 0;
+	if (flags & AOP_FLAG_NOFS)
+		gfp_notmask = __GFP_FS;
 repeat:
 	page = find_lock_page(mapping, index);
 	if (likely(page))
 		return page;
 
-	page = page_cache_alloc(mapping);
+	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
 	if (!page)
 		return NULL;
-	status = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+	status = add_to_page_cache_lru(page, mapping, index,
+						GFP_KERNEL & ~gfp_notmask);
 	if (unlikely(status)) {
 		page_cache_release(page);
 		if (status == -EEXIST)
@@ -2161,7 +2166,7 @@ repeat:
 	}
 	return page;
 }
-EXPORT_SYMBOL(__grab_cache_page);
+EXPORT_SYMBOL(grab_cache_page_write_begin);
 
 static ssize_t generic_perform_write(struct file *file,
 				struct iov_iter *i, loff_t pos)
-- 
cgit v1.2.3-70-g09d2


From 099e657625e801adf82054c8050dde5aceb68452 Mon Sep 17 00:00:00 2001
From: Alessandro Zummo <a.zummo@towertech.it>
Date: Sun, 4 Jan 2009 12:00:54 -0800
Subject: rtc: add alarm/update irq interfaces

Add standard interfaces for alarm/update irqs enabling.  Drivers are no
more required to implement equivalent ioctl code as rtc-dev will provide
it.

UIE emulation should now be handled correctly and will work even for those
RTC drivers who cannot be configured to do both UIE and AIE.

Signed-off-by: Alessandro Zummo <a.zummo@towertech.it>
Cc: David Brownell <david-b@pacbell.net>
Cc: Atsushi Nemoto <anemo@mba.ocn.ne.jp>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/rtc/Kconfig     |  6 +++++-
 drivers/rtc/interface.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/rtc/rtc-dev.c   | 51 +++++++++++++++++++++++++++++++---------------
 include/linux/rtc.h     |  8 +++++++-
 4 files changed, 101 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 123092d8a984..165a81843357 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -102,9 +102,13 @@ config RTC_INTF_DEV_UIE_EMUL
 	depends on RTC_INTF_DEV
 	help
 	  Provides an emulation for RTC_UIE if the underlying rtc chip
-	  driver does not expose RTC_UIE ioctls.  Those requests generate
+	  driver does not expose RTC_UIE ioctls. Those requests generate
 	  once-per-second update interrupts, used for synchronization.
 
+	  The emulation code will read the time from the hardware
+	  clock several times per second, please enable this option
+	  only if you know that you really need it.
+
 config RTC_DRV_TEST
 	tristate "Test driver/device"
 	help
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index a04c1b6b1575..fd2c652504ff 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -307,6 +307,60 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 }
 EXPORT_SYMBOL_GPL(rtc_set_alarm);
 
+int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled)
+{
+	int err = mutex_lock_interruptible(&rtc->ops_lock);
+	if (err)
+		return err;
+
+	if (!rtc->ops)
+		err = -ENODEV;
+	else if (!rtc->ops->alarm_irq_enable)
+		err = -EINVAL;
+	else
+		err = rtc->ops->alarm_irq_enable(rtc->dev.parent, enabled);
+
+	mutex_unlock(&rtc->ops_lock);
+	return err;
+}
+EXPORT_SYMBOL_GPL(rtc_alarm_irq_enable);
+
+int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled)
+{
+	int err = mutex_lock_interruptible(&rtc->ops_lock);
+	if (err)
+		return err;
+
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+	if (enabled == 0 && rtc->uie_irq_active) {
+		mutex_unlock(&rtc->ops_lock);
+		return rtc_dev_update_irq_enable_emul(rtc, enabled);
+	}
+#endif
+
+	if (!rtc->ops)
+		err = -ENODEV;
+	else if (!rtc->ops->update_irq_enable)
+		err = -EINVAL;
+	else
+		err = rtc->ops->update_irq_enable(rtc->dev.parent, enabled);
+
+	mutex_unlock(&rtc->ops_lock);
+
+#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
+	/*
+	 * Enable emulation if the driver did not provide
+	 * the update_irq_enable function pointer or if returned
+	 * -EINVAL to signal that it has been configured without
+	 * interrupts or that are not available at the moment.
+	 */
+	if (err == -EINVAL)
+		err = rtc_dev_update_irq_enable_emul(rtc, enabled);
+#endif
+	return err;
+}
+EXPORT_SYMBOL_GPL(rtc_update_irq_enable);
+
 /**
  * rtc_update_irq - report RTC periodic, alarm, and/or update irqs
  * @rtc: the rtc device
diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c
index ecdea44ae4e5..45152f4952d6 100644
--- a/drivers/rtc/rtc-dev.c
+++ b/drivers/rtc/rtc-dev.c
@@ -92,10 +92,10 @@ static void rtc_uie_timer(unsigned long data)
 	spin_unlock_irqrestore(&rtc->irq_lock, flags);
 }
 
-static void clear_uie(struct rtc_device *rtc)
+static int clear_uie(struct rtc_device *rtc)
 {
 	spin_lock_irq(&rtc->irq_lock);
-	if (rtc->irq_active) {
+	if (rtc->uie_irq_active) {
 		rtc->stop_uie_polling = 1;
 		if (rtc->uie_timer_active) {
 			spin_unlock_irq(&rtc->irq_lock);
@@ -108,9 +108,10 @@ static void clear_uie(struct rtc_device *rtc)
 			flush_scheduled_work();
 			spin_lock_irq(&rtc->irq_lock);
 		}
-		rtc->irq_active = 0;
+		rtc->uie_irq_active = 0;
 	}
 	spin_unlock_irq(&rtc->irq_lock);
+	return 0;
 }
 
 static int set_uie(struct rtc_device *rtc)
@@ -122,8 +123,8 @@ static int set_uie(struct rtc_device *rtc)
 	if (err)
 		return err;
 	spin_lock_irq(&rtc->irq_lock);
-	if (!rtc->irq_active) {
-		rtc->irq_active = 1;
+	if (!rtc->uie_irq_active) {
+		rtc->uie_irq_active = 1;
 		rtc->stop_uie_polling = 0;
 		rtc->oldsecs = tm.tm_sec;
 		rtc->uie_task_active = 1;
@@ -134,6 +135,16 @@ static int set_uie(struct rtc_device *rtc)
 	spin_unlock_irq(&rtc->irq_lock);
 	return 0;
 }
+
+int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc, unsigned int enabled)
+{
+	if (enabled)
+		return set_uie(rtc);
+	else
+		return clear_uie(rtc);
+}
+EXPORT_SYMBOL(rtc_dev_update_irq_enable_emul);
+
 #endif /* CONFIG_RTC_INTF_DEV_UIE_EMUL */
 
 static ssize_t
@@ -357,6 +368,22 @@ static long rtc_dev_ioctl(struct file *file,
 		err = rtc_irq_set_state(rtc, NULL, 0);
 		break;
 
+	case RTC_AIE_ON:
+		mutex_unlock(&rtc->ops_lock);
+		return rtc_alarm_irq_enable(rtc, 1);
+
+	case RTC_AIE_OFF:
+		mutex_unlock(&rtc->ops_lock);
+		return rtc_alarm_irq_enable(rtc, 0);
+
+	case RTC_UIE_ON:
+		mutex_unlock(&rtc->ops_lock);
+		return rtc_update_irq_enable(rtc, 1);
+
+	case RTC_UIE_OFF:
+		mutex_unlock(&rtc->ops_lock);
+		return rtc_update_irq_enable(rtc, 0);
+
 	case RTC_IRQP_SET:
 		err = rtc_irq_set_freq(rtc, NULL, arg);
 		break;
@@ -401,17 +428,6 @@ static long rtc_dev_ioctl(struct file *file,
 			err = -EFAULT;
 		return err;
 
-#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL
-	case RTC_UIE_OFF:
-		mutex_unlock(&rtc->ops_lock);
-		clear_uie(rtc);
-		return 0;
-
-	case RTC_UIE_ON:
-		mutex_unlock(&rtc->ops_lock);
-		err = set_uie(rtc);
-		return err;
-#endif
 	default:
 		err = -ENOTTY;
 		break;
@@ -440,7 +456,10 @@ static int rtc_dev_release(struct inode *inode, struct file *file)
 	 * Leave the alarm alone; it may be set to trigger a system wakeup
 	 * later, or be used by kernel code, and is a one-shot event anyway.
 	 */
+
+	/* Keep ioctl until all drivers are converted */
 	rtc_dev_ioctl(file, RTC_UIE_OFF, 0);
+	rtc_update_irq_enable(rtc, 0);
 	rtc_irq_set_state(rtc, NULL, 0);
 
 	if (rtc->ops->release)
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 91f597ad6acc..4046b75563c1 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -145,6 +145,8 @@ struct rtc_class_ops {
 	int (*irq_set_state)(struct device *, int enabled);
 	int (*irq_set_freq)(struct device *, int freq);
 	int (*read_callback)(struct device *, int data);
+	int (*alarm_irq_enable)(struct device *, unsigned int enabled);
+	int (*update_irq_enable)(struct device *, unsigned int enabled);
 };
 
 #define RTC_DEVICE_NAME_SIZE 20
@@ -181,7 +183,7 @@ struct rtc_device
 	struct timer_list uie_timer;
 	/* Those fields are protected by rtc->irq_lock */
 	unsigned int oldsecs;
-	unsigned int irq_active:1;
+	unsigned int uie_irq_active:1;
 	unsigned int stop_uie_polling:1;
 	unsigned int uie_task_active:1;
 	unsigned int uie_timer_active:1;
@@ -216,6 +218,10 @@ extern int rtc_irq_set_state(struct rtc_device *rtc,
 				struct rtc_task *task, int enabled);
 extern int rtc_irq_set_freq(struct rtc_device *rtc,
 				struct rtc_task *task, int freq);
+extern int rtc_update_irq_enable(struct rtc_device *rtc, unsigned int enabled);
+extern int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled);
+extern int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc,
+						unsigned int enabled);
 
 typedef struct rtc_task {
 	void (*func)(void *private_data);
-- 
cgit v1.2.3-70-g09d2


From 088af9a6e05d51e7c3dc85d45d8b7a52c3ee08d7 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Wed, 31 Dec 2008 12:31:18 +0100
Subject: module: fix module loading failure of large kernel modules for parisc

When creating the final layout of a kernel module in memory, allow the
module loader to reserve some additional memory in front of a given section.
This is currently only needed for the parisc port which needs to put the
stub entries there to fulfill the 17/22bit PCREL relocations with large
kernel modules like xfs.

Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (renamed fn)
---
 include/linux/moduleloader.h |  3 +++
 kernel/module.c              | 16 +++++++++++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index eb1033957486..c1f40c2f7ffb 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -13,6 +13,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr,
 			      char *secstrings,
 			      struct module *mod);
 
+/* Additional bytes needed by arch in front of individual sections */
+unsigned int arch_mod_section_prepend(struct module *mod, unsigned int section);
+
 /* Allocator used for allocating struct module, core sections and init
    sections.  Returns NULL on failure. */
 void *module_alloc(unsigned long size);
diff --git a/kernel/module.c b/kernel/module.c
index d3d254571bda..4299aefc20b8 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1578,11 +1578,21 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 	return ret;
 }
 
+/* Additional bytes needed by arch in front of individual sections */
+unsigned int __weak arch_mod_section_prepend(struct module *mod,
+					     unsigned int section)
+{
+	/* default implementation just returns zero */
+	return 0;
+}
+
 /* Update size with this section: return offset. */
-static long get_offset(unsigned int *size, Elf_Shdr *sechdr)
+static long get_offset(struct module *mod, unsigned int *size,
+		       Elf_Shdr *sechdr, unsigned int section)
 {
 	long ret;
 
+	*size += arch_mod_section_prepend(mod, section);
 	ret = ALIGN(*size, sechdr->sh_addralign ?: 1);
 	*size = ret + sechdr->sh_size;
 	return ret;
@@ -1622,7 +1632,7 @@ static void layout_sections(struct module *mod,
 			    || strncmp(secstrings + s->sh_name,
 				       ".init", 5) == 0)
 				continue;
-			s->sh_entsize = get_offset(&mod->core_size, s);
+			s->sh_entsize = get_offset(mod, &mod->core_size, s, i);
 			DEBUGP("\t%s\n", secstrings + s->sh_name);
 		}
 		if (m == 0)
@@ -1640,7 +1650,7 @@ static void layout_sections(struct module *mod,
 			    || strncmp(secstrings + s->sh_name,
 				       ".init", 5) != 0)
 				continue;
-			s->sh_entsize = (get_offset(&mod->init_size, s)
+			s->sh_entsize = (get_offset(mod, &mod->init_size, s, i)
 					 | INIT_OFFSET_MASK);
 			DEBUGP("\t%s\n", secstrings + s->sh_name);
 		}
-- 
cgit v1.2.3-70-g09d2


From 9ea09af3bd3090e8349ca2899ca2011bd94cda85 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 22 Dec 2008 12:36:30 +0100
Subject: stop_machine: introduce stop_machine_create/destroy.

Introduce stop_machine_create/destroy. With this interface subsystems
that need a non-failing stop_machine environment can create the
stop_machine machine threads before actually calling stop_machine.
When the threads aren't needed anymore they can be killed with
stop_machine_destroy again.

When stop_machine gets called and the threads aren't present they
will be created and destroyed automatically. This restores the old
behaviour of stop_machine.

This patch also converts cpu hotplug to the new interface since it
is special: cpu_down calls __stop_machine instead of stop_machine.
However the kstop threads will only be created when stop_machine
gets called.

Changing the code so that the threads would be created automatically
on __stop_machine is currently not possible: when __stop_machine gets
called we hold cpu_add_remove_lock, which is the same lock that
create_rt_workqueue would take. So the workqueue needs to be created
before the cpu hotplug code locks cpu_add_remove_lock.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/stop_machine.h | 22 ++++++++++++++++++
 kernel/cpu.c                 |  6 ++++-
 kernel/stop_machine.c        | 55 ++++++++++++++++++++++++++++++++++++--------
 3 files changed, 72 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 74d59a641362..baba3a23a814 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -35,6 +35,24 @@ int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
  * won't come or go while it's being called.  Used by hotplug cpu.
  */
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
+
+/**
+ * stop_machine_create: create all stop_machine threads
+ *
+ * Description: This causes all stop_machine threads to be created before
+ * stop_machine actually gets called. This can be used by subsystems that
+ * need a non failing stop_machine infrastructure.
+ */
+int stop_machine_create(void);
+
+/**
+ * stop_machine_destroy: destroy all stop_machine threads
+ *
+ * Description: This causes all stop_machine threads which were created with
+ * stop_machine_create to be destroyed again.
+ */
+void stop_machine_destroy(void);
+
 #else
 
 static inline int stop_machine(int (*fn)(void *), void *data,
@@ -46,5 +64,9 @@ static inline int stop_machine(int (*fn)(void *), void *data,
 	local_irq_enable();
 	return ret;
 }
+
+static inline int stop_machine_create(void) { return 0; }
+static inline void stop_machine_destroy(void) { }
+
 #endif /* CONFIG_SMP */
 #endif /* _LINUX_STOP_MACHINE */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 47fff3b63cbf..30e74dd6d01b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -269,8 +269,11 @@ out_release:
 
 int __ref cpu_down(unsigned int cpu)
 {
-	int err = 0;
+	int err;
 
+	err = stop_machine_create();
+	if (err)
+		return err;
 	cpu_maps_update_begin();
 
 	if (cpu_hotplug_disabled) {
@@ -297,6 +300,7 @@ int __ref cpu_down(unsigned int cpu)
 
 out:
 	cpu_maps_update_done();
+	stop_machine_destroy();
 	return err;
 }
 EXPORT_SYMBOL(cpu_down);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 286c41722e8c..0cd415ee62a2 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -38,7 +38,10 @@ struct stop_machine_data {
 static unsigned int num_threads;
 static atomic_t thread_ack;
 static DEFINE_MUTEX(lock);
-
+/* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */
+static DEFINE_MUTEX(setup_lock);
+/* Users of stop_machine. */
+static int refcount;
 static struct workqueue_struct *stop_machine_wq;
 static struct stop_machine_data active, idle;
 static const cpumask_t *active_cpus;
@@ -109,6 +112,43 @@ static int chill(void *unused)
 	return 0;
 }
 
+int stop_machine_create(void)
+{
+	mutex_lock(&setup_lock);
+	if (refcount)
+		goto done;
+	stop_machine_wq = create_rt_workqueue("kstop");
+	if (!stop_machine_wq)
+		goto err_out;
+	stop_machine_work = alloc_percpu(struct work_struct);
+	if (!stop_machine_work)
+		goto err_out;
+done:
+	refcount++;
+	mutex_unlock(&setup_lock);
+	return 0;
+
+err_out:
+	if (stop_machine_wq)
+		destroy_workqueue(stop_machine_wq);
+	mutex_unlock(&setup_lock);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(stop_machine_create);
+
+void stop_machine_destroy(void)
+{
+	mutex_lock(&setup_lock);
+	refcount--;
+	if (refcount)
+		goto done;
+	destroy_workqueue(stop_machine_wq);
+	free_percpu(stop_machine_work);
+done:
+	mutex_unlock(&setup_lock);
+}
+EXPORT_SYMBOL_GPL(stop_machine_destroy);
+
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
 	struct work_struct *sm_work;
@@ -146,19 +186,14 @@ int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
 	int ret;
 
+	ret = stop_machine_create();
+	if (ret)
+		return ret;
 	/* No CPUs can come up or down during this. */
 	get_online_cpus();
 	ret = __stop_machine(fn, data, cpus);
 	put_online_cpus();
-
+	stop_machine_destroy();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
-
-static int __init stop_machine_init(void)
-{
-	stop_machine_wq = create_rt_workqueue("kstop");
-	stop_machine_work = alloc_percpu(struct work_struct);
-	return 0;
-}
-core_initcall(stop_machine_init);
-- 
cgit v1.2.3-70-g09d2


From 14deae41566b5cdd992c01d0069518ced5227c83 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 4 Jan 2009 16:04:39 -0800
Subject: ipv6: Fix sporadic sendmsg -EINVAL when sending to multicast groups.

Thanks to excellent diagnosis by Eduard Guzovsky.

The core problem is that on a network with lots of active
multicast traffic, the neighbour cache can fill up.  If
we try to allocate a new route and thus neighbour cache
entry, the bog-standard GC attempt the neighbour layer does
in ineffective because route entries hold a reference
to the existing neighbour entries and GC can only liberate
entries with no references.

IPV4 already has a way to handle this, by doing a route cache
GC in such situations (when neigh attach returns -ENOBUFS).

So simply mimick this on the ipv6 side.

Tested-by: Eduard Guzovsky <eguzovsky@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ndisc.h |  4 ++--
 net/ipv6/route.c    | 52 +++++++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 49 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index ce532f2222ce..1459ed3e2697 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -155,9 +155,9 @@ static inline struct neighbour * ndisc_get_neigh(struct net_device *dev, const s
 {
 
 	if (dev)
-		return __neigh_lookup(&nd_tbl, addr, dev, 1);
+		return __neigh_lookup_errno(&nd_tbl, addr, dev);
 
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 18c486cf4987..76f06b94ab9f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -627,6 +627,9 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
 	rt = ip6_rt_copy(ort);
 
 	if (rt) {
+		struct neighbour *neigh;
+		int attempts = !in_softirq();
+
 		if (!(rt->rt6i_flags&RTF_GATEWAY)) {
 			if (rt->rt6i_dst.plen != 128 &&
 			    ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))
@@ -646,7 +649,35 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
 		}
 #endif
 
-		rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
+	retry:
+		neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
+		if (IS_ERR(neigh)) {
+			struct net *net = dev_net(rt->rt6i_dev);
+			int saved_rt_min_interval =
+				net->ipv6.sysctl.ip6_rt_gc_min_interval;
+			int saved_rt_elasticity =
+				net->ipv6.sysctl.ip6_rt_gc_elasticity;
+
+			if (attempts-- > 0) {
+				net->ipv6.sysctl.ip6_rt_gc_elasticity = 1;
+				net->ipv6.sysctl.ip6_rt_gc_min_interval = 0;
+
+				ip6_dst_gc(net->ipv6.ip6_dst_ops);
+
+				net->ipv6.sysctl.ip6_rt_gc_elasticity =
+					saved_rt_elasticity;
+				net->ipv6.sysctl.ip6_rt_gc_min_interval =
+					saved_rt_min_interval;
+				goto retry;
+			}
+
+			if (net_ratelimit())
+				printk(KERN_WARNING
+				       "Neighbour table overflow.\n");
+			dst_free(&rt->u.dst);
+			return NULL;
+		}
+		rt->rt6i_nexthop = neigh;
 
 	}
 
@@ -945,8 +976,11 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 	dev_hold(dev);
 	if (neigh)
 		neigh_hold(neigh);
-	else
+	else {
 		neigh = ndisc_get_neigh(dev, addr);
+		if (IS_ERR(neigh))
+			neigh = NULL;
+	}
 
 	rt->rt6i_dev	  = dev;
 	rt->rt6i_idev     = idev;
@@ -1887,6 +1921,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 {
 	struct net *net = dev_net(idev->dev);
 	struct rt6_info *rt = ip6_dst_alloc(net->ipv6.ip6_dst_ops);
+	struct neighbour *neigh;
 
 	if (rt == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1909,11 +1944,18 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 		rt->rt6i_flags |= RTF_ANYCAST;
 	else
 		rt->rt6i_flags |= RTF_LOCAL;
-	rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
-	if (rt->rt6i_nexthop == NULL) {
+	neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
+	if (IS_ERR(neigh)) {
 		dst_free(&rt->u.dst);
-		return ERR_PTR(-ENOMEM);
+
+		/* We are casting this because that is the return
+		 * value type.  But an errno encoded pointer is the
+		 * same regardless of the underlying pointer type,
+		 * and that's what we are returning.  So this is OK.
+		 */
+		return (struct rt6_info *) neigh;
 	}
+	rt->rt6i_nexthop = neigh;
 
 	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
 	rt->rt6i_dst.plen = 128;
-- 
cgit v1.2.3-70-g09d2


From 5d38a079ce3971f932bbdc0dc5b887806fabd5dc Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sun, 4 Jan 2009 16:13:40 -0800
Subject: gro: Add page frag support

This patch allows GRO to merge page frags (skb_shinfo(skb)->frags)
in one skb, rather than using the less efficient frag_list.

It also adds a new interface, napi_gro_frags to allow drivers
to inject page frags directly into the stack without allocating
an skb.  This is intended to be the GRO equivalent for LRO's
lro_receive_frags interface.

The existing GSO interface can already handle page frags with
or without an appended frag_list so nothing needs to be changed
there.

The merging itself is rather simple.  We store any new frag entries
after the last existing entry, without checking whether the first
new entry can be merged with the last existing entry.  Making this
check would actually be easy but since no existing driver can
produce contiguous frags anyway it would just be mental masturbation.

If the total number of entries would exceed the capacity of a
single skb, we simply resort to using frag_list as we do now.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 16 ++++++++-
 net/core/dev.c            | 91 ++++++++++++++++++++++++++++++++++++++++++++---
 net/core/skbuff.c         | 14 +++++++-
 3 files changed, 114 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 41e1224651cf..c28bbba3c23d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -313,10 +313,11 @@ struct napi_struct {
 #ifdef CONFIG_NETPOLL
 	spinlock_t		poll_lock;
 	int			poll_owner;
-	struct net_device	*dev;
 #endif
+	struct net_device	*dev;
 	struct list_head	dev_list;
 	struct sk_buff		*gro_list;
+	struct sk_buff		*skb;
 };
 
 enum
@@ -990,6 +991,9 @@ struct napi_gro_cb {
 
 	/* Number of segments aggregated. */
 	int count;
+
+	/* Free the skb? */
+	int free;
 };
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
@@ -1011,6 +1015,14 @@ struct packet_type {
 	struct list_head	list;
 };
 
+struct napi_gro_fraginfo {
+	skb_frag_t frags[MAX_SKB_FRAGS];
+	unsigned int nr_frags;
+	unsigned int ip_summed;
+	unsigned int len;
+	__wsum csum;
+};
+
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 
@@ -1363,6 +1375,8 @@ extern int		netif_receive_skb(struct sk_buff *skb);
 extern void		napi_gro_flush(struct napi_struct *napi);
 extern int		napi_gro_receive(struct napi_struct *napi,
 					 struct sk_buff *skb);
+extern int		napi_gro_frags(struct napi_struct *napi,
+				       struct napi_gro_fraginfo *info);
 extern void		netif_nit_deliver(struct sk_buff *skb);
 extern int		dev_valid_name(const char *name);
 extern int		dev_ioctl(struct net *net, unsigned int cmd, void __user *);
diff --git a/net/core/dev.c b/net/core/dev.c
index 1e1a68066457..382df6c09eec 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -132,6 +132,9 @@
 /* Instead of increasing this, you should create a hash table. */
 #define MAX_GRO_SKBS 8
 
+/* This should be increased if a protocol with a bigger head is added. */
+#define GRO_MAX_HEAD (MAX_HEADER + 128)
+
 /*
  *	The list of packet types we will receive (as opposed to discard)
  *	and the routines to invoke.
@@ -2345,7 +2348,7 @@ static int napi_gro_complete(struct sk_buff *skb)
 	struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
 	int err = -ENOENT;
 
-	if (!skb_shinfo(skb)->frag_list)
+	if (NAPI_GRO_CB(skb)->count == 1)
 		goto out;
 
 	rcu_read_lock();
@@ -2384,7 +2387,7 @@ void napi_gro_flush(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
-int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff **pp = NULL;
 	struct packet_type *ptype;
@@ -2393,6 +2396,7 @@ int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 	int count = 0;
 	int same_flow;
 	int mac_len;
+	int free;
 
 	if (!(skb->dev->features & NETIF_F_GRO))
 		goto normal;
@@ -2409,6 +2413,7 @@ int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 		skb->mac_len = mac_len;
 		NAPI_GRO_CB(skb)->same_flow = 0;
 		NAPI_GRO_CB(skb)->flush = 0;
+		NAPI_GRO_CB(skb)->free = 0;
 
 		for (p = napi->gro_list; p; p = p->next) {
 			count++;
@@ -2428,6 +2433,7 @@ int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 		goto normal;
 
 	same_flow = NAPI_GRO_CB(skb)->same_flow;
+	free = NAPI_GRO_CB(skb)->free;
 
 	if (pp) {
 		struct sk_buff *nskb = *pp;
@@ -2452,13 +2458,86 @@ int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 	napi->gro_list = skb;
 
 ok:
-	return NET_RX_SUCCESS;
+	return free;
 
 normal:
-	return netif_receive_skb(skb);
+	return -1;
+}
+
+int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+{
+	switch (__napi_gro_receive(napi, skb)) {
+	case -1:
+		return netif_receive_skb(skb);
+
+	case 1:
+		kfree_skb(skb);
+		break;
+	}
+
+	return NET_RX_SUCCESS;
 }
 EXPORT_SYMBOL(napi_gro_receive);
 
+int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info)
+{
+	struct net_device *dev = napi->dev;
+	struct sk_buff *skb = napi->skb;
+	int err = NET_RX_DROP;
+
+	napi->skb = NULL;
+
+	if (!skb) {
+		skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN);
+		if (!skb)
+			goto out;
+
+		skb_reserve(skb, NET_IP_ALIGN);
+	}
+
+	BUG_ON(info->nr_frags > MAX_SKB_FRAGS);
+	skb_shinfo(skb)->nr_frags = info->nr_frags;
+	memcpy(skb_shinfo(skb)->frags, info->frags, sizeof(info->frags));
+
+	skb->data_len = info->len;
+	skb->len += info->len;
+	skb->truesize += info->len;
+
+	if (!pskb_may_pull(skb, ETH_HLEN))
+		goto reuse;
+
+	err = NET_RX_SUCCESS;
+
+	skb->protocol = eth_type_trans(skb, dev);
+
+	skb->ip_summed = info->ip_summed;
+	skb->csum = info->csum;
+
+	switch (__napi_gro_receive(napi, skb)) {
+	case -1:
+		return netif_receive_skb(skb);
+
+	case 0:
+		goto out;
+	}
+
+reuse:
+	skb_shinfo(skb)->nr_frags = 0;
+
+	skb->len -= skb->data_len;
+	skb->truesize -= skb->data_len;
+	skb->data_len = 0;
+
+	__skb_pull(skb, skb_headlen(skb));
+	skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb));
+
+	napi->skb = skb;
+
+out:
+	return err;
+}
+EXPORT_SYMBOL(napi_gro_frags);
+
 static int process_backlog(struct napi_struct *napi, int quota)
 {
 	int work = 0;
@@ -2537,11 +2616,12 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 {
 	INIT_LIST_HEAD(&napi->poll_list);
 	napi->gro_list = NULL;
+	napi->skb = NULL;
 	napi->poll = poll;
 	napi->weight = weight;
 	list_add(&napi->dev_list, &dev->napi_list);
-#ifdef CONFIG_NETPOLL
 	napi->dev = dev;
+#ifdef CONFIG_NETPOLL
 	spin_lock_init(&napi->poll_lock);
 	napi->poll_owner = -1;
 #endif
@@ -2554,6 +2634,7 @@ void netif_napi_del(struct napi_struct *napi)
 	struct sk_buff *skb, *next;
 
 	list_del_init(&napi->dev_list);
+	kfree(napi->skb);
 
 	for (skb = napi->gro_list; skb; skb = next) {
 		next = skb->next;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3aafb10325b8..5110b359c758 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2594,6 +2594,17 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 	if (skb_shinfo(p)->frag_list)
 		goto merge;
+	else if (!skb_headlen(p) && !skb_headlen(skb) &&
+		 skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags <
+		 MAX_SKB_FRAGS) {
+		memcpy(skb_shinfo(p)->frags + skb_shinfo(p)->nr_frags,
+		       skb_shinfo(skb)->frags,
+		       skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
+
+		skb_shinfo(p)->nr_frags += skb_shinfo(skb)->nr_frags;
+		NAPI_GRO_CB(skb)->free = 1;
+		goto done;
+	}
 
 	headroom = skb_headroom(p);
 	nskb = netdev_alloc_skb(p->dev, headroom);
@@ -2628,11 +2639,12 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	p = nskb;
 
 merge:
-	NAPI_GRO_CB(p)->count++;
 	p->prev->next = skb;
 	p->prev = skb;
 	skb_header_release(skb);
 
+done:
+	NAPI_GRO_CB(p)->count++;
 	p->data_len += skb->len;
 	p->truesize += skb->len;
 	p->len += skb->len;
-- 
cgit v1.2.3-70-g09d2


From e9079cce201784632aed4b1a3121ee38c1ced0b6 Mon Sep 17 00:00:00 2001
From: Steven Whitehouse <swhiteho@redhat.com>
Date: Tue, 14 Oct 2008 14:43:29 +0100
Subject: GFS2: Support for FIEMAP ioctl

This patch implements the FIEMAP ioctl for GFS2. We can use the generic
code (aside from a lock order issue, solved as per Ted Tso's suggestion)
for which I've introduced a new variant of the generic function. We also
have one exception to deal with, namely stuffed files, so we do that
"by hand", setting all the required flags.

This has been tested with a modified (I could only find an old version) of
Eric's test program, and appears to work correctly.

This patch does not currently support FIEMAP of xattrs, but the plan is to add
that feature at some future point.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Cc: Theodore Tso <tytso@mit.edu>
Cc: Eric Sandeen <sandeen@redhat.com>
---
 fs/gfs2/ops_inode.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/ioctl.c          | 44 ++++++++++++++++++++++++++++++++++----------
 include/linux/fs.h  |  3 +++
 3 files changed, 83 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index d232991b9046..1e24b65e1d23 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -19,6 +19,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 #include <linux/lm_interface.h>
+#include <linux/fiemap.h>
 #include <asm/uaccess.h>
 
 #include "gfs2.h"
@@ -1212,6 +1213,48 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name)
 	return gfs2_ea_remove(GFS2_I(dentry->d_inode), &er);
 }
 
+static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		       u64 start, u64 len)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_holder gh;
+	int ret;
+
+	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+	if (ret)
+		return ret;
+
+	mutex_lock(&inode->i_mutex);
+
+	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+	if (ret)
+		goto out;
+
+	if (gfs2_is_stuffed(ip)) {
+		u64 phys = ip->i_no_addr << inode->i_blkbits;
+		u64 size = i_size_read(inode);
+		u32 flags = FIEMAP_EXTENT_LAST|FIEMAP_EXTENT_NOT_ALIGNED|
+			    FIEMAP_EXTENT_DATA_INLINE;
+		phys += sizeof(struct gfs2_dinode);
+		phys += start;
+		if (start + len > size)
+			len = size - start;
+		if (start < size)
+			ret = fiemap_fill_next_extent(fieinfo, start, phys,
+						      len, flags);
+		if (ret == 1)
+			ret = 0;
+	} else {
+		ret = __generic_block_fiemap(inode, fieinfo, start, len,
+					     gfs2_block_map);
+	}
+
+	gfs2_glock_dq_uninit(&gh);
+out:
+	mutex_unlock(&inode->i_mutex);
+	return ret;
+}
+
 const struct inode_operations gfs2_file_iops = {
 	.permission = gfs2_permission,
 	.setattr = gfs2_setattr,
@@ -1220,6 +1263,7 @@ const struct inode_operations gfs2_file_iops = {
 	.getxattr = gfs2_getxattr,
 	.listxattr = gfs2_listxattr,
 	.removexattr = gfs2_removexattr,
+	.fiemap = gfs2_fiemap,
 };
 
 const struct inode_operations gfs2_dir_iops = {
@@ -1239,6 +1283,7 @@ const struct inode_operations gfs2_dir_iops = {
 	.getxattr = gfs2_getxattr,
 	.listxattr = gfs2_listxattr,
 	.removexattr = gfs2_removexattr,
+	.fiemap = gfs2_fiemap,
 };
 
 const struct inode_operations gfs2_symlink_iops = {
@@ -1251,5 +1296,6 @@ const struct inode_operations gfs2_symlink_iops = {
 	.getxattr = gfs2_getxattr,
 	.listxattr = gfs2_listxattr,
 	.removexattr = gfs2_removexattr,
+	.fiemap = gfs2_fiemap,
 };
 
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 43e8b2c0664b..cc3f1aa1cf7b 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -231,7 +231,8 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
 #define blk_to_logical(inode, blk) (blk << (inode)->i_blkbits)
 #define logical_to_blk(inode, offset) (offset >> (inode)->i_blkbits);
 
-/*
+/**
+ * __generic_block_fiemap - FIEMAP for block based inodes (no locking)
  * @inode - the inode to map
  * @arg - the pointer to userspace where we copy everything to
  * @get_block - the fs's get_block function
@@ -242,11 +243,15 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
  *
  * If it is possible to have data blocks beyond a hole past @inode->i_size, then
  * please do not use this function, it will stop at the first unmapped block
- * beyond i_size
+ * beyond i_size.
+ *
+ * If you use this function directly, you need to do your own locking. Use
+ * generic_block_fiemap if you want the locking done for you.
  */
-int generic_block_fiemap(struct inode *inode,
-			 struct fiemap_extent_info *fieinfo, u64 start,
-			 u64 len, get_block_t *get_block)
+
+int __generic_block_fiemap(struct inode *inode,
+			   struct fiemap_extent_info *fieinfo, u64 start,
+			   u64 len, get_block_t *get_block)
 {
 	struct buffer_head tmp;
 	unsigned int start_blk;
@@ -260,9 +265,6 @@ int generic_block_fiemap(struct inode *inode,
 
 	start_blk = logical_to_blk(inode, start);
 
-	/* guard against change */
-	mutex_lock(&inode->i_mutex);
-
 	length = (long long)min_t(u64, len, i_size_read(inode));
 	map_len = length;
 
@@ -334,14 +336,36 @@ int generic_block_fiemap(struct inode *inode,
 		cond_resched();
 	} while (1);
 
-	mutex_unlock(&inode->i_mutex);
-
 	/* if ret is 1 then we just hit the end of the extent array */
 	if (ret == 1)
 		ret = 0;
 
 	return ret;
 }
+EXPORT_SYMBOL(__generic_block_fiemap);
+
+/**
+ * generic_block_fiemap - FIEMAP for block based inodes
+ * @inode: The inode to map
+ * @fieinfo: The mapping information
+ * @start: The initial block to map
+ * @len: The length of the extect to attempt to map
+ * @get_block: The block mapping function for the fs
+ *
+ * Calls __generic_block_fiemap to map the inode, after taking
+ * the inode's mutex lock.
+ */
+
+int generic_block_fiemap(struct inode *inode,
+			 struct fiemap_extent_info *fieinfo, u64 start,
+			 u64 len, get_block_t *get_block)
+{
+	int ret;
+	mutex_lock(&inode->i_mutex);
+	ret = __generic_block_fiemap(inode, fieinfo, start, len, get_block);
+	mutex_unlock(&inode->i_mutex);
+	return ret;
+}
 EXPORT_SYMBOL(generic_block_fiemap);
 
 #endif  /*  CONFIG_BLOCK  */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f2a3010140e3..e34bc6925fdf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2059,6 +2059,9 @@ extern int vfs_fstat(unsigned int, struct kstat *);
 
 extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		    unsigned long arg);
+extern int __generic_block_fiemap(struct inode *inode,
+				  struct fiemap_extent_info *fieinfo, u64 start,
+				  u64 len, get_block_t *get_block);
 extern int generic_block_fiemap(struct inode *inode,
 				struct fiemap_extent_info *fieinfo, u64 start,
 				u64 len, get_block_t *get_block);
-- 
cgit v1.2.3-70-g09d2


From 74f783af95c982aef6d3a1415275650dcf511666 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 19 Aug 2008 14:51:22 +0200
Subject: quota: Add callbacks for allocating and destroying dquot structures

Some filesystems would like to keep private information together with each
dquot. Add callbacks alloc_dquot and destroy_dquot allowing filesystem to
allocate larger dquots from their private slab in a similar fashion we
currently allocate inodes.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c            | 27 ++++++++++++++++++++++-----
 include/linux/quota.h |  2 ++
 2 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index c237ccc8581c..1b5fc4b7fbeb 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -415,6 +415,16 @@ out_dqlock:
 	return ret;
 }
 
+static void dquot_destroy(struct dquot *dquot)
+{
+	kmem_cache_free(dquot_cachep, dquot);
+}
+
+static inline void do_destroy_dquot(struct dquot *dquot)
+{
+	dquot->dq_sb->dq_op->destroy_dquot(dquot);
+}
+
 /* Invalidate all dquots on the list. Note that this function is called after
  * quota is disabled and pointers from inodes removed so there cannot be new
  * quota users. There can still be some users of quotas due to inodes being
@@ -463,7 +473,7 @@ restart:
 		remove_dquot_hash(dquot);
 		remove_free_dquot(dquot);
 		remove_inuse(dquot);
-		kmem_cache_free(dquot_cachep, dquot);
+		do_destroy_dquot(dquot);
 	}
 	spin_unlock(&dq_list_lock);
 }
@@ -527,7 +537,7 @@ static void prune_dqcache(int count)
 		remove_dquot_hash(dquot);
 		remove_free_dquot(dquot);
 		remove_inuse(dquot);
-		kmem_cache_free(dquot_cachep, dquot);
+		do_destroy_dquot(dquot);
 		count--;
 		head = free_dquots.prev;
 	}
@@ -625,11 +635,16 @@ we_slept:
 	spin_unlock(&dq_list_lock);
 }
 
+static struct dquot *dquot_alloc(struct super_block *sb, int type)
+{
+	return kmem_cache_zalloc(dquot_cachep, GFP_NOFS);
+}
+
 static struct dquot *get_empty_dquot(struct super_block *sb, int type)
 {
 	struct dquot *dquot;
 
-	dquot = kmem_cache_zalloc(dquot_cachep, GFP_NOFS);
+	dquot = sb->dq_op->alloc_dquot(sb, type);
 	if(!dquot)
 		return NODQUOT;
 
@@ -682,7 +697,7 @@ we_slept:
 		dqstats.lookups++;
 		spin_unlock(&dq_list_lock);
 		if (empty)
-			kmem_cache_free(dquot_cachep, empty);
+			do_destroy_dquot(empty);
 	}
 	/* Wait for dq_lock - after this we know that either dquot_release() is already
 	 * finished or it will be canceled due to dq_count > 1 test */
@@ -1533,7 +1548,9 @@ struct dquot_operations dquot_operations = {
 	.acquire_dquot	= dquot_acquire,
 	.release_dquot	= dquot_release,
 	.mark_dirty	= dquot_mark_dquot_dirty,
-	.write_info	= dquot_commit_info
+	.write_info	= dquot_commit_info,
+	.alloc_dquot	= dquot_alloc,
+	.destroy_dquot	= dquot_destroy,
 };
 
 static inline void set_enable_flags(struct quota_info *dqopt, int type)
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 40401b554484..3ce708c2cb3c 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -292,6 +292,8 @@ struct dquot_operations {
 	int (*free_inode) (const struct inode *, unsigned long);
 	int (*transfer) (struct inode *, struct iattr *);
 	int (*write_dquot) (struct dquot *);		/* Ordinary dquot write */
+	struct dquot *(*alloc_dquot)(struct super_block *, int);	/* Allocate memory for new dquot */
+	void (*destroy_dquot)(struct dquot *);		/* Free memory for dquot */
 	int (*acquire_dquot) (struct dquot *);		/* Quota is going to be created on disk */
 	int (*release_dquot) (struct dquot *);		/* Quota is going to be deleted from disk */
 	int (*mark_dirty) (struct dquot *);		/* Dquot is marked dirty */
-- 
cgit v1.2.3-70-g09d2


From 12095460f7f315f8ef67a55b2194195d325d48d7 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 20 Aug 2008 14:45:12 +0200
Subject: quota: Increase size of variables for limits and inode usage

So far quota was fine with quota block limits and inode limits/numbers in
a 32-bit type. Now with rapid increase in storage sizes there are coming
requests to be able to handle quota limits above 4TB / more that 2^32 inodes.
So bump up sizes of types in mem_dqblk structure to 64-bits to be able to
handle this. Also update inode allocation / checking functions to use qsize_t
and make global structure keep quota limits in bytes so that things are
consistent.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c               | 50 ++++++++++++++++++++++++++++--------------------
 fs/quota_v1.c            | 25 ++++++++++++++++++------
 fs/quota_v2.c            | 21 ++++++++++++++++----
 include/linux/quota.h    | 28 ++++++++++++---------------
 include/linux/quotaops.h |  4 ++--
 5 files changed, 79 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index 1b5fc4b7fbeb..c02223b6aeb2 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -835,7 +835,7 @@ static void drop_dquot_ref(struct super_block *sb, int type)
 	}
 }
 
-static inline void dquot_incr_inodes(struct dquot *dquot, unsigned long number)
+static inline void dquot_incr_inodes(struct dquot *dquot, qsize_t number)
 {
 	dquot->dq_dqb.dqb_curinodes += number;
 }
@@ -845,7 +845,7 @@ static inline void dquot_incr_space(struct dquot *dquot, qsize_t number)
 	dquot->dq_dqb.dqb_curspace += number;
 }
 
-static inline void dquot_decr_inodes(struct dquot *dquot, unsigned long number)
+static inline void dquot_decr_inodes(struct dquot *dquot, qsize_t number)
 {
 	if (dquot->dq_dqb.dqb_curinodes > number)
 		dquot->dq_dqb.dqb_curinodes -= number;
@@ -862,7 +862,7 @@ static inline void dquot_decr_space(struct dquot *dquot, qsize_t number)
 		dquot->dq_dqb.dqb_curspace -= number;
 	else
 		dquot->dq_dqb.dqb_curspace = 0;
-	if (toqb(dquot->dq_dqb.dqb_curspace) <= dquot->dq_dqb.dqb_bsoftlimit)
+	if (dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit)
 		dquot->dq_dqb.dqb_btime = (time_t) 0;
 	clear_bit(DQ_BLKS_B, &dquot->dq_flags);
 }
@@ -1038,7 +1038,7 @@ static inline char ignore_hardlimit(struct dquot *dquot)
 }
 
 /* needs dq_data_lock */
-static int check_idq(struct dquot *dquot, ulong inodes, char *warntype)
+static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
 {
 	*warntype = QUOTA_NL_NOWARN;
 	if (inodes <= 0 || test_bit(DQ_FAKE_B, &dquot->dq_flags))
@@ -1077,7 +1077,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
 		return QUOTA_OK;
 
 	if (dquot->dq_dqb.dqb_bhardlimit &&
-	   toqb(dquot->dq_dqb.dqb_curspace + space) > dquot->dq_dqb.dqb_bhardlimit &&
+	    dquot->dq_dqb.dqb_curspace + space > dquot->dq_dqb.dqb_bhardlimit &&
             !ignore_hardlimit(dquot)) {
 		if (!prealloc)
 			*warntype = QUOTA_NL_BHARDWARN;
@@ -1085,7 +1085,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
 	}
 
 	if (dquot->dq_dqb.dqb_bsoftlimit &&
-	   toqb(dquot->dq_dqb.dqb_curspace + space) > dquot->dq_dqb.dqb_bsoftlimit &&
+	    dquot->dq_dqb.dqb_curspace + space > dquot->dq_dqb.dqb_bsoftlimit &&
 	    dquot->dq_dqb.dqb_btime && get_seconds() >= dquot->dq_dqb.dqb_btime &&
             !ignore_hardlimit(dquot)) {
 		if (!prealloc)
@@ -1094,7 +1094,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
 	}
 
 	if (dquot->dq_dqb.dqb_bsoftlimit &&
-	   toqb(dquot->dq_dqb.dqb_curspace + space) > dquot->dq_dqb.dqb_bsoftlimit &&
+	    dquot->dq_dqb.dqb_curspace + space > dquot->dq_dqb.dqb_bsoftlimit &&
 	    dquot->dq_dqb.dqb_btime == 0) {
 		if (!prealloc) {
 			*warntype = QUOTA_NL_BSOFTWARN;
@@ -1111,7 +1111,7 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
 	return QUOTA_OK;
 }
 
-static int info_idq_free(struct dquot *dquot, ulong inodes)
+static int info_idq_free(struct dquot *dquot, qsize_t inodes)
 {
 	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
 	    dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit)
@@ -1128,15 +1128,13 @@ static int info_idq_free(struct dquot *dquot, ulong inodes)
 static int info_bdq_free(struct dquot *dquot, qsize_t space)
 {
 	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
-	    toqb(dquot->dq_dqb.dqb_curspace) <= dquot->dq_dqb.dqb_bsoftlimit)
+	    dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit)
 		return QUOTA_NL_NOWARN;
 
-	if (toqb(dquot->dq_dqb.dqb_curspace - space) <=
-	    dquot->dq_dqb.dqb_bsoftlimit)
+	if (dquot->dq_dqb.dqb_curspace - space <= dquot->dq_dqb.dqb_bsoftlimit)
 		return QUOTA_NL_BSOFTBELOW;
-	if (toqb(dquot->dq_dqb.dqb_curspace) >= dquot->dq_dqb.dqb_bhardlimit &&
-	    toqb(dquot->dq_dqb.dqb_curspace - space) <
-						dquot->dq_dqb.dqb_bhardlimit)
+	if (dquot->dq_dqb.dqb_curspace >= dquot->dq_dqb.dqb_bhardlimit &&
+	    dquot->dq_dqb.dqb_curspace - space < dquot->dq_dqb.dqb_bhardlimit)
 		return QUOTA_NL_BHARDBELOW;
 	return QUOTA_NL_NOWARN;
 }
@@ -1279,7 +1277,7 @@ warn_put_all:
 /*
  * This operation can block, but only after everything is updated
  */
-int dquot_alloc_inode(const struct inode *inode, unsigned long number)
+int dquot_alloc_inode(const struct inode *inode, qsize_t number)
 {
 	int cnt, ret = NO_QUOTA;
 	char warntype[MAXQUOTAS];
@@ -1364,7 +1362,7 @@ out_sub:
 /*
  * This operation can block, but only after everything is updated
  */
-int dquot_free_inode(const struct inode *inode, unsigned long number)
+int dquot_free_inode(const struct inode *inode, qsize_t number)
 {
 	unsigned int cnt;
 	char warntype[MAXQUOTAS];
@@ -1883,14 +1881,24 @@ int vfs_dq_quota_on_remount(struct super_block *sb)
 	return ret;
 }
 
+static inline qsize_t qbtos(qsize_t blocks)
+{
+	return blocks << QIF_DQBLKSIZE_BITS;
+}
+
+static inline qsize_t stoqb(qsize_t space)
+{
+	return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
+}
+
 /* Generic routine for getting common part of quota structure */
 static void do_get_dqblk(struct dquot *dquot, struct if_dqblk *di)
 {
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 
 	spin_lock(&dq_data_lock);
-	di->dqb_bhardlimit = dm->dqb_bhardlimit;
-	di->dqb_bsoftlimit = dm->dqb_bsoftlimit;
+	di->dqb_bhardlimit = stoqb(dm->dqb_bhardlimit);
+	di->dqb_bsoftlimit = stoqb(dm->dqb_bsoftlimit);
 	di->dqb_curspace = dm->dqb_curspace;
 	di->dqb_ihardlimit = dm->dqb_ihardlimit;
 	di->dqb_isoftlimit = dm->dqb_isoftlimit;
@@ -1937,8 +1945,8 @@ static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
 		check_blim = 1;
 	}
 	if (di->dqb_valid & QIF_BLIMITS) {
-		dm->dqb_bsoftlimit = di->dqb_bsoftlimit;
-		dm->dqb_bhardlimit = di->dqb_bhardlimit;
+		dm->dqb_bsoftlimit = qbtos(di->dqb_bsoftlimit);
+		dm->dqb_bhardlimit = qbtos(di->dqb_bhardlimit);
 		check_blim = 1;
 	}
 	if (di->dqb_valid & QIF_INODES) {
@@ -1956,7 +1964,7 @@ static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
 		dm->dqb_itime = di->dqb_itime;
 
 	if (check_blim) {
-		if (!dm->dqb_bsoftlimit || toqb(dm->dqb_curspace) < dm->dqb_bsoftlimit) {
+		if (!dm->dqb_bsoftlimit || dm->dqb_curspace < dm->dqb_bsoftlimit) {
 			dm->dqb_btime = 0;
 			clear_bit(DQ_BLKS_B, &dquot->dq_flags);
 		}
diff --git a/fs/quota_v1.c b/fs/quota_v1.c
index 5ae15b13eeb0..3e078eee5644 100644
--- a/fs/quota_v1.c
+++ b/fs/quota_v1.c
@@ -14,14 +14,27 @@ MODULE_AUTHOR("Jan Kara");
 MODULE_DESCRIPTION("Old quota format support");
 MODULE_LICENSE("GPL");
 
+#define QUOTABLOCK_BITS 10
+#define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS)
+
+static inline qsize_t v1_stoqb(qsize_t space)
+{
+	return (space + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS;
+}
+
+static inline qsize_t v1_qbtos(qsize_t blocks)
+{
+	return blocks << QUOTABLOCK_BITS;
+}
+
 static void v1_disk2mem_dqblk(struct mem_dqblk *m, struct v1_disk_dqblk *d)
 {
 	m->dqb_ihardlimit = d->dqb_ihardlimit;
 	m->dqb_isoftlimit = d->dqb_isoftlimit;
 	m->dqb_curinodes = d->dqb_curinodes;
-	m->dqb_bhardlimit = d->dqb_bhardlimit;
-	m->dqb_bsoftlimit = d->dqb_bsoftlimit;
-	m->dqb_curspace = ((qsize_t)d->dqb_curblocks) << QUOTABLOCK_BITS;
+	m->dqb_bhardlimit = v1_qbtos(d->dqb_bhardlimit);
+	m->dqb_bsoftlimit = v1_qbtos(d->dqb_bsoftlimit);
+	m->dqb_curspace = v1_qbtos(d->dqb_curblocks);
 	m->dqb_itime = d->dqb_itime;
 	m->dqb_btime = d->dqb_btime;
 }
@@ -31,9 +44,9 @@ static void v1_mem2disk_dqblk(struct v1_disk_dqblk *d, struct mem_dqblk *m)
 	d->dqb_ihardlimit = m->dqb_ihardlimit;
 	d->dqb_isoftlimit = m->dqb_isoftlimit;
 	d->dqb_curinodes = m->dqb_curinodes;
-	d->dqb_bhardlimit = m->dqb_bhardlimit;
-	d->dqb_bsoftlimit = m->dqb_bsoftlimit;
-	d->dqb_curblocks = toqb(m->dqb_curspace);
+	d->dqb_bhardlimit = v1_stoqb(m->dqb_bhardlimit);
+	d->dqb_bsoftlimit = v1_stoqb(m->dqb_bsoftlimit);
+	d->dqb_curblocks = v1_stoqb(m->dqb_curspace);
 	d->dqb_itime = m->dqb_itime;
 	d->dqb_btime = m->dqb_btime;
 }
diff --git a/fs/quota_v2.c b/fs/quota_v2.c
index b53827dc02d9..51c4717f7c6a 100644
--- a/fs/quota_v2.c
+++ b/fs/quota_v2.c
@@ -26,6 +26,19 @@ typedef char *dqbuf_t;
 #define GETIDINDEX(id, depth) (((id) >> ((V2_DQTREEDEPTH-(depth)-1)*8)) & 0xff)
 #define GETENTRIES(buf) ((struct v2_disk_dqblk *)(((char *)buf)+sizeof(struct v2_disk_dqdbheader)))
 
+#define QUOTABLOCK_BITS 10
+#define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS)
+
+static inline qsize_t v2_stoqb(qsize_t space)
+{
+	return (space + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS;
+}
+
+static inline qsize_t v2_qbtos(qsize_t blocks)
+{
+	return blocks << QUOTABLOCK_BITS;
+}
+
 /* Check whether given file is really vfsv0 quotafile */
 static int v2_check_quota_file(struct super_block *sb, int type)
 {
@@ -104,8 +117,8 @@ static void disk2memdqb(struct mem_dqblk *m, struct v2_disk_dqblk *d)
 	m->dqb_isoftlimit = le32_to_cpu(d->dqb_isoftlimit);
 	m->dqb_curinodes = le32_to_cpu(d->dqb_curinodes);
 	m->dqb_itime = le64_to_cpu(d->dqb_itime);
-	m->dqb_bhardlimit = le32_to_cpu(d->dqb_bhardlimit);
-	m->dqb_bsoftlimit = le32_to_cpu(d->dqb_bsoftlimit);
+	m->dqb_bhardlimit = v2_qbtos(le32_to_cpu(d->dqb_bhardlimit));
+	m->dqb_bsoftlimit = v2_qbtos(le32_to_cpu(d->dqb_bsoftlimit));
 	m->dqb_curspace = le64_to_cpu(d->dqb_curspace);
 	m->dqb_btime = le64_to_cpu(d->dqb_btime);
 }
@@ -116,8 +129,8 @@ static void mem2diskdqb(struct v2_disk_dqblk *d, struct mem_dqblk *m, qid_t id)
 	d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit);
 	d->dqb_curinodes = cpu_to_le32(m->dqb_curinodes);
 	d->dqb_itime = cpu_to_le64(m->dqb_itime);
-	d->dqb_bhardlimit = cpu_to_le32(m->dqb_bhardlimit);
-	d->dqb_bsoftlimit = cpu_to_le32(m->dqb_bsoftlimit);
+	d->dqb_bhardlimit = cpu_to_le32(v2_qbtos(m->dqb_bhardlimit));
+	d->dqb_bsoftlimit = cpu_to_le32(v2_qbtos(m->dqb_bsoftlimit));
 	d->dqb_curspace = cpu_to_le64(m->dqb_curspace);
 	d->dqb_btime = cpu_to_le64(m->dqb_btime);
 	d->dqb_id = cpu_to_le32(id);
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 3ce708c2cb3c..9ea468363f9f 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -39,15 +39,6 @@
 #define __DQUOT_VERSION__	"dquot_6.5.1"
 #define __DQUOT_NUM_VERSION__	6*10000+5*100+1
 
-/* Size of blocks in which are counted size limits */
-#define QUOTABLOCK_BITS 10
-#define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS)
-
-/* Conversion routines from and to quota blocks */
-#define qb2kb(x) ((x) << (QUOTABLOCK_BITS-10))
-#define kb2qb(x) ((x) >> (QUOTABLOCK_BITS-10))
-#define toqb(x) (((x) + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS)
-
 #define MAXQUOTAS 2
 #define USRQUOTA  0		/* element used for user quotas */
 #define GRPQUOTA  1		/* element used for group quotas */
@@ -80,6 +71,11 @@
 #define Q_GETQUOTA 0x800007	/* get user quota structure */
 #define Q_SETQUOTA 0x800008	/* set user quota structure */
 
+/* Size of block in which space limits are passed through the quota
+ * interface */
+#define QIF_DQBLKSIZE_BITS 10
+#define QIF_DQBLKSIZE (1 << QIF_DQBLKSIZE_BITS)
+
 /*
  * Quota structure used for communication with userspace via quotactl
  * Following flags are used to specify which fields are valid
@@ -187,12 +183,12 @@ extern spinlock_t dq_data_lock;
  * Data for one user/group kept in memory
  */
 struct mem_dqblk {
-	__u32 dqb_bhardlimit;	/* absolute limit on disk blks alloc */
-	__u32 dqb_bsoftlimit;	/* preferred limit on disk blks */
+	qsize_t dqb_bhardlimit;	/* absolute limit on disk blks alloc */
+	qsize_t dqb_bsoftlimit;	/* preferred limit on disk blks */
 	qsize_t dqb_curspace;	/* current used space */
-	__u32 dqb_ihardlimit;	/* absolute limit on allocated inodes */
-	__u32 dqb_isoftlimit;	/* preferred inode limit */
-	__u32 dqb_curinodes;	/* current # allocated inodes */
+	qsize_t dqb_ihardlimit;	/* absolute limit on allocated inodes */
+	qsize_t dqb_isoftlimit;	/* preferred inode limit */
+	qsize_t dqb_curinodes;	/* current # allocated inodes */
 	time_t dqb_btime;	/* time limit for excessive disk use */
 	time_t dqb_itime;	/* time limit for excessive inode use */
 };
@@ -287,9 +283,9 @@ struct dquot_operations {
 	int (*initialize) (struct inode *, int);
 	int (*drop) (struct inode *);
 	int (*alloc_space) (struct inode *, qsize_t, int);
-	int (*alloc_inode) (const struct inode *, unsigned long);
+	int (*alloc_inode) (const struct inode *, qsize_t);
 	int (*free_space) (struct inode *, qsize_t);
-	int (*free_inode) (const struct inode *, unsigned long);
+	int (*free_inode) (const struct inode *, qsize_t);
 	int (*transfer) (struct inode *, struct iattr *);
 	int (*write_dquot) (struct dquot *);		/* Ordinary dquot write */
 	struct dquot *(*alloc_dquot)(struct super_block *, int);	/* Allocate memory for new dquot */
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index a558a4c1d35a..adcc7ba3accb 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -26,10 +26,10 @@ int dquot_initialize(struct inode *inode, int type);
 int dquot_drop(struct inode *inode);
 
 int dquot_alloc_space(struct inode *inode, qsize_t number, int prealloc);
-int dquot_alloc_inode(const struct inode *inode, unsigned long number);
+int dquot_alloc_inode(const struct inode *inode, qsize_t number);
 
 int dquot_free_space(struct inode *inode, qsize_t number);
-int dquot_free_inode(const struct inode *inode, unsigned long number);
+int dquot_free_inode(const struct inode *inode, qsize_t number);
 
 int dquot_transfer(struct inode *inode, struct iattr *iattr);
 int dquot_commit(struct dquot *dquot);
-- 
cgit v1.2.3-70-g09d2


From e4bc7b4b7ff783779b6928d55a9308910bf180a3 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 20 Aug 2008 16:21:01 +0200
Subject: quota: Make _SUSPENDED just a flag

Upto now, DQUOT_USR_SUSPENDED behaved like a state - i.e., either quota
was enabled or suspended or none. Now allowed states are 0, ENABLED,
ENABLED | SUSPENDED. This will be useful later when we implement separate
enabling of quota usage tracking and limits enforcement because we need to
keep track of a state which has been suspended.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c               | 10 ++++++----
 include/linux/quotaops.h |  6 ++++--
 2 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index c88330602ddd..22340c610e1a 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -1570,18 +1570,20 @@ static inline void reset_enable_flags(struct quota_info *dqopt, int type,
 {
 	switch (type) {
 		case USRQUOTA:
-			dqopt->flags &= ~DQUOT_USR_ENABLED;
 			if (remount)
 				dqopt->flags |= DQUOT_USR_SUSPENDED;
-			else
+			else {
+				dqopt->flags &= ~DQUOT_USR_ENABLED;
 				dqopt->flags &= ~DQUOT_USR_SUSPENDED;
+			}
 			break;
 		case GRPQUOTA:
-			dqopt->flags &= ~DQUOT_GRP_ENABLED;
 			if (remount)
 				dqopt->flags |= DQUOT_GRP_SUSPENDED;
-			else
+			else {
+				dqopt->flags &= ~DQUOT_GRP_ENABLED;
 				dqopt->flags &= ~DQUOT_GRP_SUSPENDED;
+			}
 			break;
 	}
 }
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index adcc7ba3accb..ffd97071cd1e 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -67,8 +67,10 @@ static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type)
 static inline int sb_has_quota_enabled(struct super_block *sb, int type)
 {
 	if (type == USRQUOTA)
-		return sb_dqopt(sb)->flags & DQUOT_USR_ENABLED;
-	return sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED;
+		return (sb_dqopt(sb)->flags & DQUOT_USR_ENABLED)
+			&& !(sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED);
+	return (sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED)
+		&& !(sb_dqopt(sb)->flags & DQUOT_GROUP_SUSPENDED);
 }
 
 static inline int sb_any_quota_enabled(struct super_block *sb)
-- 
cgit v1.2.3-70-g09d2


From f55abc0fb9c3189de3da829adf3220322c0da43e Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 20 Aug 2008 17:50:32 +0200
Subject: quota: Allow to separately enable quota accounting and enforcing
 limits

Split DQUOT_USR_ENABLED (and DQUOT_GRP_ENABLED) into DQUOT_USR_USAGE_ENABLED
and DQUOT_USR_LIMITS_ENABLED. This way we are able to separately enable /
disable whether we should:
1) ignore quotas completely
2) just keep uptodate information about usage
3) actually enforce quota limits

This is going to be useful when quota is treated as filesystem metadata - we
then want to keep quota information uptodate all the time and just enable /
disable limits enforcement.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c               | 222 +++++++++++++++++++++++++++++------------------
 fs/quota.c               |   8 +-
 include/linux/quota.h    |  30 ++++++-
 include/linux/quotaops.h |  91 ++++++++++++++-----
 4 files changed, 239 insertions(+), 112 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index 22340c610e1a..7569633efe0e 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -489,7 +489,7 @@ int vfs_quota_sync(struct super_block *sb, int type)
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		if (type != -1 && cnt != type)
 			continue;
-		if (!sb_has_quota_enabled(sb, cnt))
+		if (!sb_has_quota_active(sb, cnt))
 			continue;
 		spin_lock(&dq_list_lock);
 		dirty = &dqopt->info[cnt].dqi_dirty_list;
@@ -514,8 +514,8 @@ int vfs_quota_sync(struct super_block *sb, int type)
 	}
 
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
-		if ((cnt == type || type == -1) && sb_has_quota_enabled(sb, cnt)
-			&& info_dirty(&dqopt->info[cnt]))
+		if ((cnt == type || type == -1) && sb_has_quota_active(sb, cnt)
+		    && info_dirty(&dqopt->info[cnt]))
 			sb->dq_op->write_info(sb, cnt);
 	spin_lock(&dq_list_lock);
 	dqstats.syncs++;
@@ -594,7 +594,7 @@ we_slept:
 		/* We have more than one user... nothing to do */
 		atomic_dec(&dquot->dq_count);
 		/* Releasing dquot during quotaoff phase? */
-		if (!sb_has_quota_enabled(dquot->dq_sb, dquot->dq_type) &&
+		if (!sb_has_quota_active(dquot->dq_sb, dquot->dq_type) &&
 		    atomic_read(&dquot->dq_count) == 1)
 			wake_up(&dquot->dq_wait_unused);
 		spin_unlock(&dq_list_lock);
@@ -670,7 +670,7 @@ static struct dquot *dqget(struct super_block *sb, unsigned int id, int type)
 	unsigned int hashent = hashfn(sb, id, type);
 	struct dquot *dquot, *empty = NODQUOT;
 
-        if (!sb_has_quota_enabled(sb, type))
+        if (!sb_has_quota_active(sb, type))
 		return NODQUOT;
 we_slept:
 	spin_lock(&dq_list_lock);
@@ -1041,7 +1041,8 @@ static inline char ignore_hardlimit(struct dquot *dquot)
 static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
 {
 	*warntype = QUOTA_NL_NOWARN;
-	if (test_bit(DQ_FAKE_B, &dquot->dq_flags))
+	if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_type) ||
+	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
 		return QUOTA_OK;
 
 	if (dquot->dq_dqb.dqb_ihardlimit &&
@@ -1073,7 +1074,8 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, char *warntype)
 static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *warntype)
 {
 	*warntype = QUOTA_NL_NOWARN;
-	if (test_bit(DQ_FAKE_B, &dquot->dq_flags))
+	if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_type) ||
+	    test_bit(DQ_FAKE_B, &dquot->dq_flags))
 		return QUOTA_OK;
 
 	if (dquot->dq_dqb.dqb_bhardlimit &&
@@ -1114,7 +1116,8 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, char *war
 static int info_idq_free(struct dquot *dquot, qsize_t inodes)
 {
 	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) ||
-	    dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit)
+	    dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit ||
+	    !sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_type))
 		return QUOTA_NL_NOWARN;
 
 	if (dquot->dq_dqb.dqb_curinodes - inodes <= dquot->dq_dqb.dqb_isoftlimit)
@@ -1508,7 +1511,7 @@ warn_put_all:
 /* Wrapper for transferring ownership of an inode */
 int vfs_dq_transfer(struct inode *inode, struct iattr *iattr)
 {
-	if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode)) {
+	if (sb_any_quota_active(inode->i_sb) && !IS_NOQUOTA(inode)) {
 		vfs_dq_init(inode);
 		if (inode->i_sb->dq_op->transfer(inode, iattr) == NO_QUOTA)
 			return 1;
@@ -1551,53 +1554,22 @@ struct dquot_operations dquot_operations = {
 	.destroy_dquot	= dquot_destroy,
 };
 
-static inline void set_enable_flags(struct quota_info *dqopt, int type)
-{
-	switch (type) {
-		case USRQUOTA:
-			dqopt->flags |= DQUOT_USR_ENABLED;
-			dqopt->flags &= ~DQUOT_USR_SUSPENDED;
-			break;
-		case GRPQUOTA:
-			dqopt->flags |= DQUOT_GRP_ENABLED;
-			dqopt->flags &= ~DQUOT_GRP_SUSPENDED;
-			break;
-	}
-}
-
-static inline void reset_enable_flags(struct quota_info *dqopt, int type,
-				      int remount)
-{
-	switch (type) {
-		case USRQUOTA:
-			if (remount)
-				dqopt->flags |= DQUOT_USR_SUSPENDED;
-			else {
-				dqopt->flags &= ~DQUOT_USR_ENABLED;
-				dqopt->flags &= ~DQUOT_USR_SUSPENDED;
-			}
-			break;
-		case GRPQUOTA:
-			if (remount)
-				dqopt->flags |= DQUOT_GRP_SUSPENDED;
-			else {
-				dqopt->flags &= ~DQUOT_GRP_ENABLED;
-				dqopt->flags &= ~DQUOT_GRP_SUSPENDED;
-			}
-			break;
-	}
-}
-
-
 /*
  * Turn quota off on a device. type == -1 ==> quotaoff for all types (umount)
  */
-int vfs_quota_off(struct super_block *sb, int type, int remount)
+int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags)
 {
 	int cnt, ret = 0;
 	struct quota_info *dqopt = sb_dqopt(sb);
 	struct inode *toputinode[MAXQUOTAS];
 
+	/* Cannot turn off usage accounting without turning off limits, or
+	 * suspend quotas and simultaneously turn quotas off. */
+	if ((flags & DQUOT_USAGE_ENABLED && !(flags & DQUOT_LIMITS_ENABLED))
+	    || (flags & DQUOT_SUSPENDED && flags & (DQUOT_LIMITS_ENABLED |
+	    DQUOT_USAGE_ENABLED)))
+		return -EINVAL;
+
 	/* We need to serialize quota_off() for device */
 	mutex_lock(&dqopt->dqonoff_mutex);
 
@@ -1606,7 +1578,7 @@ int vfs_quota_off(struct super_block *sb, int type, int remount)
 	 * sometimes we are called when fill_super() failed and calling
 	 * sync_fs() in such cases does no good.
 	 */
-	if (!sb_any_quota_enabled(sb) && !sb_any_quota_suspended(sb)) {
+	if (!sb_any_quota_loaded(sb)) {
 		mutex_unlock(&dqopt->dqonoff_mutex);
 		return 0;
 	}
@@ -1614,17 +1586,28 @@ int vfs_quota_off(struct super_block *sb, int type, int remount)
 		toputinode[cnt] = NULL;
 		if (type != -1 && cnt != type)
 			continue;
-		/* If we keep inodes of quota files after remount and quotaoff
-		 * is called, drop kept inodes. */
-		if (!remount && sb_has_quota_suspended(sb, cnt)) {
-			iput(dqopt->files[cnt]);
-			dqopt->files[cnt] = NULL;
-			reset_enable_flags(dqopt, cnt, 0);
+		if (!sb_has_quota_loaded(sb, cnt))
 			continue;
+
+		if (flags & DQUOT_SUSPENDED) {
+			dqopt->flags |=
+				dquot_state_flag(DQUOT_SUSPENDED, cnt);
+		} else {
+			dqopt->flags &= ~dquot_state_flag(flags, cnt);
+			/* Turning off suspended quotas? */
+			if (!sb_has_quota_loaded(sb, cnt) &&
+			    sb_has_quota_suspended(sb, cnt)) {
+				dqopt->flags &=	~dquot_state_flag(
+							DQUOT_SUSPENDED, cnt);
+				iput(dqopt->files[cnt]);
+				dqopt->files[cnt] = NULL;
+				continue;
+			}
 		}
-		if (!sb_has_quota_enabled(sb, cnt))
+
+		/* We still have to keep quota loaded? */
+		if (sb_has_quota_loaded(sb, cnt) && !(flags & DQUOT_SUSPENDED))
 			continue;
-		reset_enable_flags(dqopt, cnt, remount);
 
 		/* Note: these are blocking operations */
 		drop_dquot_ref(sb, cnt);
@@ -1640,7 +1623,7 @@ int vfs_quota_off(struct super_block *sb, int type, int remount)
 		put_quota_format(dqopt->info[cnt].dqi_format);
 
 		toputinode[cnt] = dqopt->files[cnt];
-		if (!remount)
+		if (!sb_has_quota_loaded(sb, cnt))
 			dqopt->files[cnt] = NULL;
 		dqopt->info[cnt].dqi_flags = 0;
 		dqopt->info[cnt].dqi_igrace = 0;
@@ -1663,7 +1646,7 @@ int vfs_quota_off(struct super_block *sb, int type, int remount)
 			mutex_lock(&dqopt->dqonoff_mutex);
 			/* If quota was reenabled in the meantime, we have
 			 * nothing to do */
-			if (!sb_has_quota_enabled(sb, cnt)) {
+			if (!sb_has_quota_loaded(sb, cnt)) {
 				mutex_lock_nested(&toputinode[cnt]->i_mutex, I_MUTEX_QUOTA);
 				toputinode[cnt]->i_flags &= ~(S_IMMUTABLE |
 				  S_NOATIME | S_NOQUOTA);
@@ -1673,10 +1656,13 @@ int vfs_quota_off(struct super_block *sb, int type, int remount)
 			}
 			mutex_unlock(&dqopt->dqonoff_mutex);
 			/* On remount RO, we keep the inode pointer so that we
-			 * can reenable quota on the subsequent remount RW.
-			 * But we have better not keep inode pointer when there
-			 * is pending delete on the quota file... */
-			if (!remount)
+			 * can reenable quota on the subsequent remount RW. We
+			 * have to check 'flags' variable and not use sb_has_
+			 * function because another quotaon / quotaoff could
+			 * change global state before we got here. We refuse
+			 * to suspend quotas when there is pending delete on
+			 * the quota file... */
+			if (!(flags & DQUOT_SUSPENDED))
 				iput(toputinode[cnt]);
 			else if (!toputinode[cnt]->i_nlink)
 				ret = -EBUSY;
@@ -1686,12 +1672,22 @@ int vfs_quota_off(struct super_block *sb, int type, int remount)
 	return ret;
 }
 
+int vfs_quota_off(struct super_block *sb, int type, int remount)
+{
+	return vfs_quota_disable(sb, type, remount ? DQUOT_SUSPENDED :
+				 (DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED));
+}
+
 /*
  *	Turn quotas on on a device
  */
 
-/* Helper function when we already have the inode */
-static int vfs_quota_on_inode(struct inode *inode, int type, int format_id)
+/*
+ * Helper function to turn quotas on when we already have the inode of
+ * quota file and no quota information is loaded.
+ */
+static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
+	unsigned int flags)
 {
 	struct quota_format_type *fmt = find_quota_format(format_id);
 	struct super_block *sb = inode->i_sb;
@@ -1713,6 +1709,11 @@ static int vfs_quota_on_inode(struct inode *inode, int type, int format_id)
 		error = -EINVAL;
 		goto out_fmt;
 	}
+	/* Usage always has to be set... */
+	if (!(flags & DQUOT_USAGE_ENABLED)) {
+		error = -EINVAL;
+		goto out_fmt;
+	}
 
 	/* As we bypass the pagecache we must now flush the inode so that
 	 * we see all the changes from userspace... */
@@ -1721,8 +1722,7 @@ static int vfs_quota_on_inode(struct inode *inode, int type, int format_id)
 	invalidate_bdev(sb->s_bdev);
 	mutex_lock(&inode->i_mutex);
 	mutex_lock(&dqopt->dqonoff_mutex);
-	if (sb_has_quota_enabled(sb, type) ||
-			sb_has_quota_suspended(sb, type)) {
+	if (sb_has_quota_loaded(sb, type)) {
 		error = -EBUSY;
 		goto out_lock;
 	}
@@ -1754,7 +1754,7 @@ static int vfs_quota_on_inode(struct inode *inode, int type, int format_id)
 	}
 	mutex_unlock(&dqopt->dqio_mutex);
 	mutex_unlock(&inode->i_mutex);
-	set_enable_flags(dqopt, type);
+	dqopt->flags |= dquot_state_flag(flags, type);
 
 	add_dquot_ref(sb, type);
 	mutex_unlock(&dqopt->dqonoff_mutex);
@@ -1787,20 +1787,23 @@ static int vfs_quota_on_remount(struct super_block *sb, int type)
 	struct quota_info *dqopt = sb_dqopt(sb);
 	struct inode *inode;
 	int ret;
+	unsigned int flags;
 
 	mutex_lock(&dqopt->dqonoff_mutex);
 	if (!sb_has_quota_suspended(sb, type)) {
 		mutex_unlock(&dqopt->dqonoff_mutex);
 		return 0;
 	}
-	BUG_ON(sb_has_quota_enabled(sb, type));
-
 	inode = dqopt->files[type];
 	dqopt->files[type] = NULL;
-	reset_enable_flags(dqopt, type, 0);
+	flags = dqopt->flags & dquot_state_flag(DQUOT_USAGE_ENABLED |
+						DQUOT_LIMITS_ENABLED, type);
+	dqopt->flags &= ~dquot_state_flag(DQUOT_STATE_FLAGS, type);
 	mutex_unlock(&dqopt->dqonoff_mutex);
 
-	ret = vfs_quota_on_inode(inode, type, dqopt->info[type].dqi_fmt_id);
+	flags = dquot_generic_flag(flags, type);
+	ret = vfs_load_quota_inode(inode, type, dqopt->info[type].dqi_fmt_id,
+				   flags);
 	iput(inode);
 
 	return ret;
@@ -1816,12 +1819,12 @@ int vfs_quota_on_path(struct super_block *sb, int type, int format_id,
 	if (path->mnt->mnt_sb != sb)
 		error = -EXDEV;
 	else
-		error = vfs_quota_on_inode(path->dentry->d_inode, type,
-					   format_id);
+		error = vfs_load_quota_inode(path->dentry->d_inode, type,
+					     format_id, DQUOT_USAGE_ENABLED |
+					     DQUOT_LIMITS_ENABLED);
 	return error;
 }
 
-/* Actual function called from quotactl() */
 int vfs_quota_on(struct super_block *sb, int type, int format_id, char *name,
 		 int remount)
 {
@@ -1839,6 +1842,50 @@ int vfs_quota_on(struct super_block *sb, int type, int format_id, char *name,
 	return error;
 }
 
+/*
+ * More powerful function for turning on quotas allowing setting
+ * of individual quota flags
+ */
+int vfs_quota_enable(struct inode *inode, int type, int format_id,
+		unsigned int flags)
+{
+	int ret = 0;
+	struct super_block *sb = inode->i_sb;
+	struct quota_info *dqopt = sb_dqopt(sb);
+
+	/* Just unsuspend quotas? */
+	if (flags & DQUOT_SUSPENDED)
+		return vfs_quota_on_remount(sb, type);
+	if (!flags)
+		return 0;
+	/* Just updating flags needed? */
+	if (sb_has_quota_loaded(sb, type)) {
+		mutex_lock(&dqopt->dqonoff_mutex);
+		/* Now do a reliable test... */
+		if (!sb_has_quota_loaded(sb, type)) {
+			mutex_unlock(&dqopt->dqonoff_mutex);
+			goto load_quota;
+		}
+		if (flags & DQUOT_USAGE_ENABLED &&
+		    sb_has_quota_usage_enabled(sb, type)) {
+			ret = -EBUSY;
+			goto out_lock;
+		}
+		if (flags & DQUOT_LIMITS_ENABLED &&
+		    sb_has_quota_limits_enabled(sb, type)) {
+			ret = -EBUSY;
+			goto out_lock;
+		}
+		sb_dqopt(sb)->flags |= dquot_state_flag(flags, type);
+out_lock:
+		mutex_unlock(&dqopt->dqonoff_mutex);
+		return ret;
+	}
+
+load_quota:
+	return vfs_load_quota_inode(inode, type, format_id, flags);
+}
+
 /*
  * This function is used when filesystem needs to initialize quotas
  * during mount time.
@@ -1860,7 +1907,8 @@ int vfs_quota_on_mount(struct super_block *sb, char *qf_name,
 
 	error = security_quota_on(dentry);
 	if (!error)
-		error = vfs_quota_on_inode(dentry->d_inode, type, format_id);
+		error = vfs_load_quota_inode(dentry->d_inode, type, format_id,
+				DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
 
 out:
 	dput(dentry);
@@ -1997,12 +2045,14 @@ int vfs_set_dqblk(struct super_block *sb, int type, qid_t id, struct if_dqblk *d
 	int rc;
 
 	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
-	if (!(dquot = dqget(sb, id, type))) {
-		mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
-		return -ESRCH;
+	dquot = dqget(sb, id, type);
+	if (!dquot) {
+		rc = -ESRCH;
+		goto out;
 	}
 	rc = do_set_dqblk(dquot, di);
 	dqput(dquot);
+out:
 	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
 	return rc;
 }
@@ -2013,7 +2063,7 @@ int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
 	struct mem_dqinfo *mi;
   
 	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
-	if (!sb_has_quota_enabled(sb, type)) {
+	if (!sb_has_quota_active(sb, type)) {
 		mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
 		return -ESRCH;
 	}
@@ -2032,11 +2082,12 @@ int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
 int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
 {
 	struct mem_dqinfo *mi;
+	int err = 0;
 
 	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
-	if (!sb_has_quota_enabled(sb, type)) {
-		mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
-		return -ESRCH;
+	if (!sb_has_quota_active(sb, type)) {
+		err = -ESRCH;
+		goto out;
 	}
 	mi = sb_dqopt(sb)->info + type;
 	spin_lock(&dq_data_lock);
@@ -2050,8 +2101,9 @@ int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii)
 	mark_info_dirty(sb, type);
 	/* Force write to disk */
 	sb->dq_op->write_info(sb, type);
+out:
 	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
-	return 0;
+	return err;
 }
 
 struct quotactl_ops vfs_quotactl_ops = {
@@ -2213,9 +2265,11 @@ EXPORT_SYMBOL(register_quota_format);
 EXPORT_SYMBOL(unregister_quota_format);
 EXPORT_SYMBOL(dqstats);
 EXPORT_SYMBOL(dq_data_lock);
+EXPORT_SYMBOL(vfs_quota_enable);
 EXPORT_SYMBOL(vfs_quota_on);
 EXPORT_SYMBOL(vfs_quota_on_path);
 EXPORT_SYMBOL(vfs_quota_on_mount);
+EXPORT_SYMBOL(vfs_quota_disable);
 EXPORT_SYMBOL(vfs_quota_off);
 EXPORT_SYMBOL(vfs_quota_sync);
 EXPORT_SYMBOL(vfs_get_dqinfo);
diff --git a/fs/quota.c b/fs/quota.c
index b7fe44e01618..8678d9f35ee9 100644
--- a/fs/quota.c
+++ b/fs/quota.c
@@ -73,7 +73,7 @@ static int generic_quotactl_valid(struct super_block *sb, int type, int cmd, qid
 		case Q_SETQUOTA:
 		case Q_GETQUOTA:
 			/* This is just informative test so we are satisfied without a lock */
-			if (!sb_has_quota_enabled(sb, type))
+			if (!sb_has_quota_active(sb, type))
 				return -ESRCH;
 	}
 
@@ -175,7 +175,7 @@ static void quota_sync_sb(struct super_block *sb, int type)
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		if (type != -1 && cnt != type)
 			continue;
-		if (!sb_has_quota_enabled(sb, cnt))
+		if (!sb_has_quota_active(sb, cnt))
 			continue;
 		mutex_lock_nested(&sb_dqopt(sb)->files[cnt]->i_mutex, I_MUTEX_QUOTA);
 		truncate_inode_pages(&sb_dqopt(sb)->files[cnt]->i_data, 0);
@@ -201,7 +201,7 @@ restart:
 		for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 			if (type != -1 && type != cnt)
 				continue;
-			if (!sb_has_quota_enabled(sb, cnt))
+			if (!sb_has_quota_active(sb, cnt))
 				continue;
 			if (!info_dirty(&sb_dqopt(sb)->info[cnt]) &&
 			    list_empty(&sb_dqopt(sb)->info[cnt].dqi_dirty_list))
@@ -245,7 +245,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, void
 			__u32 fmt;
 
 			down_read(&sb_dqopt(sb)->dqptr_sem);
-			if (!sb_has_quota_enabled(sb, type)) {
+			if (!sb_has_quota_active(sb, type)) {
 				up_read(&sb_dqopt(sb)->dqptr_sem);
 				return -ESRCH;
 			}
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 9ea468363f9f..93717abcd35b 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -318,12 +318,34 @@ struct quota_format_type {
 	struct quota_format_type *qf_next;
 };
 
-#define DQUOT_USR_ENABLED	0x01		/* User diskquotas enabled */
-#define DQUOT_GRP_ENABLED	0x02		/* Group diskquotas enabled */
-#define DQUOT_USR_SUSPENDED	0x04		/* User diskquotas are off, but
+/* Quota state flags - they actually come in two flavors - for users and groups */
+enum {
+	_DQUOT_USAGE_ENABLED = 0,		/* Track disk usage for users */
+	_DQUOT_LIMITS_ENABLED,			/* Enforce quota limits for users */
+	_DQUOT_SUSPENDED,			/* User diskquotas are off, but
 						 * we have necessary info in
 						 * memory to turn them on */
-#define DQUOT_GRP_SUSPENDED	0x08		/* The same for group quotas */
+	_DQUOT_STATE_FLAGS
+};
+#define DQUOT_USAGE_ENABLED	(1 << _DQUOT_USAGE_ENABLED)
+#define DQUOT_LIMITS_ENABLED	(1 << _DQUOT_LIMITS_ENABLED)
+#define DQUOT_SUSPENDED		(1 << _DQUOT_SUSPENDED)
+#define DQUOT_STATE_FLAGS	(DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED | \
+				 DQUOT_SUSPENDED)
+
+static inline unsigned int dquot_state_flag(unsigned int flags, int type)
+{
+	if (type == USRQUOTA)
+		return flags;
+	return flags << _DQUOT_STATE_FLAGS;
+}
+
+static inline unsigned int dquot_generic_flag(unsigned int flags, int type)
+{
+	if (type == USRQUOTA)
+		return flags;
+	return flags >> _DQUOT_STATE_FLAGS;
+}
 
 struct quota_info {
 	unsigned int flags;			/* Flags for diskquotas on this device */
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index ffd97071cd1e..3b3346fa657c 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -40,11 +40,14 @@ int dquot_mark_dquot_dirty(struct dquot *dquot);
 
 int vfs_quota_on(struct super_block *sb, int type, int format_id,
  	char *path, int remount);
+int vfs_quota_enable(struct inode *inode, int type, int format_id,
+	unsigned int flags);
 int vfs_quota_on_path(struct super_block *sb, int type, int format_id,
  	struct path *path);
 int vfs_quota_on_mount(struct super_block *sb, char *qf_name,
  	int format_id, int type);
 int vfs_quota_off(struct super_block *sb, int type, int remount);
+int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags);
 int vfs_quota_sync(struct super_block *sb, int type);
 int vfs_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int vfs_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
@@ -64,26 +67,22 @@ static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type)
  * Functions for checking status of quota
  */
 
-static inline int sb_has_quota_enabled(struct super_block *sb, int type)
+static inline int sb_has_quota_usage_enabled(struct super_block *sb, int type)
 {
-	if (type == USRQUOTA)
-		return (sb_dqopt(sb)->flags & DQUOT_USR_ENABLED)
-			&& !(sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED);
-	return (sb_dqopt(sb)->flags & DQUOT_GRP_ENABLED)
-		&& !(sb_dqopt(sb)->flags & DQUOT_GROUP_SUSPENDED);
+	return sb_dqopt(sb)->flags &
+				dquot_state_flag(DQUOT_USAGE_ENABLED, type);
 }
 
-static inline int sb_any_quota_enabled(struct super_block *sb)
+static inline int sb_has_quota_limits_enabled(struct super_block *sb, int type)
 {
-	return sb_has_quota_enabled(sb, USRQUOTA) ||
-		sb_has_quota_enabled(sb, GRPQUOTA);
+	return sb_dqopt(sb)->flags &
+				dquot_state_flag(DQUOT_LIMITS_ENABLED, type);
 }
 
 static inline int sb_has_quota_suspended(struct super_block *sb, int type)
 {
-	if (type == USRQUOTA)
-		return sb_dqopt(sb)->flags & DQUOT_USR_SUSPENDED;
-	return sb_dqopt(sb)->flags & DQUOT_GRP_SUSPENDED;
+	return sb_dqopt(sb)->flags &
+				dquot_state_flag(DQUOT_SUSPENDED, type);
 }
 
 static inline int sb_any_quota_suspended(struct super_block *sb)
@@ -92,6 +91,34 @@ static inline int sb_any_quota_suspended(struct super_block *sb)
 		sb_has_quota_suspended(sb, GRPQUOTA);
 }
 
+/* Does kernel know about any quota information for given sb + type? */
+static inline int sb_has_quota_loaded(struct super_block *sb, int type)
+{
+	/* Currently if anything is on, then quota usage is on as well */
+	return sb_has_quota_usage_enabled(sb, type);
+}
+
+static inline int sb_any_quota_loaded(struct super_block *sb)
+{
+	return sb_has_quota_loaded(sb, USRQUOTA) ||
+		sb_has_quota_loaded(sb, GRPQUOTA);
+}
+
+static inline int sb_has_quota_active(struct super_block *sb, int type)
+{
+	return sb_has_quota_loaded(sb, type) &&
+	       !sb_has_quota_suspended(sb, type);
+}
+
+static inline int sb_any_quota_active(struct super_block *sb)
+{
+	return sb_has_quota_active(sb, USRQUOTA) ||
+	       sb_has_quota_active(sb, GRPQUOTA);
+}
+
+/* For backward compatibility until we remove all users */
+#define sb_any_quota_enabled(sb) sb_any_quota_active(sb)
+
 /*
  * Operations supported for diskquotas.
  */
@@ -106,7 +133,7 @@ extern struct quotactl_ops vfs_quotactl_ops;
 static inline void vfs_dq_init(struct inode *inode)
 {
 	BUG_ON(!inode->i_sb);
-	if (sb_any_quota_enabled(inode->i_sb) && !IS_NOQUOTA(inode))
+	if (sb_any_quota_active(inode->i_sb) && !IS_NOQUOTA(inode))
 		inode->i_sb->dq_op->initialize(inode, -1);
 }
 
@@ -114,7 +141,7 @@ static inline void vfs_dq_init(struct inode *inode)
  * a transaction (deadlocks possible otherwise) */
 static inline int vfs_dq_prealloc_space_nodirty(struct inode *inode, qsize_t nr)
 {
-	if (sb_any_quota_enabled(inode->i_sb)) {
+	if (sb_any_quota_active(inode->i_sb)) {
 		/* Used space is updated in alloc_space() */
 		if (inode->i_sb->dq_op->alloc_space(inode, nr, 1) == NO_QUOTA)
 			return 1;
@@ -134,7 +161,7 @@ static inline int vfs_dq_prealloc_space(struct inode *inode, qsize_t nr)
 
 static inline int vfs_dq_alloc_space_nodirty(struct inode *inode, qsize_t nr)
 {
-	if (sb_any_quota_enabled(inode->i_sb)) {
+	if (sb_any_quota_active(inode->i_sb)) {
 		/* Used space is updated in alloc_space() */
 		if (inode->i_sb->dq_op->alloc_space(inode, nr, 0) == NO_QUOTA)
 			return 1;
@@ -154,7 +181,7 @@ static inline int vfs_dq_alloc_space(struct inode *inode, qsize_t nr)
 
 static inline int vfs_dq_alloc_inode(struct inode *inode)
 {
-	if (sb_any_quota_enabled(inode->i_sb)) {
+	if (sb_any_quota_active(inode->i_sb)) {
 		vfs_dq_init(inode);
 		if (inode->i_sb->dq_op->alloc_inode(inode, 1) == NO_QUOTA)
 			return 1;
@@ -164,7 +191,7 @@ static inline int vfs_dq_alloc_inode(struct inode *inode)
 
 static inline void vfs_dq_free_space_nodirty(struct inode *inode, qsize_t nr)
 {
-	if (sb_any_quota_enabled(inode->i_sb))
+	if (sb_any_quota_active(inode->i_sb))
 		inode->i_sb->dq_op->free_space(inode, nr);
 	else
 		inode_sub_bytes(inode, nr);
@@ -178,7 +205,7 @@ static inline void vfs_dq_free_space(struct inode *inode, qsize_t nr)
 
 static inline void vfs_dq_free_inode(struct inode *inode)
 {
-	if (sb_any_quota_enabled(inode->i_sb))
+	if (sb_any_quota_active(inode->i_sb))
 		inode->i_sb->dq_op->free_inode(inode, 1);
 }
 
@@ -199,12 +226,12 @@ static inline int vfs_dq_off(struct super_block *sb, int remount)
 
 #else
 
-static inline int sb_has_quota_enabled(struct super_block *sb, int type)
+static inline int sb_has_quota_usage_enabled(struct super_block *sb, int type)
 {
 	return 0;
 }
 
-static inline int sb_any_quota_enabled(struct super_block *sb)
+static inline int sb_has_quota_limits_enabled(struct super_block *sb, int type)
 {
 	return 0;
 }
@@ -219,6 +246,30 @@ static inline int sb_any_quota_suspended(struct super_block *sb)
 	return 0;
 }
 
+/* Does kernel know about any quota information for given sb + type? */
+static inline int sb_has_quota_loaded(struct super_block *sb, int type)
+{
+	return 0;
+}
+
+static inline int sb_any_quota_loaded(struct super_block *sb)
+{
+	return 0;
+}
+
+static inline int sb_has_quota_active(struct super_block *sb, int type)
+{
+	return 0;
+}
+
+static inline int sb_any_quota_active(struct super_block *sb)
+{
+	return 0;
+}
+
+/* For backward compatibility until we remove all users */
+#define sb_any_quota_enabled(sb) sb_any_quota_active(sb)
+
 /*
  * NO-OP when quota not configured.
  */
-- 
cgit v1.2.3-70-g09d2


From dcb30695f2cac86b71417629a6fe8042b4fe2ab2 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 20 Aug 2008 18:30:40 +0200
Subject: quota: Remove compatibility function sb_any_quota_enabled()

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 include/linux/quotaops.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 3b3346fa657c..e840ca523175 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -116,9 +116,6 @@ static inline int sb_any_quota_active(struct super_block *sb)
 	       sb_has_quota_active(sb, GRPQUOTA);
 }
 
-/* For backward compatibility until we remove all users */
-#define sb_any_quota_enabled(sb) sb_any_quota_active(sb)
-
 /*
  * Operations supported for diskquotas.
  */
@@ -267,9 +264,6 @@ static inline int sb_any_quota_active(struct super_block *sb)
 	return 0;
 }
 
-/* For backward compatibility until we remove all users */
-#define sb_any_quota_enabled(sb) sb_any_quota_active(sb)
-
 /*
  * NO-OP when quota not configured.
  */
-- 
cgit v1.2.3-70-g09d2


From ca785ec66b991e9ca74dd9840fc014487ad095e1 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 30 Sep 2008 17:53:37 +0200
Subject: quota: Introduce DQUOT_QUOTA_SYS_FILE flag

If filesystem can handle quota files as system files hidden from users, we can
skip a lot of cache invalidation, syncing, inode flags setting etc. when
turning quotas on, off and quota_sync. Allow filesystem to indicate that it is
hiding quota files from users by DQUOT_QUOTA_SYS_FILE flag.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c            | 45 ++++++++++++++++++++++++++++++---------------
 fs/quota.c            |  3 +++
 include/linux/quota.h |  7 +++++++
 3 files changed, 40 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index 7569633efe0e..74185c34a4f0 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -1631,6 +1631,11 @@ int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags)
 		dqopt->ops[cnt] = NULL;
 	}
 	mutex_unlock(&dqopt->dqonoff_mutex);
+
+	/* Skip syncing and setting flags if quota files are hidden */
+	if (dqopt->flags & DQUOT_QUOTA_SYS_FILE)
+		goto put_inodes;
+
 	/* Sync the superblock so that buffers with quota data are written to
 	 * disk (and so userspace sees correct data afterwards). */
 	if (sb->s_op->sync_fs)
@@ -1655,6 +1660,12 @@ int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags)
 				mark_inode_dirty(toputinode[cnt]);
 			}
 			mutex_unlock(&dqopt->dqonoff_mutex);
+		}
+	if (sb->s_bdev)
+		invalidate_bdev(sb->s_bdev);
+put_inodes:
+	for (cnt = 0; cnt < MAXQUOTAS; cnt++)
+		if (toputinode[cnt]) {
 			/* On remount RO, we keep the inode pointer so that we
 			 * can reenable quota on the subsequent remount RW. We
 			 * have to check 'flags' variable and not use sb_has_
@@ -1667,8 +1678,6 @@ int vfs_quota_disable(struct super_block *sb, int type, unsigned int flags)
 			else if (!toputinode[cnt]->i_nlink)
 				ret = -EBUSY;
 		}
-	if (sb->s_bdev)
-		invalidate_bdev(sb->s_bdev);
 	return ret;
 }
 
@@ -1715,25 +1724,31 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
 		goto out_fmt;
 	}
 
-	/* As we bypass the pagecache we must now flush the inode so that
-	 * we see all the changes from userspace... */
-	write_inode_now(inode, 1);
-	/* And now flush the block cache so that kernel sees the changes */
-	invalidate_bdev(sb->s_bdev);
+	if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
+		/* As we bypass the pagecache we must now flush the inode so
+		 * that we see all the changes from userspace... */
+		write_inode_now(inode, 1);
+		/* And now flush the block cache so that kernel sees the
+		 * changes */
+		invalidate_bdev(sb->s_bdev);
+	}
 	mutex_lock(&inode->i_mutex);
 	mutex_lock(&dqopt->dqonoff_mutex);
 	if (sb_has_quota_loaded(sb, type)) {
 		error = -EBUSY;
 		goto out_lock;
 	}
-	/* We don't want quota and atime on quota files (deadlocks possible)
-	 * Also nobody should write to the file - we use special IO operations
-	 * which ignore the immutable bit. */
-	down_write(&dqopt->dqptr_sem);
-	oldflags = inode->i_flags & (S_NOATIME | S_IMMUTABLE | S_NOQUOTA);
-	inode->i_flags |= S_NOQUOTA | S_NOATIME | S_IMMUTABLE;
-	up_write(&dqopt->dqptr_sem);
-	sb->dq_op->drop(inode);
+
+	if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) {
+		/* We don't want quota and atime on quota files (deadlocks
+		 * possible) Also nobody should write to the file - we use
+		 * special IO operations which ignore the immutable bit. */
+		down_write(&dqopt->dqptr_sem);
+		oldflags = inode->i_flags & (S_NOATIME | S_IMMUTABLE | S_NOQUOTA);
+		inode->i_flags |= S_NOQUOTA | S_NOATIME | S_IMMUTABLE;
+		up_write(&dqopt->dqptr_sem);
+		sb->dq_op->drop(inode);
+	}
 
 	error = -EIO;
 	dqopt->files[type] = igrab(inode);
diff --git a/fs/quota.c b/fs/quota.c
index 8678d9f35ee9..4a8c94f05f76 100644
--- a/fs/quota.c
+++ b/fs/quota.c
@@ -160,6 +160,9 @@ static void quota_sync_sb(struct super_block *sb, int type)
 	int cnt;
 
 	sb->s_qcop->quota_sync(sb, type);
+
+	if (sb_dqopt(sb)->flags & DQUOT_QUOTA_SYS_FILE)
+		return;
 	/* This is not very clever (and fast) but currently I don't know about
 	 * any other simple way of getting quota data to disk and we must get
 	 * them there for userspace to be visible... */
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 93717abcd35b..80b8807b4988 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -332,6 +332,13 @@ enum {
 #define DQUOT_SUSPENDED		(1 << _DQUOT_SUSPENDED)
 #define DQUOT_STATE_FLAGS	(DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED | \
 				 DQUOT_SUSPENDED)
+/* Other quota flags */
+#define DQUOT_QUOTA_SYS_FILE	(1 << 6)	/* Quota file is a special
+						 * system file and user cannot
+						 * touch it. Filesystem is
+						 * responsible for setting
+						 * S_NOQUOTA, S_NOATIME flags
+						 */
 
 static inline unsigned int dquot_state_flag(unsigned int flags, int type)
 {
-- 
cgit v1.2.3-70-g09d2


From cf770c137122b78470a67ebd5498947869a09197 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Sun, 21 Sep 2008 23:17:53 +0200
Subject: quota: Move quotaio_v[12].h from include/linux/ to fs/

Since these include files are used only by implementation of quota formats,
there's no need to have them in include/linux/.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/quota_v1.c              |  3 +-
 fs/quota_v2.c              |  7 ++--
 fs/quotaio_v1.h            | 33 +++++++++++++++++++
 fs/quotaio_v2.h            | 79 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/Kbuild       |  2 --
 include/linux/quotaio_v1.h | 33 -------------------
 include/linux/quotaio_v2.h | 79 ----------------------------------------------
 7 files changed, 118 insertions(+), 118 deletions(-)
 create mode 100644 fs/quotaio_v1.h
 create mode 100644 fs/quotaio_v2.h
 delete mode 100644 include/linux/quotaio_v1.h
 delete mode 100644 include/linux/quotaio_v2.h

(limited to 'include')

diff --git a/fs/quota_v1.c b/fs/quota_v1.c
index 3e078eee5644..b4af1c69ad16 100644
--- a/fs/quota_v1.c
+++ b/fs/quota_v1.c
@@ -3,13 +3,14 @@
 #include <linux/quota.h>
 #include <linux/quotaops.h>
 #include <linux/dqblk_v1.h>
-#include <linux/quotaio_v1.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/module.h>
 
 #include <asm/byteorder.h>
 
+#include "quotaio_v1.h"
+
 MODULE_AUTHOR("Jan Kara");
 MODULE_DESCRIPTION("Old quota format support");
 MODULE_LICENSE("GPL");
diff --git a/fs/quota_v2.c b/fs/quota_v2.c
index 51c4717f7c6a..a21d1a7c356a 100644
--- a/fs/quota_v2.c
+++ b/fs/quota_v2.c
@@ -6,7 +6,6 @@
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/dqblk_v2.h>
-#include <linux/quotaio_v2.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -15,6 +14,8 @@
 
 #include <asm/byteorder.h>
 
+#include "quotaio_v2.h"
+
 MODULE_AUTHOR("Jan Kara");
 MODULE_DESCRIPTION("Quota format v2 support");
 MODULE_LICENSE("GPL");
@@ -129,8 +130,8 @@ static void mem2diskdqb(struct v2_disk_dqblk *d, struct mem_dqblk *m, qid_t id)
 	d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit);
 	d->dqb_curinodes = cpu_to_le32(m->dqb_curinodes);
 	d->dqb_itime = cpu_to_le64(m->dqb_itime);
-	d->dqb_bhardlimit = cpu_to_le32(v2_qbtos(m->dqb_bhardlimit));
-	d->dqb_bsoftlimit = cpu_to_le32(v2_qbtos(m->dqb_bsoftlimit));
+	d->dqb_bhardlimit = cpu_to_le32(v2_stoqb(m->dqb_bhardlimit));
+	d->dqb_bsoftlimit = cpu_to_le32(v2_stoqb(m->dqb_bsoftlimit));
 	d->dqb_curspace = cpu_to_le64(m->dqb_curspace);
 	d->dqb_btime = cpu_to_le64(m->dqb_btime);
 	d->dqb_id = cpu_to_le32(id);
diff --git a/fs/quotaio_v1.h b/fs/quotaio_v1.h
new file mode 100644
index 000000000000..746654b5de70
--- /dev/null
+++ b/fs/quotaio_v1.h
@@ -0,0 +1,33 @@
+#ifndef _LINUX_QUOTAIO_V1_H
+#define _LINUX_QUOTAIO_V1_H
+
+#include <linux/types.h>
+
+/*
+ * The following constants define the amount of time given a user
+ * before the soft limits are treated as hard limits (usually resulting
+ * in an allocation failure). The timer is started when the user crosses
+ * their soft limit, it is reset when they go below their soft limit.
+ */
+#define MAX_IQ_TIME  604800	/* (7*24*60*60) 1 week */
+#define MAX_DQ_TIME  604800	/* (7*24*60*60) 1 week */
+
+/*
+ * The following structure defines the format of the disk quota file
+ * (as it appears on disk) - the file is an array of these structures
+ * indexed by user or group number.
+ */
+struct v1_disk_dqblk {
+	__u32 dqb_bhardlimit;	/* absolute limit on disk blks alloc */
+	__u32 dqb_bsoftlimit;	/* preferred limit on disk blks */
+	__u32 dqb_curblocks;	/* current block count */
+	__u32 dqb_ihardlimit;	/* absolute limit on allocated inodes */
+	__u32 dqb_isoftlimit;	/* preferred inode limit */
+	__u32 dqb_curinodes;	/* current # allocated inodes */
+	time_t dqb_btime;	/* time limit for excessive disk use */
+	time_t dqb_itime;	/* time limit for excessive inode use */
+};
+
+#define v1_dqoff(UID)      ((loff_t)((UID) * sizeof (struct v1_disk_dqblk)))
+
+#endif	/* _LINUX_QUOTAIO_V1_H */
diff --git a/fs/quotaio_v2.h b/fs/quotaio_v2.h
new file mode 100644
index 000000000000..303d7cbe30d4
--- /dev/null
+++ b/fs/quotaio_v2.h
@@ -0,0 +1,79 @@
+/*
+ *	Definitions of structures for vfsv0 quota format
+ */
+
+#ifndef _LINUX_QUOTAIO_V2_H
+#define _LINUX_QUOTAIO_V2_H
+
+#include <linux/types.h>
+#include <linux/quota.h>
+
+/*
+ * Definitions of magics and versions of current quota files
+ */
+#define V2_INITQMAGICS {\
+	0xd9c01f11,	/* USRQUOTA */\
+	0xd9c01927	/* GRPQUOTA */\
+}
+
+#define V2_INITQVERSIONS {\
+	0,		/* USRQUOTA */\
+	0		/* GRPQUOTA */\
+}
+
+/*
+ * The following structure defines the format of the disk quota file
+ * (as it appears on disk) - the file is a radix tree whose leaves point
+ * to blocks of these structures.
+ */
+struct v2_disk_dqblk {
+	__le32 dqb_id;		/* id this quota applies to */
+	__le32 dqb_ihardlimit;	/* absolute limit on allocated inodes */
+	__le32 dqb_isoftlimit;	/* preferred inode limit */
+	__le32 dqb_curinodes;	/* current # allocated inodes */
+	__le32 dqb_bhardlimit;	/* absolute limit on disk space (in QUOTABLOCK_SIZE) */
+	__le32 dqb_bsoftlimit;	/* preferred limit on disk space (in QUOTABLOCK_SIZE) */
+	__le64 dqb_curspace;	/* current space occupied (in bytes) */
+	__le64 dqb_btime;	/* time limit for excessive disk use */
+	__le64 dqb_itime;	/* time limit for excessive inode use */
+};
+
+/*
+ * Here are header structures as written on disk and their in-memory copies
+ */
+/* First generic header */
+struct v2_disk_dqheader {
+	__le32 dqh_magic;	/* Magic number identifying file */
+	__le32 dqh_version;	/* File version */
+};
+
+/* Header with type and version specific information */
+struct v2_disk_dqinfo {
+	__le32 dqi_bgrace;	/* Time before block soft limit becomes hard limit */
+	__le32 dqi_igrace;	/* Time before inode soft limit becomes hard limit */
+	__le32 dqi_flags;	/* Flags for quotafile (DQF_*) */
+	__le32 dqi_blocks;	/* Number of blocks in file */
+	__le32 dqi_free_blk;	/* Number of first free block in the list */
+	__le32 dqi_free_entry;	/* Number of block with at least one free entry */
+};
+
+/*
+ *  Structure of header of block with quota structures. It is padded to 16 bytes so
+ *  there will be space for exactly 21 quota-entries in a block
+ */
+struct v2_disk_dqdbheader {
+	__le32 dqdh_next_free;	/* Number of next block with free entry */
+	__le32 dqdh_prev_free;	/* Number of previous block with free entry */
+	__le16 dqdh_entries;	/* Number of valid entries in block */
+	__le16 dqdh_pad1;
+	__le32 dqdh_pad2;
+};
+
+#define V2_DQINFOOFF	sizeof(struct v2_disk_dqheader)	/* Offset of info header in file */
+#define V2_DQBLKSIZE_BITS	10
+#define V2_DQBLKSIZE	(1 << V2_DQBLKSIZE_BITS)	/* Size of block with quota structures */
+#define V2_DQTREEOFF	1		/* Offset of tree in file in blocks */
+#define V2_DQTREEDEPTH	4		/* Depth of quota tree */
+#define V2_DQSTRINBLK	((V2_DQBLKSIZE - sizeof(struct v2_disk_dqdbheader)) / sizeof(struct v2_disk_dqblk))	/* Number of entries in one blocks */
+
+#endif /* _LINUX_QUOTAIO_V2_H */
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 95ac82340c3b..900a787cbae9 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -134,8 +134,6 @@ header-y += posix_types.h
 header-y += ppdev.h
 header-y += prctl.h
 header-y += qnxtypes.h
-header-y += quotaio_v1.h
-header-y += quotaio_v2.h
 header-y += radeonfb.h
 header-y += raw.h
 header-y += resource.h
diff --git a/include/linux/quotaio_v1.h b/include/linux/quotaio_v1.h
deleted file mode 100644
index 746654b5de70..000000000000
--- a/include/linux/quotaio_v1.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef _LINUX_QUOTAIO_V1_H
-#define _LINUX_QUOTAIO_V1_H
-
-#include <linux/types.h>
-
-/*
- * The following constants define the amount of time given a user
- * before the soft limits are treated as hard limits (usually resulting
- * in an allocation failure). The timer is started when the user crosses
- * their soft limit, it is reset when they go below their soft limit.
- */
-#define MAX_IQ_TIME  604800	/* (7*24*60*60) 1 week */
-#define MAX_DQ_TIME  604800	/* (7*24*60*60) 1 week */
-
-/*
- * The following structure defines the format of the disk quota file
- * (as it appears on disk) - the file is an array of these structures
- * indexed by user or group number.
- */
-struct v1_disk_dqblk {
-	__u32 dqb_bhardlimit;	/* absolute limit on disk blks alloc */
-	__u32 dqb_bsoftlimit;	/* preferred limit on disk blks */
-	__u32 dqb_curblocks;	/* current block count */
-	__u32 dqb_ihardlimit;	/* absolute limit on allocated inodes */
-	__u32 dqb_isoftlimit;	/* preferred inode limit */
-	__u32 dqb_curinodes;	/* current # allocated inodes */
-	time_t dqb_btime;	/* time limit for excessive disk use */
-	time_t dqb_itime;	/* time limit for excessive inode use */
-};
-
-#define v1_dqoff(UID)      ((loff_t)((UID) * sizeof (struct v1_disk_dqblk)))
-
-#endif	/* _LINUX_QUOTAIO_V1_H */
diff --git a/include/linux/quotaio_v2.h b/include/linux/quotaio_v2.h
deleted file mode 100644
index 303d7cbe30d4..000000000000
--- a/include/linux/quotaio_v2.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- *	Definitions of structures for vfsv0 quota format
- */
-
-#ifndef _LINUX_QUOTAIO_V2_H
-#define _LINUX_QUOTAIO_V2_H
-
-#include <linux/types.h>
-#include <linux/quota.h>
-
-/*
- * Definitions of magics and versions of current quota files
- */
-#define V2_INITQMAGICS {\
-	0xd9c01f11,	/* USRQUOTA */\
-	0xd9c01927	/* GRPQUOTA */\
-}
-
-#define V2_INITQVERSIONS {\
-	0,		/* USRQUOTA */\
-	0		/* GRPQUOTA */\
-}
-
-/*
- * The following structure defines the format of the disk quota file
- * (as it appears on disk) - the file is a radix tree whose leaves point
- * to blocks of these structures.
- */
-struct v2_disk_dqblk {
-	__le32 dqb_id;		/* id this quota applies to */
-	__le32 dqb_ihardlimit;	/* absolute limit on allocated inodes */
-	__le32 dqb_isoftlimit;	/* preferred inode limit */
-	__le32 dqb_curinodes;	/* current # allocated inodes */
-	__le32 dqb_bhardlimit;	/* absolute limit on disk space (in QUOTABLOCK_SIZE) */
-	__le32 dqb_bsoftlimit;	/* preferred limit on disk space (in QUOTABLOCK_SIZE) */
-	__le64 dqb_curspace;	/* current space occupied (in bytes) */
-	__le64 dqb_btime;	/* time limit for excessive disk use */
-	__le64 dqb_itime;	/* time limit for excessive inode use */
-};
-
-/*
- * Here are header structures as written on disk and their in-memory copies
- */
-/* First generic header */
-struct v2_disk_dqheader {
-	__le32 dqh_magic;	/* Magic number identifying file */
-	__le32 dqh_version;	/* File version */
-};
-
-/* Header with type and version specific information */
-struct v2_disk_dqinfo {
-	__le32 dqi_bgrace;	/* Time before block soft limit becomes hard limit */
-	__le32 dqi_igrace;	/* Time before inode soft limit becomes hard limit */
-	__le32 dqi_flags;	/* Flags for quotafile (DQF_*) */
-	__le32 dqi_blocks;	/* Number of blocks in file */
-	__le32 dqi_free_blk;	/* Number of first free block in the list */
-	__le32 dqi_free_entry;	/* Number of block with at least one free entry */
-};
-
-/*
- *  Structure of header of block with quota structures. It is padded to 16 bytes so
- *  there will be space for exactly 21 quota-entries in a block
- */
-struct v2_disk_dqdbheader {
-	__le32 dqdh_next_free;	/* Number of next block with free entry */
-	__le32 dqdh_prev_free;	/* Number of previous block with free entry */
-	__le16 dqdh_entries;	/* Number of valid entries in block */
-	__le16 dqdh_pad1;
-	__le32 dqdh_pad2;
-};
-
-#define V2_DQINFOOFF	sizeof(struct v2_disk_dqheader)	/* Offset of info header in file */
-#define V2_DQBLKSIZE_BITS	10
-#define V2_DQBLKSIZE	(1 << V2_DQBLKSIZE_BITS)	/* Size of block with quota structures */
-#define V2_DQTREEOFF	1		/* Offset of tree in file in blocks */
-#define V2_DQTREEDEPTH	4		/* Depth of quota tree */
-#define V2_DQSTRINBLK	((V2_DQBLKSIZE - sizeof(struct v2_disk_dqdbheader)) / sizeof(struct v2_disk_dqblk))	/* Number of entries in one blocks */
-
-#endif /* _LINUX_QUOTAIO_V2_H */
-- 
cgit v1.2.3-70-g09d2


From 1ccd14b9c271c1ac6eec5c5ec5def433100e7248 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 22 Sep 2008 05:54:49 +0200
Subject: quota: Split off quota tree handling into a separate file

There is going to be a new version of quota format having 64-bit
quota limits and a new quota format for OCFS2. They are both
going to use the same tree structure as VFSv0 quota format. So
split out tree handling into a separate file and make size of
leaf blocks, amount of space usable in each block (needed for
checksumming) and structures contained in them configurable
so that the code can be shared.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/Kconfig                  |   5 +
 fs/Makefile                 |   1 +
 fs/quota_tree.c             | 645 ++++++++++++++++++++++++++++++++++++++++++++
 fs/quota_tree.h             |  25 ++
 fs/quota_v2.c               | 596 ++++------------------------------------
 fs/quotaio_v2.h             |  33 +--
 include/linux/dqblk_qtree.h |  56 ++++
 include/linux/dqblk_v2.h    |  19 +-
 8 files changed, 799 insertions(+), 581 deletions(-)
 create mode 100644 fs/quota_tree.c
 create mode 100644 fs/quota_tree.h
 create mode 100644 include/linux/dqblk_qtree.h

(limited to 'include')

diff --git a/fs/Kconfig b/fs/Kconfig
index b93425ad15de..c1ce3d8831d8 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -302,6 +302,10 @@ config PRINT_QUOTA_WARNING
 	  Note that this behavior is currently deprecated and may go away in
 	  future. Please use notification via netlink socket instead.
 
+# Generic support for tree structured quota files. Seleted when needed.
+config QUOTA_TREE
+	 tristate
+
 config QFMT_V1
 	tristate "Old quota format support"
 	depends on QUOTA
@@ -313,6 +317,7 @@ config QFMT_V1
 config QFMT_V2
 	tristate "Quota format v2 support"
 	depends on QUOTA
+	select QUOTA_TREE
 	help
 	  This quota format allows using quotas with 32-bit UIDs/GIDs. If you
 	  need this functionality say Y here.
diff --git a/fs/Makefile b/fs/Makefile
index e6f423d1d228..c830611550d3 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -54,6 +54,7 @@ obj-$(CONFIG_GENERIC_ACL)	+= generic_acl.o
 obj-$(CONFIG_QUOTA)		+= dquot.o
 obj-$(CONFIG_QFMT_V1)		+= quota_v1.o
 obj-$(CONFIG_QFMT_V2)		+= quota_v2.o
+obj-$(CONFIG_QUOTA_TREE)	+= quota_tree.o
 obj-$(CONFIG_QUOTACTL)		+= quota.o
 
 obj-$(CONFIG_PROC_FS)		+= proc/
diff --git a/fs/quota_tree.c b/fs/quota_tree.c
new file mode 100644
index 000000000000..953404c95b17
--- /dev/null
+++ b/fs/quota_tree.c
@@ -0,0 +1,645 @@
+/*
+ *	vfsv0 quota IO operations on file
+ */
+
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/dqblk_v2.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/quotaops.h>
+
+#include <asm/byteorder.h>
+
+#include "quota_tree.h"
+
+MODULE_AUTHOR("Jan Kara");
+MODULE_DESCRIPTION("Quota trie support");
+MODULE_LICENSE("GPL");
+
+#define __QUOTA_QT_PARANOIA
+
+typedef char *dqbuf_t;
+
+static int get_index(struct qtree_mem_dqinfo *info, qid_t id, int depth)
+{
+	unsigned int epb = info->dqi_usable_bs >> 2;
+
+	depth = info->dqi_qtree_depth - depth - 1;
+	while (depth--)
+		id /= epb;
+	return id % epb;
+}
+
+/* Number of entries in one blocks */
+static inline int qtree_dqstr_in_blk(struct qtree_mem_dqinfo *info)
+{
+	return (info->dqi_usable_bs - sizeof(struct qt_disk_dqdbheader))
+	       / info->dqi_entry_size;
+}
+
+static dqbuf_t getdqbuf(size_t size)
+{
+	dqbuf_t buf = kmalloc(size, GFP_NOFS);
+	if (!buf)
+		printk(KERN_WARNING "VFS: Not enough memory for quota buffers.\n");
+	return buf;
+}
+
+static inline void freedqbuf(dqbuf_t buf)
+{
+	kfree(buf);
+}
+
+static inline ssize_t read_blk(struct qtree_mem_dqinfo *info, uint blk, dqbuf_t buf)
+{
+	struct super_block *sb = info->dqi_sb;
+
+	memset(buf, 0, info->dqi_usable_bs);
+	return sb->s_op->quota_read(sb, info->dqi_type, (char *)buf,
+	       info->dqi_usable_bs, blk << info->dqi_blocksize_bits);
+}
+
+static inline ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, dqbuf_t buf)
+{
+	struct super_block *sb = info->dqi_sb;
+
+	return sb->s_op->quota_write(sb, info->dqi_type, (char *)buf,
+	       info->dqi_usable_bs, blk << info->dqi_blocksize_bits);
+}
+
+/* Remove empty block from list and return it */
+static int get_free_dqblk(struct qtree_mem_dqinfo *info)
+{
+	dqbuf_t buf = getdqbuf(info->dqi_usable_bs);
+	struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf;
+	int ret, blk;
+
+	if (!buf)
+		return -ENOMEM;
+	if (info->dqi_free_blk) {
+		blk = info->dqi_free_blk;
+		ret = read_blk(info, blk, buf);
+		if (ret < 0)
+			goto out_buf;
+		info->dqi_free_blk = le32_to_cpu(dh->dqdh_next_free);
+	}
+	else {
+		memset(buf, 0, info->dqi_usable_bs);
+		/* Assure block allocation... */
+		ret = write_blk(info, info->dqi_blocks, buf);
+		if (ret < 0)
+			goto out_buf;
+		blk = info->dqi_blocks++;
+	}
+	mark_info_dirty(info->dqi_sb, info->dqi_type);
+	ret = blk;
+out_buf:
+	freedqbuf(buf);
+	return ret;
+}
+
+/* Insert empty block to the list */
+static int put_free_dqblk(struct qtree_mem_dqinfo *info, dqbuf_t buf, uint blk)
+{
+	struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf;
+	int err;
+
+	dh->dqdh_next_free = cpu_to_le32(info->dqi_free_blk);
+	dh->dqdh_prev_free = cpu_to_le32(0);
+	dh->dqdh_entries = cpu_to_le16(0);
+	err = write_blk(info, blk, buf);
+	if (err < 0)
+		return err;
+	info->dqi_free_blk = blk;
+	mark_info_dirty(info->dqi_sb, info->dqi_type);
+	return 0;
+}
+
+/* Remove given block from the list of blocks with free entries */
+static int remove_free_dqentry(struct qtree_mem_dqinfo *info, dqbuf_t buf, uint blk)
+{
+	dqbuf_t tmpbuf = getdqbuf(info->dqi_usable_bs);
+	struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf;
+	uint nextblk = le32_to_cpu(dh->dqdh_next_free);
+	uint prevblk = le32_to_cpu(dh->dqdh_prev_free);
+	int err;
+
+	if (!tmpbuf)
+		return -ENOMEM;
+	if (nextblk) {
+		err = read_blk(info, nextblk, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+		((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_prev_free =
+							dh->dqdh_prev_free;
+		err = write_blk(info, nextblk, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+	}
+	if (prevblk) {
+		err = read_blk(info, prevblk, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+		((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_next_free =
+							dh->dqdh_next_free;
+		err = write_blk(info, prevblk, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+	} else {
+		info->dqi_free_entry = nextblk;
+		mark_info_dirty(info->dqi_sb, info->dqi_type);
+	}
+	freedqbuf(tmpbuf);
+	dh->dqdh_next_free = dh->dqdh_prev_free = cpu_to_le32(0);
+	/* No matter whether write succeeds block is out of list */
+	if (write_blk(info, blk, buf) < 0)
+		printk(KERN_ERR "VFS: Can't write block (%u) with free entries.\n", blk);
+	return 0;
+out_buf:
+	freedqbuf(tmpbuf);
+	return err;
+}
+
+/* Insert given block to the beginning of list with free entries */
+static int insert_free_dqentry(struct qtree_mem_dqinfo *info, dqbuf_t buf, uint blk)
+{
+	dqbuf_t tmpbuf = getdqbuf(info->dqi_usable_bs);
+	struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf;
+	int err;
+
+	if (!tmpbuf)
+		return -ENOMEM;
+	dh->dqdh_next_free = cpu_to_le32(info->dqi_free_entry);
+	dh->dqdh_prev_free = cpu_to_le32(0);
+	err = write_blk(info, blk, buf);
+	if (err < 0)
+		goto out_buf;
+	if (info->dqi_free_entry) {
+		err = read_blk(info, info->dqi_free_entry, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+		((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_prev_free =
+							cpu_to_le32(blk);
+		err = write_blk(info, info->dqi_free_entry, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+	}
+	freedqbuf(tmpbuf);
+	info->dqi_free_entry = blk;
+	mark_info_dirty(info->dqi_sb, info->dqi_type);
+	return 0;
+out_buf:
+	freedqbuf(tmpbuf);
+	return err;
+}
+
+/* Is the entry in the block free? */
+int qtree_entry_unused(struct qtree_mem_dqinfo *info, char *disk)
+{
+	int i;
+
+	for (i = 0; i < info->dqi_entry_size; i++)
+		if (disk[i])
+			return 0;
+	return 1;
+}
+EXPORT_SYMBOL(qtree_entry_unused);
+
+/* Find space for dquot */
+static uint find_free_dqentry(struct qtree_mem_dqinfo *info,
+			      struct dquot *dquot, int *err)
+{
+	uint blk, i;
+	struct qt_disk_dqdbheader *dh;
+	dqbuf_t buf = getdqbuf(info->dqi_usable_bs);
+	char *ddquot;
+
+	*err = 0;
+	if (!buf) {
+		*err = -ENOMEM;
+		return 0;
+	}
+	dh = (struct qt_disk_dqdbheader *)buf;
+	if (info->dqi_free_entry) {
+		blk = info->dqi_free_entry;
+		*err = read_blk(info, blk, buf);
+		if (*err < 0)
+			goto out_buf;
+	} else {
+		blk = get_free_dqblk(info);
+		if ((int)blk < 0) {
+			*err = blk;
+			freedqbuf(buf);
+			return 0;
+		}
+		memset(buf, 0, info->dqi_usable_bs);
+		/* This is enough as block is already zeroed and entry list is empty... */
+		info->dqi_free_entry = blk;
+		mark_info_dirty(dquot->dq_sb, dquot->dq_type);
+	}
+	/* Block will be full? */
+	if (le16_to_cpu(dh->dqdh_entries) + 1 >= qtree_dqstr_in_blk(info)) {
+		*err = remove_free_dqentry(info, buf, blk);
+		if (*err < 0) {
+			printk(KERN_ERR "VFS: find_free_dqentry(): Can't "
+			       "remove block (%u) from entry free list.\n",
+			       blk);
+			goto out_buf;
+		}
+	}
+	le16_add_cpu(&dh->dqdh_entries, 1);
+	/* Find free structure in block */
+	for (i = 0, ddquot = ((char *)buf) + sizeof(struct qt_disk_dqdbheader);
+	     i < qtree_dqstr_in_blk(info) && !qtree_entry_unused(info, ddquot);
+	     i++, ddquot += info->dqi_entry_size);
+#ifdef __QUOTA_QT_PARANOIA
+	if (i == qtree_dqstr_in_blk(info)) {
+		printk(KERN_ERR "VFS: find_free_dqentry(): Data block full "
+				"but it shouldn't.\n");
+		*err = -EIO;
+		goto out_buf;
+	}
+#endif
+	*err = write_blk(info, blk, buf);
+	if (*err < 0) {
+		printk(KERN_ERR "VFS: find_free_dqentry(): Can't write quota "
+				"data block %u.\n", blk);
+		goto out_buf;
+	}
+	dquot->dq_off = (blk << info->dqi_blocksize_bits) +
+			sizeof(struct qt_disk_dqdbheader) +
+			i * info->dqi_entry_size;
+	freedqbuf(buf);
+	return blk;
+out_buf:
+	freedqbuf(buf);
+	return 0;
+}
+
+/* Insert reference to structure into the trie */
+static int do_insert_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot,
+			  uint *treeblk, int depth)
+{
+	dqbuf_t buf = getdqbuf(info->dqi_usable_bs);
+	int ret = 0, newson = 0, newact = 0;
+	__le32 *ref;
+	uint newblk;
+
+	if (!buf)
+		return -ENOMEM;
+	if (!*treeblk) {
+		ret = get_free_dqblk(info);
+		if (ret < 0)
+			goto out_buf;
+		*treeblk = ret;
+		memset(buf, 0, info->dqi_usable_bs);
+		newact = 1;
+	} else {
+		ret = read_blk(info, *treeblk, buf);
+		if (ret < 0) {
+			printk(KERN_ERR "VFS: Can't read tree quota block "
+					"%u.\n", *treeblk);
+			goto out_buf;
+		}
+	}
+	ref = (__le32 *)buf;
+	newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]);
+	if (!newblk)
+		newson = 1;
+	if (depth == info->dqi_qtree_depth - 1) {
+#ifdef __QUOTA_QT_PARANOIA
+		if (newblk) {
+			printk(KERN_ERR "VFS: Inserting already present quota "
+					"entry (block %u).\n",
+			       le32_to_cpu(ref[get_index(info,
+						dquot->dq_id, depth)]));
+			ret = -EIO;
+			goto out_buf;
+		}
+#endif
+		newblk = find_free_dqentry(info, dquot, &ret);
+	} else {
+		ret = do_insert_tree(info, dquot, &newblk, depth+1);
+	}
+	if (newson && ret >= 0) {
+		ref[get_index(info, dquot->dq_id, depth)] =
+							cpu_to_le32(newblk);
+		ret = write_blk(info, *treeblk, buf);
+	} else if (newact && ret < 0) {
+		put_free_dqblk(info, buf, *treeblk);
+	}
+out_buf:
+	freedqbuf(buf);
+	return ret;
+}
+
+/* Wrapper for inserting quota structure into tree */
+static inline int dq_insert_tree(struct qtree_mem_dqinfo *info,
+				 struct dquot *dquot)
+{
+	int tmp = QT_TREEOFF;
+	return do_insert_tree(info, dquot, &tmp, 0);
+}
+
+/*
+ *	We don't have to be afraid of deadlocks as we never have quotas on quota files...
+ */
+int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
+{
+	int type = dquot->dq_type;
+	struct super_block *sb = dquot->dq_sb;
+	ssize_t ret;
+	dqbuf_t ddquot = getdqbuf(info->dqi_entry_size);
+
+	if (!ddquot)
+		return -ENOMEM;
+
+	/* dq_off is guarded by dqio_mutex */
+	if (!dquot->dq_off) {
+		ret = dq_insert_tree(info, dquot);
+		if (ret < 0) {
+			printk(KERN_ERR "VFS: Error %zd occurred while "
+					"creating quota.\n", ret);
+			freedqbuf(ddquot);
+			return ret;
+		}
+	}
+	spin_lock(&dq_data_lock);
+	info->dqi_ops->mem2disk_dqblk(ddquot, dquot);
+	spin_unlock(&dq_data_lock);
+	ret = sb->s_op->quota_write(sb, type, (char *)ddquot,
+					info->dqi_entry_size, dquot->dq_off);
+	if (ret != info->dqi_entry_size) {
+		printk(KERN_WARNING "VFS: dquota write failed on dev %s\n",
+		       sb->s_id);
+		if (ret >= 0)
+			ret = -ENOSPC;
+	} else {
+		ret = 0;
+	}
+	dqstats.writes++;
+	freedqbuf(ddquot);
+
+	return ret;
+}
+EXPORT_SYMBOL(qtree_write_dquot);
+
+/* Free dquot entry in data block */
+static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot,
+			uint blk)
+{
+	struct qt_disk_dqdbheader *dh;
+	dqbuf_t buf = getdqbuf(info->dqi_usable_bs);
+	int ret = 0;
+
+	if (!buf)
+		return -ENOMEM;
+	if (dquot->dq_off >> info->dqi_blocksize_bits != blk) {
+		printk(KERN_ERR "VFS: Quota structure has offset to other "
+		  "block (%u) than it should (%u).\n", blk,
+		  (uint)(dquot->dq_off >> info->dqi_blocksize_bits));
+		goto out_buf;
+	}
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		printk(KERN_ERR "VFS: Can't read quota data block %u\n", blk);
+		goto out_buf;
+	}
+	dh = (struct qt_disk_dqdbheader *)buf;
+	le16_add_cpu(&dh->dqdh_entries, -1);
+	if (!le16_to_cpu(dh->dqdh_entries)) {	/* Block got free? */
+		ret = remove_free_dqentry(info, buf, blk);
+		if (ret >= 0)
+			ret = put_free_dqblk(info, buf, blk);
+		if (ret < 0) {
+			printk(KERN_ERR "VFS: Can't move quota data block (%u) "
+			  "to free list.\n", blk);
+			goto out_buf;
+		}
+	} else {
+		memset(buf +
+		       (dquot->dq_off & ((1 << info->dqi_blocksize_bits) - 1)),
+		       0, info->dqi_entry_size);
+		if (le16_to_cpu(dh->dqdh_entries) ==
+		    qtree_dqstr_in_blk(info) - 1) {
+			/* Insert will write block itself */
+			ret = insert_free_dqentry(info, buf, blk);
+			if (ret < 0) {
+				printk(KERN_ERR "VFS: Can't insert quota data "
+				       "block (%u) to free entry list.\n", blk);
+				goto out_buf;
+			}
+		} else {
+			ret = write_blk(info, blk, buf);
+			if (ret < 0) {
+				printk(KERN_ERR "VFS: Can't write quota data "
+				  "block %u\n", blk);
+				goto out_buf;
+			}
+		}
+	}
+	dquot->dq_off = 0;	/* Quota is now unattached */
+out_buf:
+	freedqbuf(buf);
+	return ret;
+}
+
+/* Remove reference to dquot from tree */
+static int remove_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot,
+		       uint *blk, int depth)
+{
+	dqbuf_t buf = getdqbuf(info->dqi_usable_bs);
+	int ret = 0;
+	uint newblk;
+	__le32 *ref = (__le32 *)buf;
+
+	if (!buf)
+		return -ENOMEM;
+	ret = read_blk(info, *blk, buf);
+	if (ret < 0) {
+		printk(KERN_ERR "VFS: Can't read quota data block %u\n", *blk);
+		goto out_buf;
+	}
+	newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]);
+	if (depth == info->dqi_qtree_depth - 1) {
+		ret = free_dqentry(info, dquot, newblk);
+		newblk = 0;
+	} else {
+		ret = remove_tree(info, dquot, &newblk, depth+1);
+	}
+	if (ret >= 0 && !newblk) {
+		int i;
+		ref[get_index(info, dquot->dq_id, depth)] = cpu_to_le32(0);
+		/* Block got empty? */
+		for (i = 0;
+		     i < (info->dqi_usable_bs >> 2) && !ref[i];
+		     i++);
+		/* Don't put the root block into the free block list */
+		if (i == (info->dqi_usable_bs >> 2)
+		    && *blk != QT_TREEOFF) {
+			put_free_dqblk(info, buf, *blk);
+			*blk = 0;
+		} else {
+			ret = write_blk(info, *blk, buf);
+			if (ret < 0)
+				printk(KERN_ERR "VFS: Can't write quota tree "
+				  "block %u.\n", *blk);
+		}
+	}
+out_buf:
+	freedqbuf(buf);
+	return ret;
+}
+
+/* Delete dquot from tree */
+int qtree_delete_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
+{
+	uint tmp = QT_TREEOFF;
+
+	if (!dquot->dq_off)	/* Even not allocated? */
+		return 0;
+	return remove_tree(info, dquot, &tmp, 0);
+}
+EXPORT_SYMBOL(qtree_delete_dquot);
+
+/* Find entry in block */
+static loff_t find_block_dqentry(struct qtree_mem_dqinfo *info,
+				 struct dquot *dquot, uint blk)
+{
+	dqbuf_t buf = getdqbuf(info->dqi_usable_bs);
+	loff_t ret = 0;
+	int i;
+	char *ddquot;
+
+	if (!buf)
+		return -ENOMEM;
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		printk(KERN_ERR "VFS: Can't read quota tree block %u.\n", blk);
+		goto out_buf;
+	}
+	for (i = 0, ddquot = ((char *)buf) + sizeof(struct qt_disk_dqdbheader);
+	     i < qtree_dqstr_in_blk(info) && !info->dqi_ops->is_id(ddquot, dquot);
+	     i++, ddquot += info->dqi_entry_size);
+	if (i == qtree_dqstr_in_blk(info)) {
+		printk(KERN_ERR "VFS: Quota for id %u referenced "
+		  "but not present.\n", dquot->dq_id);
+		ret = -EIO;
+		goto out_buf;
+	} else {
+		ret = (blk << info->dqi_blocksize_bits) + sizeof(struct
+		  qt_disk_dqdbheader) + i * info->dqi_entry_size;
+	}
+out_buf:
+	freedqbuf(buf);
+	return ret;
+}
+
+/* Find entry for given id in the tree */
+static loff_t find_tree_dqentry(struct qtree_mem_dqinfo *info,
+				struct dquot *dquot, uint blk, int depth)
+{
+	dqbuf_t buf = getdqbuf(info->dqi_usable_bs);
+	loff_t ret = 0;
+	__le32 *ref = (__le32 *)buf;
+
+	if (!buf)
+		return -ENOMEM;
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		printk(KERN_ERR "VFS: Can't read quota tree block %u.\n", blk);
+		goto out_buf;
+	}
+	ret = 0;
+	blk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]);
+	if (!blk)	/* No reference? */
+		goto out_buf;
+	if (depth < info->dqi_qtree_depth - 1)
+		ret = find_tree_dqentry(info, dquot, blk, depth+1);
+	else
+		ret = find_block_dqentry(info, dquot, blk);
+out_buf:
+	freedqbuf(buf);
+	return ret;
+}
+
+/* Find entry for given id in the tree - wrapper function */
+static inline loff_t find_dqentry(struct qtree_mem_dqinfo *info,
+				  struct dquot *dquot)
+{
+	return find_tree_dqentry(info, dquot, QT_TREEOFF, 0);
+}
+
+int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
+{
+	int type = dquot->dq_type;
+	struct super_block *sb = dquot->dq_sb;
+	loff_t offset;
+	dqbuf_t ddquot;
+	int ret = 0;
+
+#ifdef __QUOTA_QT_PARANOIA
+	/* Invalidated quota? */
+	if (!sb_dqopt(dquot->dq_sb)->files[type]) {
+		printk(KERN_ERR "VFS: Quota invalidated while reading!\n");
+		return -EIO;
+	}
+#endif
+	/* Do we know offset of the dquot entry in the quota file? */
+	if (!dquot->dq_off) {
+		offset = find_dqentry(info, dquot);
+		if (offset <= 0) {	/* Entry not present? */
+			if (offset < 0)
+				printk(KERN_ERR "VFS: Can't read quota "
+				  "structure for id %u.\n", dquot->dq_id);
+			dquot->dq_off = 0;
+			set_bit(DQ_FAKE_B, &dquot->dq_flags);
+			memset(&dquot->dq_dqb, 0, sizeof(struct mem_dqblk));
+			ret = offset;
+			goto out;
+		}
+		dquot->dq_off = offset;
+	}
+	ddquot = getdqbuf(info->dqi_entry_size);
+	if (!ddquot)
+		return -ENOMEM;
+	ret = sb->s_op->quota_read(sb, type, (char *)ddquot,
+				   info->dqi_entry_size, dquot->dq_off);
+	if (ret != info->dqi_entry_size) {
+		if (ret >= 0)
+			ret = -EIO;
+		printk(KERN_ERR "VFS: Error while reading quota "
+				"structure for id %u.\n", dquot->dq_id);
+		set_bit(DQ_FAKE_B, &dquot->dq_flags);
+		memset(&dquot->dq_dqb, 0, sizeof(struct mem_dqblk));
+		freedqbuf(ddquot);
+		goto out;
+	}
+	spin_lock(&dq_data_lock);
+	info->dqi_ops->disk2mem_dqblk(dquot, ddquot);
+	if (!dquot->dq_dqb.dqb_bhardlimit &&
+	    !dquot->dq_dqb.dqb_bsoftlimit &&
+	    !dquot->dq_dqb.dqb_ihardlimit &&
+	    !dquot->dq_dqb.dqb_isoftlimit)
+		set_bit(DQ_FAKE_B, &dquot->dq_flags);
+	spin_unlock(&dq_data_lock);
+	freedqbuf(ddquot);
+out:
+	dqstats.reads++;
+	return ret;
+}
+EXPORT_SYMBOL(qtree_read_dquot);
+
+/* Check whether dquot should not be deleted. We know we are
+ * the only one operating on dquot (thanks to dq_lock) */
+int qtree_release_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
+{
+	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) && !(dquot->dq_dqb.dqb_curinodes | dquot->dq_dqb.dqb_curspace))
+		return qtree_delete_dquot(info, dquot);
+	return 0;
+}
+EXPORT_SYMBOL(qtree_release_dquot);
diff --git a/fs/quota_tree.h b/fs/quota_tree.h
new file mode 100644
index 000000000000..a1ab8db81a51
--- /dev/null
+++ b/fs/quota_tree.h
@@ -0,0 +1,25 @@
+/*
+ *	Definitions of structures for vfsv0 quota format
+ */
+
+#ifndef _LINUX_QUOTA_TREE_H
+#define _LINUX_QUOTA_TREE_H
+
+#include <linux/types.h>
+#include <linux/quota.h>
+
+/*
+ *  Structure of header of block with quota structures. It is padded to 16 bytes so
+ *  there will be space for exactly 21 quota-entries in a block
+ */
+struct qt_disk_dqdbheader {
+	__le32 dqdh_next_free;	/* Number of next block with free entry */
+	__le32 dqdh_prev_free;	/* Number of previous block with free entry */
+	__le16 dqdh_entries;	/* Number of valid entries in block */
+	__le16 dqdh_pad1;
+	__le32 dqdh_pad2;
+};
+
+#define QT_TREEOFF	1		/* Offset of tree in file in blocks */
+
+#endif /* _LINUX_QUOTAIO_TREE_H */
diff --git a/fs/quota_v2.c b/fs/quota_v2.c
index a21d1a7c356a..a87f1028a425 100644
--- a/fs/quota_v2.c
+++ b/fs/quota_v2.c
@@ -14,6 +14,7 @@
 
 #include <asm/byteorder.h>
 
+#include "quota_tree.h"
 #include "quotaio_v2.h"
 
 MODULE_AUTHOR("Jan Kara");
@@ -22,10 +23,15 @@ MODULE_LICENSE("GPL");
 
 #define __QUOTA_V2_PARANOIA
 
-typedef char *dqbuf_t;
+static void v2_mem2diskdqb(void *dp, struct dquot *dquot);
+static void v2_disk2memdqb(struct dquot *dquot, void *dp);
+static int v2_is_id(void *dp, struct dquot *dquot);
 
-#define GETIDINDEX(id, depth) (((id) >> ((V2_DQTREEDEPTH-(depth)-1)*8)) & 0xff)
-#define GETENTRIES(buf) ((struct v2_disk_dqblk *)(((char *)buf)+sizeof(struct v2_disk_dqdbheader)))
+static struct qtree_fmt_operations v2_qtree_ops = {
+	.mem2disk_dqblk = v2_mem2diskdqb,
+	.disk2mem_dqblk = v2_disk2memdqb,
+	.is_id = v2_is_id,
+};
 
 #define QUOTABLOCK_BITS 10
 #define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS)
@@ -64,7 +70,7 @@ static int v2_check_quota_file(struct super_block *sb, int type)
 static int v2_read_file_info(struct super_block *sb, int type)
 {
 	struct v2_disk_dqinfo dinfo;
-	struct mem_dqinfo *info = sb_dqopt(sb)->info+type;
+	struct mem_dqinfo *info = sb_dqinfo(sb, type);
 	ssize_t size;
 
 	size = sb->s_op->quota_read(sb, type, (char *)&dinfo,
@@ -80,9 +86,16 @@ static int v2_read_file_info(struct super_block *sb, int type)
 	info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
 	info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
 	info->dqi_flags = le32_to_cpu(dinfo.dqi_flags);
-	info->u.v2_i.dqi_blocks = le32_to_cpu(dinfo.dqi_blocks);
-	info->u.v2_i.dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk);
-	info->u.v2_i.dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry);
+	info->u.v2_i.i.dqi_sb = sb;
+	info->u.v2_i.i.dqi_type = type;
+	info->u.v2_i.i.dqi_blocks = le32_to_cpu(dinfo.dqi_blocks);
+	info->u.v2_i.i.dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk);
+	info->u.v2_i.i.dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry);
+	info->u.v2_i.i.dqi_blocksize_bits = V2_DQBLKSIZE_BITS;
+	info->u.v2_i.i.dqi_usable_bs = 1 << V2_DQBLKSIZE_BITS;
+	info->u.v2_i.i.dqi_qtree_depth = qtree_depth(&info->u.v2_i.i);
+	info->u.v2_i.i.dqi_entry_size = sizeof(struct v2_disk_dqblk);
+	info->u.v2_i.i.dqi_ops = &v2_qtree_ops;
 	return 0;
 }
 
@@ -90,7 +103,7 @@ static int v2_read_file_info(struct super_block *sb, int type)
 static int v2_write_file_info(struct super_block *sb, int type)
 {
 	struct v2_disk_dqinfo dinfo;
-	struct mem_dqinfo *info = sb_dqopt(sb)->info+type;
+	struct mem_dqinfo *info = sb_dqinfo(sb, type);
 	ssize_t size;
 
 	spin_lock(&dq_data_lock);
@@ -99,9 +112,9 @@ static int v2_write_file_info(struct super_block *sb, int type)
 	dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace);
 	dinfo.dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK);
 	spin_unlock(&dq_data_lock);
-	dinfo.dqi_blocks = cpu_to_le32(info->u.v2_i.dqi_blocks);
-	dinfo.dqi_free_blk = cpu_to_le32(info->u.v2_i.dqi_free_blk);
-	dinfo.dqi_free_entry = cpu_to_le32(info->u.v2_i.dqi_free_entry);
+	dinfo.dqi_blocks = cpu_to_le32(info->u.v2_i.i.dqi_blocks);
+	dinfo.dqi_free_blk = cpu_to_le32(info->u.v2_i.i.dqi_free_blk);
+	dinfo.dqi_free_entry = cpu_to_le32(info->u.v2_i.i.dqi_free_entry);
 	size = sb->s_op->quota_write(sb, type, (char *)&dinfo,
 	       sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF);
 	if (size != sizeof(struct v2_disk_dqinfo)) {
@@ -112,8 +125,11 @@ static int v2_write_file_info(struct super_block *sb, int type)
 	return 0;
 }
 
-static void disk2memdqb(struct mem_dqblk *m, struct v2_disk_dqblk *d)
+static void v2_disk2memdqb(struct dquot *dquot, void *dp)
 {
+	struct v2_disk_dqblk *d = dp, empty;
+	struct mem_dqblk *m = &dquot->dq_dqb;
+
 	m->dqb_ihardlimit = le32_to_cpu(d->dqb_ihardlimit);
 	m->dqb_isoftlimit = le32_to_cpu(d->dqb_isoftlimit);
 	m->dqb_curinodes = le32_to_cpu(d->dqb_curinodes);
@@ -122,10 +138,20 @@ static void disk2memdqb(struct mem_dqblk *m, struct v2_disk_dqblk *d)
 	m->dqb_bsoftlimit = v2_qbtos(le32_to_cpu(d->dqb_bsoftlimit));
 	m->dqb_curspace = le64_to_cpu(d->dqb_curspace);
 	m->dqb_btime = le64_to_cpu(d->dqb_btime);
+	/* We need to escape back all-zero structure */
+	memset(&empty, 0, sizeof(struct v2_disk_dqblk));
+	empty.dqb_itime = cpu_to_le64(1);
+	if (!memcmp(&empty, dp, sizeof(struct v2_disk_dqblk)))
+		m->dqb_itime = 0;
 }
 
-static void mem2diskdqb(struct v2_disk_dqblk *d, struct mem_dqblk *m, qid_t id)
+static void v2_mem2diskdqb(void *dp, struct dquot *dquot)
 {
+	struct v2_disk_dqblk *d = dp;
+	struct mem_dqblk *m = &dquot->dq_dqb;
+	struct qtree_mem_dqinfo *info =
+			&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i;
+
 	d->dqb_ihardlimit = cpu_to_le32(m->dqb_ihardlimit);
 	d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit);
 	d->dqb_curinodes = cpu_to_le32(m->dqb_curinodes);
@@ -134,553 +160,35 @@ static void mem2diskdqb(struct v2_disk_dqblk *d, struct mem_dqblk *m, qid_t id)
 	d->dqb_bsoftlimit = cpu_to_le32(v2_stoqb(m->dqb_bsoftlimit));
 	d->dqb_curspace = cpu_to_le64(m->dqb_curspace);
 	d->dqb_btime = cpu_to_le64(m->dqb_btime);
-	d->dqb_id = cpu_to_le32(id);
-}
-
-static dqbuf_t getdqbuf(void)
-{
-	dqbuf_t buf = kmalloc(V2_DQBLKSIZE, GFP_NOFS);
-	if (!buf)
-		printk(KERN_WARNING "VFS: Not enough memory for quota buffers.\n");
-	return buf;
-}
-
-static inline void freedqbuf(dqbuf_t buf)
-{
-	kfree(buf);
-}
-
-static inline ssize_t read_blk(struct super_block *sb, int type, uint blk, dqbuf_t buf)
-{
-	memset(buf, 0, V2_DQBLKSIZE);
-	return sb->s_op->quota_read(sb, type, (char *)buf,
-	       V2_DQBLKSIZE, blk << V2_DQBLKSIZE_BITS);
-}
-
-static inline ssize_t write_blk(struct super_block *sb, int type, uint blk, dqbuf_t buf)
-{
-	return sb->s_op->quota_write(sb, type, (char *)buf,
-	       V2_DQBLKSIZE, blk << V2_DQBLKSIZE_BITS);
-}
-
-/* Remove empty block from list and return it */
-static int get_free_dqblk(struct super_block *sb, int type)
-{
-	dqbuf_t buf = getdqbuf();
-	struct mem_dqinfo *info = sb_dqinfo(sb, type);
-	struct v2_disk_dqdbheader *dh = (struct v2_disk_dqdbheader *)buf;
-	int ret, blk;
-
-	if (!buf)
-		return -ENOMEM;
-	if (info->u.v2_i.dqi_free_blk) {
-		blk = info->u.v2_i.dqi_free_blk;
-		if ((ret = read_blk(sb, type, blk, buf)) < 0)
-			goto out_buf;
-		info->u.v2_i.dqi_free_blk = le32_to_cpu(dh->dqdh_next_free);
-	}
-	else {
-		memset(buf, 0, V2_DQBLKSIZE);
-		/* Assure block allocation... */
-		if ((ret = write_blk(sb, type, info->u.v2_i.dqi_blocks, buf)) < 0)
-			goto out_buf;
-		blk = info->u.v2_i.dqi_blocks++;
-	}
-	mark_info_dirty(sb, type);
-	ret = blk;
-out_buf:
-	freedqbuf(buf);
-	return ret;
-}
-
-/* Insert empty block to the list */
-static int put_free_dqblk(struct super_block *sb, int type, dqbuf_t buf, uint blk)
-{
-	struct mem_dqinfo *info = sb_dqinfo(sb, type);
-	struct v2_disk_dqdbheader *dh = (struct v2_disk_dqdbheader *)buf;
-	int err;
-
-	dh->dqdh_next_free = cpu_to_le32(info->u.v2_i.dqi_free_blk);
-	dh->dqdh_prev_free = cpu_to_le32(0);
-	dh->dqdh_entries = cpu_to_le16(0);
-	info->u.v2_i.dqi_free_blk = blk;
-	mark_info_dirty(sb, type);
-	/* Some strange block. We had better leave it... */
-	if ((err = write_blk(sb, type, blk, buf)) < 0)
-		return err;
-	return 0;
+	d->dqb_id = cpu_to_le32(dquot->dq_id);
+	if (qtree_entry_unused(info, dp))
+		d->dqb_itime = cpu_to_le64(1);
 }
 
-/* Remove given block from the list of blocks with free entries */
-static int remove_free_dqentry(struct super_block *sb, int type, dqbuf_t buf, uint blk)
+static int v2_is_id(void *dp, struct dquot *dquot)
 {
-	dqbuf_t tmpbuf = getdqbuf();
-	struct mem_dqinfo *info = sb_dqinfo(sb, type);
-	struct v2_disk_dqdbheader *dh = (struct v2_disk_dqdbheader *)buf;
-	uint nextblk = le32_to_cpu(dh->dqdh_next_free), prevblk = le32_to_cpu(dh->dqdh_prev_free);
-	int err;
+	struct v2_disk_dqblk *d = dp;
+	struct qtree_mem_dqinfo *info =
+			&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i;
 
-	if (!tmpbuf)
-		return -ENOMEM;
-	if (nextblk) {
-		if ((err = read_blk(sb, type, nextblk, tmpbuf)) < 0)
-			goto out_buf;
-		((struct v2_disk_dqdbheader *)tmpbuf)->dqdh_prev_free = dh->dqdh_prev_free;
-		if ((err = write_blk(sb, type, nextblk, tmpbuf)) < 0)
-			goto out_buf;
-	}
-	if (prevblk) {
-		if ((err = read_blk(sb, type, prevblk, tmpbuf)) < 0)
-			goto out_buf;
-		((struct v2_disk_dqdbheader *)tmpbuf)->dqdh_next_free = dh->dqdh_next_free;
-		if ((err = write_blk(sb, type, prevblk, tmpbuf)) < 0)
-			goto out_buf;
-	}
-	else {
-		info->u.v2_i.dqi_free_entry = nextblk;
-		mark_info_dirty(sb, type);
-	}
-	freedqbuf(tmpbuf);
-	dh->dqdh_next_free = dh->dqdh_prev_free = cpu_to_le32(0);
-	/* No matter whether write succeeds block is out of list */
-	if (write_blk(sb, type, blk, buf) < 0)
-		printk(KERN_ERR "VFS: Can't write block (%u) with free entries.\n", blk);
-	return 0;
-out_buf:
-	freedqbuf(tmpbuf);
-	return err;
-}
-
-/* Insert given block to the beginning of list with free entries */
-static int insert_free_dqentry(struct super_block *sb, int type, dqbuf_t buf, uint blk)
-{
-	dqbuf_t tmpbuf = getdqbuf();
-	struct mem_dqinfo *info = sb_dqinfo(sb, type);
-	struct v2_disk_dqdbheader *dh = (struct v2_disk_dqdbheader *)buf;
-	int err;
-
-	if (!tmpbuf)
-		return -ENOMEM;
-	dh->dqdh_next_free = cpu_to_le32(info->u.v2_i.dqi_free_entry);
-	dh->dqdh_prev_free = cpu_to_le32(0);
-	if ((err = write_blk(sb, type, blk, buf)) < 0)
-		goto out_buf;
-	if (info->u.v2_i.dqi_free_entry) {
-		if ((err = read_blk(sb, type, info->u.v2_i.dqi_free_entry, tmpbuf)) < 0)
-			goto out_buf;
-		((struct v2_disk_dqdbheader *)tmpbuf)->dqdh_prev_free = cpu_to_le32(blk);
-		if ((err = write_blk(sb, type, info->u.v2_i.dqi_free_entry, tmpbuf)) < 0)
-			goto out_buf;
-	}
-	freedqbuf(tmpbuf);
-	info->u.v2_i.dqi_free_entry = blk;
-	mark_info_dirty(sb, type);
-	return 0;
-out_buf:
-	freedqbuf(tmpbuf);
-	return err;
-}
-
-/* Find space for dquot */
-static uint find_free_dqentry(struct dquot *dquot, int *err)
-{
-	struct super_block *sb = dquot->dq_sb;
-	struct mem_dqinfo *info = sb_dqopt(sb)->info+dquot->dq_type;
-	uint blk, i;
-	struct v2_disk_dqdbheader *dh;
-	struct v2_disk_dqblk *ddquot;
-	struct v2_disk_dqblk fakedquot;
-	dqbuf_t buf;
-
-	*err = 0;
-	if (!(buf = getdqbuf())) {
-		*err = -ENOMEM;
+	if (qtree_entry_unused(info, dp))
 		return 0;
-	}
-	dh = (struct v2_disk_dqdbheader *)buf;
-	ddquot = GETENTRIES(buf);
-	if (info->u.v2_i.dqi_free_entry) {
-		blk = info->u.v2_i.dqi_free_entry;
-		if ((*err = read_blk(sb, dquot->dq_type, blk, buf)) < 0)
-			goto out_buf;
-	}
-	else {
-		blk = get_free_dqblk(sb, dquot->dq_type);
-		if ((int)blk < 0) {
-			*err = blk;
-			freedqbuf(buf);
-			return 0;
-		}
-		memset(buf, 0, V2_DQBLKSIZE);
-		/* This is enough as block is already zeroed and entry list is empty... */
-		info->u.v2_i.dqi_free_entry = blk;
-		mark_info_dirty(sb, dquot->dq_type);
-	}
-	if (le16_to_cpu(dh->dqdh_entries)+1 >= V2_DQSTRINBLK)	/* Block will be full? */
-		if ((*err = remove_free_dqentry(sb, dquot->dq_type, buf, blk)) < 0) {
-			printk(KERN_ERR "VFS: find_free_dqentry(): Can't remove block (%u) from entry free list.\n", blk);
-			goto out_buf;
-		}
-	le16_add_cpu(&dh->dqdh_entries, 1);
-	memset(&fakedquot, 0, sizeof(struct v2_disk_dqblk));
-	/* Find free structure in block */
-	for (i = 0; i < V2_DQSTRINBLK && memcmp(&fakedquot, ddquot+i, sizeof(struct v2_disk_dqblk)); i++);
-#ifdef __QUOTA_V2_PARANOIA
-	if (i == V2_DQSTRINBLK) {
-		printk(KERN_ERR "VFS: find_free_dqentry(): Data block full but it shouldn't.\n");
-		*err = -EIO;
-		goto out_buf;
-	}
-#endif
-	if ((*err = write_blk(sb, dquot->dq_type, blk, buf)) < 0) {
-		printk(KERN_ERR "VFS: find_free_dqentry(): Can't write quota data block %u.\n", blk);
-		goto out_buf;
-	}
-	dquot->dq_off = (blk<<V2_DQBLKSIZE_BITS)+sizeof(struct v2_disk_dqdbheader)+i*sizeof(struct v2_disk_dqblk);
-	freedqbuf(buf);
-	return blk;
-out_buf:
-	freedqbuf(buf);
-	return 0;
+	return le32_to_cpu(d->dqb_id) == dquot->dq_id;
 }
 
-/* Insert reference to structure into the trie */
-static int do_insert_tree(struct dquot *dquot, uint *treeblk, int depth)
-{
-	struct super_block *sb = dquot->dq_sb;
-	dqbuf_t buf;
-	int ret = 0, newson = 0, newact = 0;
-	__le32 *ref;
-	uint newblk;
-
-	if (!(buf = getdqbuf()))
-		return -ENOMEM;
-	if (!*treeblk) {
-		ret = get_free_dqblk(sb, dquot->dq_type);
-		if (ret < 0)
-			goto out_buf;
-		*treeblk = ret;
-		memset(buf, 0, V2_DQBLKSIZE);
-		newact = 1;
-	}
-	else {
-		if ((ret = read_blk(sb, dquot->dq_type, *treeblk, buf)) < 0) {
-			printk(KERN_ERR "VFS: Can't read tree quota block %u.\n", *treeblk);
-			goto out_buf;
-		}
-	}
-	ref = (__le32 *)buf;
-	newblk = le32_to_cpu(ref[GETIDINDEX(dquot->dq_id, depth)]);
-	if (!newblk)
-		newson = 1;
-	if (depth == V2_DQTREEDEPTH-1) {
-#ifdef __QUOTA_V2_PARANOIA
-		if (newblk) {
-			printk(KERN_ERR "VFS: Inserting already present quota entry (block %u).\n", le32_to_cpu(ref[GETIDINDEX(dquot->dq_id, depth)]));
-			ret = -EIO;
-			goto out_buf;
-		}
-#endif
-		newblk = find_free_dqentry(dquot, &ret);
-	}
-	else
-		ret = do_insert_tree(dquot, &newblk, depth+1);
-	if (newson && ret >= 0) {
-		ref[GETIDINDEX(dquot->dq_id, depth)] = cpu_to_le32(newblk);
-		ret = write_blk(sb, dquot->dq_type, *treeblk, buf);
-	}
-	else if (newact && ret < 0)
-		put_free_dqblk(sb, dquot->dq_type, buf, *treeblk);
-out_buf:
-	freedqbuf(buf);
-	return ret;
-}
-
-/* Wrapper for inserting quota structure into tree */
-static inline int dq_insert_tree(struct dquot *dquot)
+static int v2_read_dquot(struct dquot *dquot)
 {
-	int tmp = V2_DQTREEOFF;
-	return do_insert_tree(dquot, &tmp, 0);
+	return qtree_read_dquot(&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i, dquot);
 }
 
-/*
- *	We don't have to be afraid of deadlocks as we never have quotas on quota files...
- */
 static int v2_write_dquot(struct dquot *dquot)
 {
-	int type = dquot->dq_type;
-	ssize_t ret;
-	struct v2_disk_dqblk ddquot, empty;
-
-	/* dq_off is guarded by dqio_mutex */
-	if (!dquot->dq_off)
-		if ((ret = dq_insert_tree(dquot)) < 0) {
-			printk(KERN_ERR "VFS: Error %zd occurred while creating quota.\n", ret);
-			return ret;
-		}
-	spin_lock(&dq_data_lock);
-	mem2diskdqb(&ddquot, &dquot->dq_dqb, dquot->dq_id);
-	/* Argh... We may need to write structure full of zeroes but that would be
-	 * treated as an empty place by the rest of the code. Format change would
-	 * be definitely cleaner but the problems probably are not worth it */
-	memset(&empty, 0, sizeof(struct v2_disk_dqblk));
-	if (!memcmp(&empty, &ddquot, sizeof(struct v2_disk_dqblk)))
-		ddquot.dqb_itime = cpu_to_le64(1);
-	spin_unlock(&dq_data_lock);
-	ret = dquot->dq_sb->s_op->quota_write(dquot->dq_sb, type,
-	      (char *)&ddquot, sizeof(struct v2_disk_dqblk), dquot->dq_off);
-	if (ret != sizeof(struct v2_disk_dqblk)) {
-		printk(KERN_WARNING "VFS: dquota write failed on dev %s\n", dquot->dq_sb->s_id);
-		if (ret >= 0)
-			ret = -ENOSPC;
-	}
-	else
-		ret = 0;
-	dqstats.writes++;
-
-	return ret;
+	return qtree_write_dquot(&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i, dquot);
 }
 
-/* Free dquot entry in data block */
-static int free_dqentry(struct dquot *dquot, uint blk)
-{
-	struct super_block *sb = dquot->dq_sb;
-	int type = dquot->dq_type;
-	struct v2_disk_dqdbheader *dh;
-	dqbuf_t buf = getdqbuf();
-	int ret = 0;
-
-	if (!buf)
-		return -ENOMEM;
-	if (dquot->dq_off >> V2_DQBLKSIZE_BITS != blk) {
-		printk(KERN_ERR "VFS: Quota structure has offset to other "
-		  "block (%u) than it should (%u).\n", blk,
-		  (uint)(dquot->dq_off >> V2_DQBLKSIZE_BITS));
-		goto out_buf;
-	}
-	if ((ret = read_blk(sb, type, blk, buf)) < 0) {
-		printk(KERN_ERR "VFS: Can't read quota data block %u\n", blk);
-		goto out_buf;
-	}
-	dh = (struct v2_disk_dqdbheader *)buf;
-	le16_add_cpu(&dh->dqdh_entries, -1);
-	if (!le16_to_cpu(dh->dqdh_entries)) {	/* Block got free? */
-		if ((ret = remove_free_dqentry(sb, type, buf, blk)) < 0 ||
-		    (ret = put_free_dqblk(sb, type, buf, blk)) < 0) {
-			printk(KERN_ERR "VFS: Can't move quota data block (%u) "
-			  "to free list.\n", blk);
-			goto out_buf;
-		}
-	}
-	else {
-		memset(buf+(dquot->dq_off & ((1 << V2_DQBLKSIZE_BITS)-1)), 0,
-		  sizeof(struct v2_disk_dqblk));
-		if (le16_to_cpu(dh->dqdh_entries) == V2_DQSTRINBLK-1) {
-			/* Insert will write block itself */
-			if ((ret = insert_free_dqentry(sb, type, buf, blk)) < 0) {
-				printk(KERN_ERR "VFS: Can't insert quota data block (%u) to free entry list.\n", blk);
-				goto out_buf;
-			}
-		}
-		else
-			if ((ret = write_blk(sb, type, blk, buf)) < 0) {
-				printk(KERN_ERR "VFS: Can't write quota data "
-				  "block %u\n", blk);
-				goto out_buf;
-			}
-	}
-	dquot->dq_off = 0;	/* Quota is now unattached */
-out_buf:
-	freedqbuf(buf);
-	return ret;
-}
-
-/* Remove reference to dquot from tree */
-static int remove_tree(struct dquot *dquot, uint *blk, int depth)
-{
-	struct super_block *sb = dquot->dq_sb;
-	int type = dquot->dq_type;
-	dqbuf_t buf = getdqbuf();
-	int ret = 0;
-	uint newblk;
-	__le32 *ref = (__le32 *)buf;
-	
-	if (!buf)
-		return -ENOMEM;
-	if ((ret = read_blk(sb, type, *blk, buf)) < 0) {
-		printk(KERN_ERR "VFS: Can't read quota data block %u\n", *blk);
-		goto out_buf;
-	}
-	newblk = le32_to_cpu(ref[GETIDINDEX(dquot->dq_id, depth)]);
-	if (depth == V2_DQTREEDEPTH-1) {
-		ret = free_dqentry(dquot, newblk);
-		newblk = 0;
-	}
-	else
-		ret = remove_tree(dquot, &newblk, depth+1);
-	if (ret >= 0 && !newblk) {
-		int i;
-		ref[GETIDINDEX(dquot->dq_id, depth)] = cpu_to_le32(0);
-		for (i = 0; i < V2_DQBLKSIZE && !buf[i]; i++);	/* Block got empty? */
-		/* Don't put the root block into the free block list */
-		if (i == V2_DQBLKSIZE && *blk != V2_DQTREEOFF) {
-			put_free_dqblk(sb, type, buf, *blk);
-			*blk = 0;
-		}
-		else
-			if ((ret = write_blk(sb, type, *blk, buf)) < 0)
-				printk(KERN_ERR "VFS: Can't write quota tree "
-				  "block %u.\n", *blk);
-	}
-out_buf:
-	freedqbuf(buf);
-	return ret;	
-}
-
-/* Delete dquot from tree */
-static int v2_delete_dquot(struct dquot *dquot)
-{
-	uint tmp = V2_DQTREEOFF;
-
-	if (!dquot->dq_off)	/* Even not allocated? */
-		return 0;
-	return remove_tree(dquot, &tmp, 0);
-}
-
-/* Find entry in block */
-static loff_t find_block_dqentry(struct dquot *dquot, uint blk)
-{
-	dqbuf_t buf = getdqbuf();
-	loff_t ret = 0;
-	int i;
-	struct v2_disk_dqblk *ddquot = GETENTRIES(buf);
-
-	if (!buf)
-		return -ENOMEM;
-	if ((ret = read_blk(dquot->dq_sb, dquot->dq_type, blk, buf)) < 0) {
-		printk(KERN_ERR "VFS: Can't read quota tree block %u.\n", blk);
-		goto out_buf;
-	}
-	if (dquot->dq_id)
-		for (i = 0; i < V2_DQSTRINBLK &&
-		     le32_to_cpu(ddquot[i].dqb_id) != dquot->dq_id; i++);
-	else {	/* ID 0 as a bit more complicated searching... */
-		struct v2_disk_dqblk fakedquot;
-
-		memset(&fakedquot, 0, sizeof(struct v2_disk_dqblk));
-		for (i = 0; i < V2_DQSTRINBLK; i++)
-			if (!le32_to_cpu(ddquot[i].dqb_id) &&
-			    memcmp(&fakedquot, ddquot+i, sizeof(struct v2_disk_dqblk)))
-				break;
-	}
-	if (i == V2_DQSTRINBLK) {
-		printk(KERN_ERR "VFS: Quota for id %u referenced "
-		  "but not present.\n", dquot->dq_id);
-		ret = -EIO;
-		goto out_buf;
-	}
-	else
-		ret = (blk << V2_DQBLKSIZE_BITS) + sizeof(struct
-		  v2_disk_dqdbheader) + i * sizeof(struct v2_disk_dqblk);
-out_buf:
-	freedqbuf(buf);
-	return ret;
-}
-
-/* Find entry for given id in the tree */
-static loff_t find_tree_dqentry(struct dquot *dquot, uint blk, int depth)
-{
-	dqbuf_t buf = getdqbuf();
-	loff_t ret = 0;
-	__le32 *ref = (__le32 *)buf;
-
-	if (!buf)
-		return -ENOMEM;
-	if ((ret = read_blk(dquot->dq_sb, dquot->dq_type, blk, buf)) < 0) {
-		printk(KERN_ERR "VFS: Can't read quota tree block %u.\n", blk);
-		goto out_buf;
-	}
-	ret = 0;
-	blk = le32_to_cpu(ref[GETIDINDEX(dquot->dq_id, depth)]);
-	if (!blk)	/* No reference? */
-		goto out_buf;
-	if (depth < V2_DQTREEDEPTH-1)
-		ret = find_tree_dqentry(dquot, blk, depth+1);
-	else
-		ret = find_block_dqentry(dquot, blk);
-out_buf:
-	freedqbuf(buf);
-	return ret;
-}
-
-/* Find entry for given id in the tree - wrapper function */
-static inline loff_t find_dqentry(struct dquot *dquot)
-{
-	return find_tree_dqentry(dquot, V2_DQTREEOFF, 0);
-}
-
-static int v2_read_dquot(struct dquot *dquot)
-{
-	int type = dquot->dq_type;
-	loff_t offset;
-	struct v2_disk_dqblk ddquot, empty;
-	int ret = 0;
-
-#ifdef __QUOTA_V2_PARANOIA
-	/* Invalidated quota? */
-	if (!dquot->dq_sb || !sb_dqopt(dquot->dq_sb)->files[type]) {
-		printk(KERN_ERR "VFS: Quota invalidated while reading!\n");
-		return -EIO;
-	}
-#endif
-	offset = find_dqentry(dquot);
-	if (offset <= 0) {	/* Entry not present? */
-		if (offset < 0)
-			printk(KERN_ERR "VFS: Can't read quota "
-			  "structure for id %u.\n", dquot->dq_id);
-		dquot->dq_off = 0;
-		set_bit(DQ_FAKE_B, &dquot->dq_flags);
-		memset(&dquot->dq_dqb, 0, sizeof(struct mem_dqblk));
-		ret = offset;
-	}
-	else {
-		dquot->dq_off = offset;
-		if ((ret = dquot->dq_sb->s_op->quota_read(dquot->dq_sb, type,
-		    (char *)&ddquot, sizeof(struct v2_disk_dqblk), offset))
-		    != sizeof(struct v2_disk_dqblk)) {
-			if (ret >= 0)
-				ret = -EIO;
-			printk(KERN_ERR "VFS: Error while reading quota "
-			  "structure for id %u.\n", dquot->dq_id);
-			memset(&ddquot, 0, sizeof(struct v2_disk_dqblk));
-		}
-		else {
-			ret = 0;
-			/* We need to escape back all-zero structure */
-			memset(&empty, 0, sizeof(struct v2_disk_dqblk));
-			empty.dqb_itime = cpu_to_le64(1);
-			if (!memcmp(&empty, &ddquot, sizeof(struct v2_disk_dqblk)))
-				ddquot.dqb_itime = 0;
-		}
-		disk2memdqb(&dquot->dq_dqb, &ddquot);
-		if (!dquot->dq_dqb.dqb_bhardlimit &&
-			!dquot->dq_dqb.dqb_bsoftlimit &&
-			!dquot->dq_dqb.dqb_ihardlimit &&
-			!dquot->dq_dqb.dqb_isoftlimit)
-			set_bit(DQ_FAKE_B, &dquot->dq_flags);
-	}
-	dqstats.reads++;
-
-	return ret;
-}
-
-/* Check whether dquot should not be deleted. We know we are
- * the only one operating on dquot (thanks to dq_lock) */
 static int v2_release_dquot(struct dquot *dquot)
 {
-	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) && !(dquot->dq_dqb.dqb_curinodes | dquot->dq_dqb.dqb_curspace))
-		return v2_delete_dquot(dquot);
-	return 0;
+	return qtree_release_dquot(&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i, dquot);
 }
 
 static struct quota_format_ops v2_format_ops = {
diff --git a/fs/quotaio_v2.h b/fs/quotaio_v2.h
index 303d7cbe30d4..530fe580685c 100644
--- a/fs/quotaio_v2.h
+++ b/fs/quotaio_v2.h
@@ -21,6 +21,12 @@
 	0		/* GRPQUOTA */\
 }
 
+/* First generic header */
+struct v2_disk_dqheader {
+	__le32 dqh_magic;	/* Magic number identifying file */
+	__le32 dqh_version;	/* File version */
+};
+
 /*
  * The following structure defines the format of the disk quota file
  * (as it appears on disk) - the file is a radix tree whose leaves point
@@ -38,15 +44,6 @@ struct v2_disk_dqblk {
 	__le64 dqb_itime;	/* time limit for excessive inode use */
 };
 
-/*
- * Here are header structures as written on disk and their in-memory copies
- */
-/* First generic header */
-struct v2_disk_dqheader {
-	__le32 dqh_magic;	/* Magic number identifying file */
-	__le32 dqh_version;	/* File version */
-};
-
 /* Header with type and version specific information */
 struct v2_disk_dqinfo {
 	__le32 dqi_bgrace;	/* Time before block soft limit becomes hard limit */
@@ -57,23 +54,7 @@ struct v2_disk_dqinfo {
 	__le32 dqi_free_entry;	/* Number of block with at least one free entry */
 };
 
-/*
- *  Structure of header of block with quota structures. It is padded to 16 bytes so
- *  there will be space for exactly 21 quota-entries in a block
- */
-struct v2_disk_dqdbheader {
-	__le32 dqdh_next_free;	/* Number of next block with free entry */
-	__le32 dqdh_prev_free;	/* Number of previous block with free entry */
-	__le16 dqdh_entries;	/* Number of valid entries in block */
-	__le16 dqdh_pad1;
-	__le32 dqdh_pad2;
-};
-
 #define V2_DQINFOOFF	sizeof(struct v2_disk_dqheader)	/* Offset of info header in file */
-#define V2_DQBLKSIZE_BITS	10
-#define V2_DQBLKSIZE	(1 << V2_DQBLKSIZE_BITS)	/* Size of block with quota structures */
-#define V2_DQTREEOFF	1		/* Offset of tree in file in blocks */
-#define V2_DQTREEDEPTH	4		/* Depth of quota tree */
-#define V2_DQSTRINBLK	((V2_DQBLKSIZE - sizeof(struct v2_disk_dqdbheader)) / sizeof(struct v2_disk_dqblk))	/* Number of entries in one blocks */
+#define V2_DQBLKSIZE_BITS 10				/* Size of leaf block in tree */
 
 #endif /* _LINUX_QUOTAIO_V2_H */
diff --git a/include/linux/dqblk_qtree.h b/include/linux/dqblk_qtree.h
new file mode 100644
index 000000000000..82a16527b367
--- /dev/null
+++ b/include/linux/dqblk_qtree.h
@@ -0,0 +1,56 @@
+/*
+ *	Definitions of structures and functions for quota formats using trie
+ */
+
+#ifndef _LINUX_DQBLK_QTREE_H
+#define _LINUX_DQBLK_QTREE_H
+
+#include <linux/types.h>
+
+/* Numbers of blocks needed for updates - we count with the smallest
+ * possible block size (1024) */
+#define QTREE_INIT_ALLOC 4
+#define QTREE_INIT_REWRITE 2
+#define QTREE_DEL_ALLOC 0
+#define QTREE_DEL_REWRITE 6
+
+struct dquot;
+
+/* Operations */
+struct qtree_fmt_operations {
+	void (*mem2disk_dqblk)(void *disk, struct dquot *dquot);	/* Convert given entry from in memory format to disk one */
+	void (*disk2mem_dqblk)(struct dquot *dquot, void *disk);	/* Convert given entry from disk format to in memory one */
+	int (*is_id)(void *disk, struct dquot *dquot);	/* Is this structure for given id? */
+};
+
+/* Inmemory copy of version specific information */
+struct qtree_mem_dqinfo {
+	struct super_block *dqi_sb;	/* Sb quota is on */
+	int dqi_type;			/* Quota type */
+	unsigned int dqi_blocks;	/* # of blocks in quota file */
+	unsigned int dqi_free_blk;	/* First block in list of free blocks */
+	unsigned int dqi_free_entry;	/* First block with free entry */
+	unsigned int dqi_blocksize_bits;	/* Block size of quota file */
+	unsigned int dqi_entry_size;	/* Size of quota entry in quota file */
+	unsigned int dqi_usable_bs;	/* Space usable in block for quota data */
+	unsigned int dqi_qtree_depth;	/* Precomputed depth of quota tree */
+	struct qtree_fmt_operations *dqi_ops;	/* Operations for entry manipulation */
+};
+
+int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot);
+int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot);
+int qtree_delete_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot);
+int qtree_release_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot);
+int qtree_entry_unused(struct qtree_mem_dqinfo *info, char *disk);
+static inline int qtree_depth(struct qtree_mem_dqinfo *info)
+{
+	unsigned int epb = info->dqi_usable_bs >> 2;
+	unsigned long long entries = epb;
+	int i;
+
+	for (i = 1; entries < (1ULL << 32); i++)
+		entries *= epb;
+	return i;
+}
+
+#endif /* _LINUX_DQBLK_QTREE_H */
diff --git a/include/linux/dqblk_v2.h b/include/linux/dqblk_v2.h
index 4f853322cb7f..e5e22a787d58 100644
--- a/include/linux/dqblk_v2.h
+++ b/include/linux/dqblk_v2.h
@@ -1,26 +1,23 @@
 /*
- *	Definitions of structures for vfsv0 quota format
+ *  Definitions for vfsv0 quota format
  */
 
 #ifndef _LINUX_DQBLK_V2_H
 #define _LINUX_DQBLK_V2_H
 
-#include <linux/types.h>
+#include <linux/dqblk_qtree.h>
 
-/* id numbers of quota format */
+/* Id number of quota format */
 #define QFMT_VFS_V0 2
 
 /* Numbers of blocks needed for updates */
-#define V2_INIT_ALLOC 4
-#define V2_INIT_REWRITE 2
-#define V2_DEL_ALLOC 0
-#define V2_DEL_REWRITE 6
+#define V2_INIT_ALLOC QTREE_INIT_ALLOC
+#define V2_INIT_REWRITE QTREE_INIT_REWRITE
+#define V2_DEL_ALLOC QTREE_DEL_ALLOC
+#define V2_DEL_REWRITE QTREE_DEL_REWRITE
 
-/* Inmemory copy of version specific information */
 struct v2_mem_dqinfo {
-	unsigned int dqi_blocks;
-	unsigned int dqi_free_blk;
-	unsigned int dqi_free_entry;
+	struct qtree_mem_dqinfo i;
 };
 
 #endif /* _LINUX_DQBLK_V2_H */
-- 
cgit v1.2.3-70-g09d2


From e3d4d56b9715e40ded2a84d0d4fa7f3b6c58983c Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 2 Oct 2008 18:44:14 +0200
Subject: quota: Convert union in mem_dqinfo to a pointer

Coming quota support for OCFS2 is going to need quite a bit
of additional per-sb quota information. Moreover having fs.h
include all the types needed for this structure would be a
pain in the a**. So remove the union from mem_dqinfo and add
a private pointer for filesystem's use.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/quota_v2.c            | 53 +++++++++++++++++++++++++++++++-----------------
 include/linux/dqblk_v1.h |  4 ----
 include/linux/dqblk_v2.h |  4 ----
 include/linux/quota.h    |  5 +----
 4 files changed, 35 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/fs/quota_v2.c b/fs/quota_v2.c
index a87f1028a425..b618b563635c 100644
--- a/fs/quota_v2.c
+++ b/fs/quota_v2.c
@@ -71,6 +71,7 @@ static int v2_read_file_info(struct super_block *sb, int type)
 {
 	struct v2_disk_dqinfo dinfo;
 	struct mem_dqinfo *info = sb_dqinfo(sb, type);
+	struct qtree_mem_dqinfo *qinfo;
 	ssize_t size;
 
 	size = sb->s_op->quota_read(sb, type, (char *)&dinfo,
@@ -80,22 +81,29 @@ static int v2_read_file_info(struct super_block *sb, int type)
 			sb->s_id);
 		return -1;
 	}
+	info->dqi_priv = kmalloc(sizeof(struct qtree_mem_dqinfo), GFP_NOFS);
+	if (!info->dqi_priv) {
+		printk(KERN_WARNING
+		       "Not enough memory for quota information structure.\n");
+		return -1;
+	}
+	qinfo = info->dqi_priv;
 	/* limits are stored as unsigned 32-bit data */
 	info->dqi_maxblimit = 0xffffffff;
 	info->dqi_maxilimit = 0xffffffff;
 	info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
 	info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
 	info->dqi_flags = le32_to_cpu(dinfo.dqi_flags);
-	info->u.v2_i.i.dqi_sb = sb;
-	info->u.v2_i.i.dqi_type = type;
-	info->u.v2_i.i.dqi_blocks = le32_to_cpu(dinfo.dqi_blocks);
-	info->u.v2_i.i.dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk);
-	info->u.v2_i.i.dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry);
-	info->u.v2_i.i.dqi_blocksize_bits = V2_DQBLKSIZE_BITS;
-	info->u.v2_i.i.dqi_usable_bs = 1 << V2_DQBLKSIZE_BITS;
-	info->u.v2_i.i.dqi_qtree_depth = qtree_depth(&info->u.v2_i.i);
-	info->u.v2_i.i.dqi_entry_size = sizeof(struct v2_disk_dqblk);
-	info->u.v2_i.i.dqi_ops = &v2_qtree_ops;
+	qinfo->dqi_sb = sb;
+	qinfo->dqi_type = type;
+	qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks);
+	qinfo->dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk);
+	qinfo->dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry);
+	qinfo->dqi_blocksize_bits = V2_DQBLKSIZE_BITS;
+	qinfo->dqi_usable_bs = 1 << V2_DQBLKSIZE_BITS;
+	qinfo->dqi_qtree_depth = qtree_depth(qinfo);
+	qinfo->dqi_entry_size = sizeof(struct v2_disk_dqblk);
+	qinfo->dqi_ops = &v2_qtree_ops;
 	return 0;
 }
 
@@ -104,6 +112,7 @@ static int v2_write_file_info(struct super_block *sb, int type)
 {
 	struct v2_disk_dqinfo dinfo;
 	struct mem_dqinfo *info = sb_dqinfo(sb, type);
+	struct qtree_mem_dqinfo *qinfo = info->dqi_priv;
 	ssize_t size;
 
 	spin_lock(&dq_data_lock);
@@ -112,9 +121,9 @@ static int v2_write_file_info(struct super_block *sb, int type)
 	dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace);
 	dinfo.dqi_flags = cpu_to_le32(info->dqi_flags & DQF_MASK);
 	spin_unlock(&dq_data_lock);
-	dinfo.dqi_blocks = cpu_to_le32(info->u.v2_i.i.dqi_blocks);
-	dinfo.dqi_free_blk = cpu_to_le32(info->u.v2_i.i.dqi_free_blk);
-	dinfo.dqi_free_entry = cpu_to_le32(info->u.v2_i.i.dqi_free_entry);
+	dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks);
+	dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk);
+	dinfo.dqi_free_entry = cpu_to_le32(qinfo->dqi_free_entry);
 	size = sb->s_op->quota_write(sb, type, (char *)&dinfo,
 	       sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF);
 	if (size != sizeof(struct v2_disk_dqinfo)) {
@@ -150,7 +159,7 @@ static void v2_mem2diskdqb(void *dp, struct dquot *dquot)
 	struct v2_disk_dqblk *d = dp;
 	struct mem_dqblk *m = &dquot->dq_dqb;
 	struct qtree_mem_dqinfo *info =
-			&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i;
+			sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv;
 
 	d->dqb_ihardlimit = cpu_to_le32(m->dqb_ihardlimit);
 	d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit);
@@ -169,7 +178,7 @@ static int v2_is_id(void *dp, struct dquot *dquot)
 {
 	struct v2_disk_dqblk *d = dp;
 	struct qtree_mem_dqinfo *info =
-			&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i;
+			sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv;
 
 	if (qtree_entry_unused(info, dp))
 		return 0;
@@ -178,24 +187,30 @@ static int v2_is_id(void *dp, struct dquot *dquot)
 
 static int v2_read_dquot(struct dquot *dquot)
 {
-	return qtree_read_dquot(&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i, dquot);
+	return qtree_read_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv, dquot);
 }
 
 static int v2_write_dquot(struct dquot *dquot)
 {
-	return qtree_write_dquot(&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i, dquot);
+	return qtree_write_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv, dquot);
 }
 
 static int v2_release_dquot(struct dquot *dquot)
 {
-	return qtree_release_dquot(&sb_dqinfo(dquot->dq_sb, dquot->dq_type)->u.v2_i.i, dquot);
+	return qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv, dquot);
+}
+
+static int v2_free_file_info(struct super_block *sb, int type)
+{
+	kfree(sb_dqinfo(sb, type)->dqi_priv);
+	return 0;
 }
 
 static struct quota_format_ops v2_format_ops = {
 	.check_quota_file	= v2_check_quota_file,
 	.read_file_info		= v2_read_file_info,
 	.write_file_info	= v2_write_file_info,
-	.free_file_info		= NULL,
+	.free_file_info		= v2_free_file_info,
 	.read_dqblk		= v2_read_dquot,
 	.commit_dqblk		= v2_write_dquot,
 	.release_dqblk		= v2_release_dquot,
diff --git a/include/linux/dqblk_v1.h b/include/linux/dqblk_v1.h
index 57f1250d5a52..9cea901f5bba 100644
--- a/include/linux/dqblk_v1.h
+++ b/include/linux/dqblk_v1.h
@@ -17,8 +17,4 @@
 #define V1_DEL_ALLOC 0
 #define V1_DEL_REWRITE 2
 
-/* Special information about quotafile */
-struct v1_mem_dqinfo {
-};
-
 #endif	/* _LINUX_DQBLK_V1_H */
diff --git a/include/linux/dqblk_v2.h b/include/linux/dqblk_v2.h
index e5e22a787d58..ff8af1b4bda7 100644
--- a/include/linux/dqblk_v2.h
+++ b/include/linux/dqblk_v2.h
@@ -16,8 +16,4 @@
 #define V2_DEL_ALLOC QTREE_DEL_ALLOC
 #define V2_DEL_REWRITE QTREE_DEL_REWRITE
 
-struct v2_mem_dqinfo {
-	struct qtree_mem_dqinfo i;
-};
-
 #endif /* _LINUX_DQBLK_V2_H */
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 80b8807b4988..e51dfdc0aef0 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -208,10 +208,7 @@ struct mem_dqinfo {
 	unsigned int dqi_igrace;
 	qsize_t dqi_maxblimit;
 	qsize_t dqi_maxilimit;
-	union {
-		struct v1_mem_dqinfo v1_i;
-		struct v2_mem_dqinfo v2_i;
-	} u;
+	void *dqi_priv;
 };
 
 struct super_block;
-- 
cgit v1.2.3-70-g09d2


From db49d2df489f727096438706a5428115e84a3f0d Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 1 Oct 2008 18:21:39 +0200
Subject: quota: Allow negative usage of space and inodes

For clustered filesystems, it can happen that space / inode usage goes
negative temporarily (because some node is allocating another node
is freeing and they are not completely in sync). So let quota code
allow this and change qsize_t so a signed type so that we don't
underflow the variables.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c            | 6 ++++--
 include/linux/quota.h | 3 ++-
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index 74185c34a4f0..9c78ffe1aad2 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -847,7 +847,8 @@ static inline void dquot_incr_space(struct dquot *dquot, qsize_t number)
 
 static inline void dquot_decr_inodes(struct dquot *dquot, qsize_t number)
 {
-	if (dquot->dq_dqb.dqb_curinodes > number)
+	if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE ||
+	    dquot->dq_dqb.dqb_curinodes >= number)
 		dquot->dq_dqb.dqb_curinodes -= number;
 	else
 		dquot->dq_dqb.dqb_curinodes = 0;
@@ -858,7 +859,8 @@ static inline void dquot_decr_inodes(struct dquot *dquot, qsize_t number)
 
 static inline void dquot_decr_space(struct dquot *dquot, qsize_t number)
 {
-	if (dquot->dq_dqb.dqb_curspace > number)
+	if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE ||
+	    dquot->dq_dqb.dqb_curspace >= number)
 		dquot->dq_dqb.dqb_curspace -= number;
 	else
 		dquot->dq_dqb.dqb_curspace = 0;
diff --git a/include/linux/quota.h b/include/linux/quota.h
index e51dfdc0aef0..75bf761caef2 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -168,7 +168,7 @@ enum {
 #include <asm/atomic.h>
 
 typedef __kernel_uid32_t qid_t; /* Type in which we store ids in memory */
-typedef __u64 qsize_t;          /* Type in which we store sizes */
+typedef long long qsize_t;	/* Type in which we store sizes */
 
 extern spinlock_t dq_data_lock;
 
@@ -336,6 +336,7 @@ enum {
 						 * responsible for setting
 						 * S_NOQUOTA, S_NOATIME flags
 						 */
+#define DQUOT_NEGATIVE_USAGE	(1 << 7)	/* Allow negative quota usage */
 
 static inline unsigned int dquot_state_flag(unsigned int flags, int type)
 {
-- 
cgit v1.2.3-70-g09d2


From 4d59bce4f9eaf26d6d9046b56a2f1c0c7f20981d Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 2 Oct 2008 16:48:10 +0200
Subject: quota: Keep which entries were set by SETQUOTA quotactl

Quota in a clustered environment needs to synchronize quota information
among cluster nodes. This means we have to occasionally update some
information in dquot from disk / network. On the other hand we have to
be careful not to overwrite changes administrator did via SETQUOTA.
So indicate in dquot->dq_flags which entries have been set by SETQUOTA
and quota format can clear these flags when it properly propagated
the changes.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c            | 12 ++++++++++--
 include/linux/quota.h | 26 ++++++++++++++++++++------
 2 files changed, 30 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index 9c78ffe1aad2..89226726daa8 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -2010,25 +2010,33 @@ static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
 	if (di->dqb_valid & QIF_SPACE) {
 		dm->dqb_curspace = di->dqb_curspace;
 		check_blim = 1;
+		__set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
 	}
 	if (di->dqb_valid & QIF_BLIMITS) {
 		dm->dqb_bsoftlimit = qbtos(di->dqb_bsoftlimit);
 		dm->dqb_bhardlimit = qbtos(di->dqb_bhardlimit);
 		check_blim = 1;
+		__set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
 	}
 	if (di->dqb_valid & QIF_INODES) {
 		dm->dqb_curinodes = di->dqb_curinodes;
 		check_ilim = 1;
+		__set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
 	}
 	if (di->dqb_valid & QIF_ILIMITS) {
 		dm->dqb_isoftlimit = di->dqb_isoftlimit;
 		dm->dqb_ihardlimit = di->dqb_ihardlimit;
 		check_ilim = 1;
+		__set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
 	}
-	if (di->dqb_valid & QIF_BTIME)
+	if (di->dqb_valid & QIF_BTIME) {
 		dm->dqb_btime = di->dqb_btime;
-	if (di->dqb_valid & QIF_ITIME)
+		__set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
+	}
+	if (di->dqb_valid & QIF_ITIME) {
 		dm->dqb_itime = di->dqb_itime;
+		__set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
+	}
 
 	if (check_blim) {
 		if (!dm->dqb_bsoftlimit || dm->dqb_curspace < dm->dqb_bsoftlimit) {
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 75bf761caef2..6d98885c16da 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -80,12 +80,21 @@
  * Quota structure used for communication with userspace via quotactl
  * Following flags are used to specify which fields are valid
  */
-#define QIF_BLIMITS	1
-#define QIF_SPACE	2
-#define QIF_ILIMITS	4
-#define QIF_INODES	8
-#define QIF_BTIME	16
-#define QIF_ITIME	32
+enum {
+	QIF_BLIMITS_B = 0,
+	QIF_SPACE_B,
+	QIF_ILIMITS_B,
+	QIF_INODES_B,
+	QIF_BTIME_B,
+	QIF_ITIME_B,
+};
+
+#define QIF_BLIMITS	(1 << QIF_BLIMITS_B)
+#define QIF_SPACE	(1 << QIF_SPACE_B)
+#define QIF_ILIMITS	(1 << QIF_ILIMITS_B)
+#define QIF_INODES	(1 << QIF_INODES_B)
+#define QIF_BTIME	(1 << QIF_BTIME_B)
+#define QIF_ITIME	(1 << QIF_ITIME_B)
 #define QIF_LIMITS	(QIF_BLIMITS | QIF_ILIMITS)
 #define QIF_USAGE	(QIF_SPACE | QIF_INODES)
 #define QIF_TIMES	(QIF_BTIME | QIF_ITIME)
@@ -242,6 +251,11 @@ extern struct dqstats dqstats;
 #define DQ_FAKE_B	3	/* no limits only usage */
 #define DQ_READ_B	4	/* dquot was read into memory */
 #define DQ_ACTIVE_B	5	/* dquot is active (dquot_release not called) */
+#define DQ_LASTSET_B	6	/* Following 6 bits (see QIF_) are reserved\
+				 * for the mask of entries set via SETQUOTA\
+				 * quotactl. They are set under dq_data_lock\
+				 * and the quota format handling dquot can\
+				 * clear them when it sees fit. */
 
 struct dquot {
 	struct hlist_node dq_hash;	/* Hash list in memory */
-- 
cgit v1.2.3-70-g09d2


From 571b46e40bebb0d57130ca24c4a84dfd553adb91 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 30 Oct 2008 09:17:52 +0100
Subject: quota: Update version number

Increase reported version number of quota support since quota core has changed
significantly. Also remove __DQUOT_NUM_VERSION__ since nobody uses it.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 include/linux/quota.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/quota.h b/include/linux/quota.h
index 6d98885c16da..ec82beb10424 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -36,8 +36,7 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 
-#define __DQUOT_VERSION__	"dquot_6.5.1"
-#define __DQUOT_NUM_VERSION__	6*10000+5*100+1
+#define __DQUOT_VERSION__	"dquot_6.5.2"
 
 #define MAXQUOTAS 2
 #define USRQUOTA  0		/* element used for user quotas */
-- 
cgit v1.2.3-70-g09d2


From 3d9ea253a0e73dccaa869888ec2ceb17ea76c810 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Fri, 10 Oct 2008 16:12:23 +0200
Subject: quota: Add helpers to allow ocfs2 specific quota initialization,
 freeing and recovery

OCFS2 needs to peek whether quota structure is already in memory so
that it can avoid expensive cluster locking in that case. Similarly
when freeing dquots, it checks whether it is the last quota structure
user or not. Finally, it needs to get reference to dquot structure for
specified id and quota type when recovering quota file after crash.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c               | 38 ++++++++++++++++++++++++++++++++------
 include/linux/quotaops.h |  4 ++++
 2 files changed, 36 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index 89226726daa8..ae8fd9e645cc 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -211,8 +211,6 @@ static struct hlist_head *dquot_hash;
 
 struct dqstats dqstats;
 
-static void dqput(struct dquot *dquot);
-
 static inline unsigned int
 hashfn(const struct super_block *sb, unsigned int id, int type)
 {
@@ -568,7 +566,7 @@ static struct shrinker dqcache_shrinker = {
  * NOTE: If you change this function please check whether dqput_blocks() works right...
  * MUST be called with either dqptr_sem or dqonoff_mutex held
  */
-static void dqput(struct dquot *dquot)
+void dqput(struct dquot *dquot)
 {
 	int ret;
 
@@ -661,11 +659,29 @@ static struct dquot *get_empty_dquot(struct super_block *sb, int type)
 	return dquot;
 }
 
+/*
+ * Check whether dquot is in memory.
+ * MUST be called with either dqptr_sem or dqonoff_mutex held
+ */
+int dquot_is_cached(struct super_block *sb, unsigned int id, int type)
+{
+	unsigned int hashent = hashfn(sb, id, type);
+	int ret = 0;
+
+        if (!sb_has_quota_active(sb, type))
+		return 0;
+	spin_lock(&dq_list_lock);
+	if (find_dquot(hashent, sb, id, type) != NODQUOT)
+		ret = 1;
+	spin_unlock(&dq_list_lock);
+	return ret;
+}
+
 /*
  * Get reference to dquot
  * MUST be called with either dqptr_sem or dqonoff_mutex held
  */
-static struct dquot *dqget(struct super_block *sb, unsigned int id, int type)
+struct dquot *dqget(struct super_block *sb, unsigned int id, int type)
 {
 	unsigned int hashent = hashfn(sb, id, type);
 	struct dquot *dquot, *empty = NODQUOT;
@@ -1184,17 +1200,23 @@ out_err:
  * 	Release all quotas referenced by inode
  *	Transaction must be started at an entry
  */
-int dquot_drop(struct inode *inode)
+int dquot_drop_locked(struct inode *inode)
 {
 	int cnt;
 
-	down_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		if (inode->i_dquot[cnt] != NODQUOT) {
 			dqput(inode->i_dquot[cnt]);
 			inode->i_dquot[cnt] = NODQUOT;
 		}
 	}
+	return 0;
+}
+
+int dquot_drop(struct inode *inode)
+{
+	down_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
+	dquot_drop_locked(inode);
 	up_write(&sb_dqopt(inode->i_sb)->dqptr_sem);
 	return 0;
 }
@@ -2308,7 +2330,11 @@ EXPORT_SYMBOL(dquot_release);
 EXPORT_SYMBOL(dquot_mark_dquot_dirty);
 EXPORT_SYMBOL(dquot_initialize);
 EXPORT_SYMBOL(dquot_drop);
+EXPORT_SYMBOL(dquot_drop_locked);
 EXPORT_SYMBOL(vfs_dq_drop);
+EXPORT_SYMBOL(dqget);
+EXPORT_SYMBOL(dqput);
+EXPORT_SYMBOL(dquot_is_cached);
 EXPORT_SYMBOL(dquot_alloc_space);
 EXPORT_SYMBOL(dquot_alloc_inode);
 EXPORT_SYMBOL(dquot_free_space);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index e840ca523175..e3a10272d471 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -24,6 +24,10 @@ void sync_dquots(struct super_block *sb, int type);
 
 int dquot_initialize(struct inode *inode, int type);
 int dquot_drop(struct inode *inode);
+int dquot_drop_locked(struct inode *inode);
+struct dquot *dqget(struct super_block *sb, unsigned int id, int type);
+void dqput(struct dquot *dquot);
+int dquot_is_cached(struct super_block *sb, unsigned int id, int type);
 
 int dquot_alloc_space(struct inode *inode, qsize_t number, int prealloc);
 int dquot_alloc_inode(const struct inode *inode, qsize_t number);
-- 
cgit v1.2.3-70-g09d2


From 12c77527e4138bc3b17d17b0e0c909e4fc84924f Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 20 Oct 2008 17:05:00 +0200
Subject: quota: Implement function for scanning active dquots

OCFS2 needs to scan all active dquots once in a while and sync quota
information among cluster nodes. Provide a helper function for it so
that it does not have to reimplement internally a list which VFS
already has. Moreover this function is probably going to be useful
for other clustered filesystems if they decide to use VFS quotas.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c               | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/quotaops.h |  3 +++
 2 files changed, 39 insertions(+)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index ae8fd9e645cc..075dc76904e7 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -476,6 +476,41 @@ restart:
 	spin_unlock(&dq_list_lock);
 }
 
+/* Call callback for every active dquot on given filesystem */
+int dquot_scan_active(struct super_block *sb,
+		      int (*fn)(struct dquot *dquot, unsigned long priv),
+		      unsigned long priv)
+{
+	struct dquot *dquot, *old_dquot = NULL;
+	int ret = 0;
+
+	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
+	spin_lock(&dq_list_lock);
+	list_for_each_entry(dquot, &inuse_list, dq_inuse) {
+		if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags))
+			continue;
+		if (dquot->dq_sb != sb)
+			continue;
+		/* Now we have active dquot so we can just increase use count */
+		atomic_inc(&dquot->dq_count);
+		dqstats.lookups++;
+		spin_unlock(&dq_list_lock);
+		dqput(old_dquot);
+		old_dquot = dquot;
+		ret = fn(dquot, priv);
+		if (ret < 0)
+			goto out;
+		spin_lock(&dq_list_lock);
+		/* We are safe to continue now because our dquot could not
+		 * be moved out of the inuse list while we hold the reference */
+	}
+	spin_unlock(&dq_list_lock);
+out:
+	dqput(old_dquot);
+	mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
+	return ret;
+}
+
 int vfs_quota_sync(struct super_block *sb, int type)
 {
 	struct list_head *dirty;
@@ -2318,6 +2353,7 @@ EXPORT_SYMBOL(vfs_quota_on_path);
 EXPORT_SYMBOL(vfs_quota_on_mount);
 EXPORT_SYMBOL(vfs_quota_disable);
 EXPORT_SYMBOL(vfs_quota_off);
+EXPORT_SYMBOL(dquot_scan_active);
 EXPORT_SYMBOL(vfs_quota_sync);
 EXPORT_SYMBOL(vfs_get_dqinfo);
 EXPORT_SYMBOL(vfs_set_dqinfo);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index e3a10272d471..f4913948c305 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -28,6 +28,9 @@ int dquot_drop_locked(struct inode *inode);
 struct dquot *dqget(struct super_block *sb, unsigned int id, int type);
 void dqput(struct dquot *dquot);
 int dquot_is_cached(struct super_block *sb, unsigned int id, int type);
+int dquot_scan_active(struct super_block *sb,
+		      int (*fn)(struct dquot *dquot, unsigned long priv),
+		      unsigned long priv);
 
 int dquot_alloc_space(struct inode *inode, qsize_t number, int prealloc);
 int dquot_alloc_inode(const struct inode *inode, qsize_t number);
-- 
cgit v1.2.3-70-g09d2


From e97fcd95a4778a8caf1980c6c72fdf68185a0838 Mon Sep 17 00:00:00 2001
From: Mark Fasheh <mfasheh@suse.com>
Date: Tue, 18 Nov 2008 17:15:24 -0800
Subject: jbd2: Add BH_JBDPrivateStart

Add this so that file systems using JBD2 can safely allocate unused b_state
bits.

In this case, we add it so that Ocfs2 can define a single bit for tracking
the validation state of a buffer.

Acked-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 include/linux/jbd2.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index c7d106ef22e2..f36645745489 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -329,6 +329,7 @@ enum jbd_state_bits {
 	BH_State,		/* Pins most journal_head state */
 	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
 	BH_Unshadow,		/* Dummy bit, for BJ_Shadow wakeup filtering */
+	BH_JBDPrivateStart,	/* First bit available for private use by FS */
 };
 
 BUFFER_FNS(JBD, jbd)
-- 
cgit v1.2.3-70-g09d2


From 5cd9d5bb86daf632a40f90e2321ea9379e42f073 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 25 Nov 2008 15:31:31 +0100
Subject: quota: Unexport dqblk_v1.h and dqblk_v2.h

Unexport header files dqblk_v[12].h since except for quota format ID they
don't contain information userspace should be interested in. Move ID
definitions to quota.h.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 include/linux/Kbuild     | 2 --
 include/linux/dqblk_v1.h | 3 ---
 include/linux/dqblk_v2.h | 3 ---
 include/linux/quota.h    | 4 ++++
 4 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 900a787cbae9..39da666067b9 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -56,8 +56,6 @@ header-y += dlm_device.h
 header-y += dlm_netlink.h
 header-y += dm-ioctl.h
 header-y += dn.h
-header-y += dqblk_v1.h
-header-y += dqblk_v2.h
 header-y += dqblk_xfs.h
 header-y += efs_fs_sb.h
 header-y += elf-fdpic.h
diff --git a/include/linux/dqblk_v1.h b/include/linux/dqblk_v1.h
index 9cea901f5bba..3713a7232dd8 100644
--- a/include/linux/dqblk_v1.h
+++ b/include/linux/dqblk_v1.h
@@ -5,9 +5,6 @@
 #ifndef _LINUX_DQBLK_V1_H
 #define _LINUX_DQBLK_V1_H
 
-/* Id of quota format */
-#define QFMT_VFS_OLD 1
-
 /* Root squash turned on */
 #define V1_DQF_RSQUASH 1
 
diff --git a/include/linux/dqblk_v2.h b/include/linux/dqblk_v2.h
index ff8af1b4bda7..18000a542677 100644
--- a/include/linux/dqblk_v2.h
+++ b/include/linux/dqblk_v2.h
@@ -7,9 +7,6 @@
 
 #include <linux/dqblk_qtree.h>
 
-/* Id number of quota format */
-#define QFMT_VFS_V0 2
-
 /* Numbers of blocks needed for updates */
 #define V2_INIT_ALLOC QTREE_INIT_ALLOC
 #define V2_INIT_REWRITE QTREE_INIT_REWRITE
diff --git a/include/linux/quota.h b/include/linux/quota.h
index ec82beb10424..d72d5d84fde5 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -70,6 +70,10 @@
 #define Q_GETQUOTA 0x800007	/* get user quota structure */
 #define Q_SETQUOTA 0x800008	/* set user quota structure */
 
+/* Quota format type IDs */
+#define	QFMT_VFS_OLD 1
+#define	QFMT_VFS_V0 2
+
 /* Size of block in which space limits are passed through the quota
  * interface */
 #define QIF_DQBLKSIZE_BITS 10
-- 
cgit v1.2.3-70-g09d2


From 7d9056ba20ebed6e3937a2e23183f6117919cb00 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 25 Nov 2008 15:31:32 +0100
Subject: quota: Export dquot_alloc() and dquot_destroy() functions

These are default functions for creating and destroying quota structures
and they should be used from filesystems.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/dquot.c               | 6 ++++--
 include/linux/quotaops.h | 2 ++
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/dquot.c b/fs/dquot.c
index 075dc76904e7..61bfff64e5af 100644
--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -413,10 +413,11 @@ out_dqlock:
 	return ret;
 }
 
-static void dquot_destroy(struct dquot *dquot)
+void dquot_destroy(struct dquot *dquot)
 {
 	kmem_cache_free(dquot_cachep, dquot);
 }
+EXPORT_SYMBOL(dquot_destroy);
 
 static inline void do_destroy_dquot(struct dquot *dquot)
 {
@@ -668,10 +669,11 @@ we_slept:
 	spin_unlock(&dq_list_lock);
 }
 
-static struct dquot *dquot_alloc(struct super_block *sb, int type)
+struct dquot *dquot_alloc(struct super_block *sb, int type)
 {
 	return kmem_cache_zalloc(dquot_cachep, GFP_NOFS);
 }
+EXPORT_SYMBOL(dquot_alloc);
 
 static struct dquot *get_empty_dquot(struct super_block *sb, int type)
 {
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index f4913948c305..21b781a3350f 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -31,6 +31,8 @@ int dquot_is_cached(struct super_block *sb, unsigned int id, int type);
 int dquot_scan_active(struct super_block *sb,
 		      int (*fn)(struct dquot *dquot, unsigned long priv),
 		      unsigned long priv);
+struct dquot *dquot_alloc(struct super_block *sb, int type);
+void dquot_destroy(struct dquot *dquot);
 
 int dquot_alloc_space(struct inode *inode, qsize_t number, int prealloc);
 int dquot_alloc_inode(const struct inode *inode, qsize_t number);
-- 
cgit v1.2.3-70-g09d2


From e06c8227fd94ec181849ba206bf032be31c4295c Mon Sep 17 00:00:00 2001
From: Joel Becker <joel.becker@oracle.com>
Date: Thu, 11 Sep 2008 15:35:47 -0700
Subject: jbd2: Add buffer triggers

Filesystems often to do compute intensive operation on some
metadata.  If this operation is repeated many times, it can be very
expensive.  It would be much nicer if the operation could be performed
once before a buffer goes to disk.

This adds triggers to jbd2 buffer heads.  Just before writing a metadata
buffer to the journal, jbd2 will optionally call a commit trigger associated
with the buffer.  If the journal is aborted, an abort trigger will be
called on any dirty buffers as they are dropped from pending
transactions.

ocfs2 will use this feature.

Initially I tried to come up with a more generic trigger that could be
used for non-buffer-related events like transaction completion.  It
doesn't tie nicely, because the information a buffer trigger needs
(specific to a journal_head) isn't the same as what a transaction
trigger needs (specific to a tranaction_t or perhaps journal_t).  So I
implemented a buffer set, with the understanding that
journal/transaction wide triggers should be implemented separately.

There is only one trigger set allowed per buffer.  I can't think of any
reason to attach more than one set.  Contrast this with a journal or
transaction in which multiple places may want to watch the entire
transaction separately.

The trigger sets are considered static allocation from the jbd2
perspective.  ocfs2 will just have one trigger set per block type,
setting the same set on every bh of the same type.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/jbd2/commit.c             |  9 +++++++++
 fs/jbd2/journal.c            | 19 ++++++++++++++++++
 fs/jbd2/transaction.c        | 47 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/jbd2.h         | 31 +++++++++++++++++++++++++++++
 include/linux/journal-head.h |  8 ++++++++
 5 files changed, 114 insertions(+)

(limited to 'include')

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index ebc667bc54a8..c8a1bace685a 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -509,6 +509,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		if (is_journal_aborted(journal)) {
 			clear_buffer_jbddirty(jh2bh(jh));
 			JBUFFER_TRACE(jh, "journal is aborting: refile");
+			jbd2_buffer_abort_trigger(jh,
+						  jh->b_frozen_data ?
+						  jh->b_frozen_triggers :
+						  jh->b_triggers);
 			jbd2_journal_refile_buffer(journal, jh);
 			/* If that was the last one, we need to clean up
 			 * any descriptor buffers which may have been
@@ -844,6 +848,9 @@ restart_loop:
 		 * data.
 		 *
 		 * Otherwise, we can just throw away the frozen data now.
+		 *
+		 * We also know that the frozen data has already fired
+		 * its triggers if they exist, so we can clear that too.
 		 */
 		if (jh->b_committed_data) {
 			jbd2_free(jh->b_committed_data, bh->b_size);
@@ -851,10 +858,12 @@ restart_loop:
 			if (jh->b_frozen_data) {
 				jh->b_committed_data = jh->b_frozen_data;
 				jh->b_frozen_data = NULL;
+				jh->b_frozen_triggers = NULL;
 			}
 		} else if (jh->b_frozen_data) {
 			jbd2_free(jh->b_frozen_data, bh->b_size);
 			jh->b_frozen_data = NULL;
+			jh->b_frozen_triggers = NULL;
 		}
 
 		spin_lock(&journal->j_list_lock);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index e70d657a19f8..f6bff9d6f8df 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -50,6 +50,7 @@ EXPORT_SYMBOL(jbd2_journal_unlock_updates);
 EXPORT_SYMBOL(jbd2_journal_get_write_access);
 EXPORT_SYMBOL(jbd2_journal_get_create_access);
 EXPORT_SYMBOL(jbd2_journal_get_undo_access);
+EXPORT_SYMBOL(jbd2_journal_set_triggers);
 EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
 EXPORT_SYMBOL(jbd2_journal_release_buffer);
 EXPORT_SYMBOL(jbd2_journal_forget);
@@ -290,6 +291,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	struct page *new_page;
 	unsigned int new_offset;
 	struct buffer_head *bh_in = jh2bh(jh_in);
+	struct jbd2_buffer_trigger_type *triggers;
 
 	/*
 	 * The buffer really shouldn't be locked: only the current committing
@@ -314,12 +316,22 @@ repeat:
 		done_copy_out = 1;
 		new_page = virt_to_page(jh_in->b_frozen_data);
 		new_offset = offset_in_page(jh_in->b_frozen_data);
+		triggers = jh_in->b_frozen_triggers;
 	} else {
 		new_page = jh2bh(jh_in)->b_page;
 		new_offset = offset_in_page(jh2bh(jh_in)->b_data);
+		triggers = jh_in->b_triggers;
 	}
 
 	mapped_data = kmap_atomic(new_page, KM_USER0);
+	/*
+	 * Fire any commit trigger.  Do this before checking for escaping,
+	 * as the trigger may modify the magic offset.  If a copy-out
+	 * happens afterwards, it will have the correct data in the buffer.
+	 */
+	jbd2_buffer_commit_trigger(jh_in, mapped_data + new_offset,
+				   triggers);
+
 	/*
 	 * Check for escaping
 	 */
@@ -352,6 +364,13 @@ repeat:
 		new_page = virt_to_page(tmp);
 		new_offset = offset_in_page(tmp);
 		done_copy_out = 1;
+
+		/*
+		 * This isn't strictly necessary, as we're using frozen
+		 * data for the escaping, but it keeps consistency with
+		 * b_frozen_data usage.
+		 */
+		jh_in->b_frozen_triggers = jh_in->b_triggers;
 	}
 
 	/*
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 39b7805a599a..4f925a4f3d05 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -741,6 +741,12 @@ done:
 		source = kmap_atomic(page, KM_USER0);
 		memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
 		kunmap_atomic(source, KM_USER0);
+
+		/*
+		 * Now that the frozen data is saved off, we need to store
+		 * any matching triggers.
+		 */
+		jh->b_frozen_triggers = jh->b_triggers;
 	}
 	jbd_unlock_bh_state(bh);
 
@@ -943,6 +949,47 @@ out:
 	return err;
 }
 
+/**
+ * void jbd2_journal_set_triggers() - Add triggers for commit writeout
+ * @bh: buffer to trigger on
+ * @type: struct jbd2_buffer_trigger_type containing the trigger(s).
+ *
+ * Set any triggers on this journal_head.  This is always safe, because
+ * triggers for a committing buffer will be saved off, and triggers for
+ * a running transaction will match the buffer in that transaction.
+ *
+ * Call with NULL to clear the triggers.
+ */
+void jbd2_journal_set_triggers(struct buffer_head *bh,
+			       struct jbd2_buffer_trigger_type *type)
+{
+	struct journal_head *jh = bh2jh(bh);
+
+	jh->b_triggers = type;
+}
+
+void jbd2_buffer_commit_trigger(struct journal_head *jh, void *mapped_data,
+				struct jbd2_buffer_trigger_type *triggers)
+{
+	struct buffer_head *bh = jh2bh(jh);
+
+	if (!triggers || !triggers->t_commit)
+		return;
+
+	triggers->t_commit(triggers, bh, mapped_data, bh->b_size);
+}
+
+void jbd2_buffer_abort_trigger(struct journal_head *jh,
+			       struct jbd2_buffer_trigger_type *triggers)
+{
+	if (!triggers || !triggers->t_abort)
+		return;
+
+	triggers->t_abort(triggers, jh2bh(jh));
+}
+
+
+
 /**
  * int jbd2_journal_dirty_metadata() -  mark a buffer as containing dirty metadata
  * @handle: transaction to add buffer to.
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index f36645745489..34456476e761 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1008,6 +1008,35 @@ int __jbd2_journal_clean_checkpoint_list(journal_t *journal);
 int __jbd2_journal_remove_checkpoint(struct journal_head *);
 void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
 
+
+/*
+ * Triggers
+ */
+
+struct jbd2_buffer_trigger_type {
+	/*
+	 * Fired just before a buffer is written to the journal.
+	 * mapped_data is a mapped buffer that is the frozen data for
+	 * commit.
+	 */
+	void (*t_commit)(struct jbd2_buffer_trigger_type *type,
+			 struct buffer_head *bh, void *mapped_data,
+			 size_t size);
+
+	/*
+	 * Fired during journal abort for dirty buffers that will not be
+	 * committed.
+	 */
+	void (*t_abort)(struct jbd2_buffer_trigger_type *type,
+			struct buffer_head *bh);
+};
+
+extern void jbd2_buffer_commit_trigger(struct journal_head *jh,
+				       void *mapped_data,
+				       struct jbd2_buffer_trigger_type *triggers);
+extern void jbd2_buffer_abort_trigger(struct journal_head *jh,
+				      struct jbd2_buffer_trigger_type *triggers);
+
 /* Buffer IO */
 extern int
 jbd2_journal_write_metadata_buffer(transaction_t	  *transaction,
@@ -1046,6 +1075,8 @@ extern int	 jbd2_journal_extend (handle_t *, int nblocks);
 extern int	 jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
+void		 jbd2_journal_set_triggers(struct buffer_head *,
+					   struct jbd2_buffer_trigger_type *type);
 extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern void	 jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h
index bb70ebb6a2d5..525aac3c97df 100644
--- a/include/linux/journal-head.h
+++ b/include/linux/journal-head.h
@@ -12,6 +12,8 @@
 
 typedef unsigned int		tid_t;		/* Unique transaction ID */
 typedef struct transaction_s	transaction_t;	/* Compound transaction type */
+
+
 struct buffer_head;
 
 struct journal_head {
@@ -87,6 +89,12 @@ struct journal_head {
 	 * [j_list_lock]
 	 */
 	struct journal_head *b_cpnext, *b_cpprev;
+
+	/* Trigger type */
+	struct jbd2_buffer_trigger_type *b_triggers;
+
+	/* Trigger type for the committing transaction's frozen data */
+	struct jbd2_buffer_trigger_type *b_frozen_triggers;
 };
 
 #endif		/* JOURNAL_HEAD_H_INCLUDED */
-- 
cgit v1.2.3-70-g09d2


From 4c728ef583b3d82266584da5cb068294c09df31e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 22 Dec 2008 21:11:15 +0100
Subject: add a vfs_fsync helper

Fsync currently has a fdatawrite/fdatawait pair around the method call,
and a mutex_lock/unlock of the inode mutex.  All callers of fsync have
to duplicate this, but we have a few and most of them don't quite get
it right.  This patch adds a new vfs_fsync that takes care of this.
It's a little more complicated as usual as ->fsync might get a NULL file
pointer and just a dentry from nfsd, but otherwise gets afile and we
want to take the mapping and file operations from it when it is there.

Notes on the fsync callers:

 - ecryptfs wasn't calling filemap_fdatawrite / filemap_fdatawait on the
   	lower file
 - coda wasn't calling filemap_fdatawrite / filemap_fdatawait on the host
	file, and returning 0 when ->fsync was missing
 - shm wasn't calling either filemap_fdatawrite / filemap_fdatawait nor
   taking i_mutex.  Now given that shared memory doesn't have disk
   backing not doing anything in fsync seems fine and I left it out of
   the vfs_fsync conversion for now, but in that case we might just
   not pass it through to the lower file at all but just call the no-op
   simple_sync_file directly.

[and now actually export vfs_fsync]

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/usb/gadget/file_storage.c | 18 +--------------
 fs/coda/file.c                    | 12 ++--------
 fs/ecryptfs/file.c                | 15 +++---------
 fs/nfsd/vfs.c                     | 35 +++-------------------------
 fs/sync.c                         | 48 ++++++++++++++++++++++++++++++---------
 include/linux/fs.h                |  2 +-
 mm/msync.c                        |  2 +-
 7 files changed, 48 insertions(+), 84 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/file_storage.c b/drivers/usb/gadget/file_storage.c
index c4e62a6297d7..2e71368f45b4 100644
--- a/drivers/usb/gadget/file_storage.c
+++ b/drivers/usb/gadget/file_storage.c
@@ -1863,26 +1863,10 @@ static int do_write(struct fsg_dev *fsg)
 static int fsync_sub(struct lun *curlun)
 {
 	struct file	*filp = curlun->filp;
-	struct inode	*inode;
-	int		rc, err;
 
 	if (curlun->ro || !filp)
 		return 0;
-	if (!filp->f_op->fsync)
-		return -EINVAL;
-
-	inode = filp->f_path.dentry->d_inode;
-	mutex_lock(&inode->i_mutex);
-	rc = filemap_fdatawrite(inode->i_mapping);
-	err = filp->f_op->fsync(filp, filp->f_path.dentry, 1);
-	if (!rc)
-		rc = err;
-	err = filemap_fdatawait(inode->i_mapping);
-	if (!rc)
-		rc = err;
-	mutex_unlock(&inode->i_mutex);
-	VLDBG(curlun, "fdatasync -> %d\n", rc);
-	return rc;
+	return vfs_fsync(filp, filp->f_path.dentry, 1);
 }
 
 static void fsync_all(struct fsg_dev *fsg)
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 466303db2df6..6a347fbc998a 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -201,8 +201,7 @@ int coda_release(struct inode *coda_inode, struct file *coda_file)
 int coda_fsync(struct file *coda_file, struct dentry *coda_dentry, int datasync)
 {
 	struct file *host_file;
-	struct dentry *host_dentry;
-	struct inode *host_inode, *coda_inode = coda_dentry->d_inode;
+	struct inode *coda_inode = coda_dentry->d_inode;
 	struct coda_file_info *cfi;
 	int err = 0;
 
@@ -214,14 +213,7 @@ int coda_fsync(struct file *coda_file, struct dentry *coda_dentry, int datasync)
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
-	if (host_file->f_op && host_file->f_op->fsync) {
-		host_dentry = host_file->f_path.dentry;
-		host_inode = host_dentry->d_inode;
-		mutex_lock(&host_inode->i_mutex);
-		err = host_file->f_op->fsync(host_file, host_dentry, datasync);
-		mutex_unlock(&host_inode->i_mutex);
-	}
-
+	err = vfs_fsync(host_file, host_file->f_path.dentry, datasync);
 	if ( !err && !datasync ) {
 		lock_kernel();
 		err = venus_fsync(coda_inode->i_sb, coda_i2f(coda_inode));
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index eb3dc4c7ac06..713834371229 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -275,18 +275,9 @@ static int ecryptfs_release(struct inode *inode, struct file *file)
 static int
 ecryptfs_fsync(struct file *file, struct dentry *dentry, int datasync)
 {
-	struct file *lower_file = ecryptfs_file_to_lower(file);
-	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
-	struct inode *lower_inode = lower_dentry->d_inode;
-	int rc = -EINVAL;
-
-	if (lower_inode->i_fop->fsync) {
-		mutex_lock(&lower_inode->i_mutex);
-		rc = lower_inode->i_fop->fsync(lower_file, lower_dentry,
-					       datasync);
-		mutex_unlock(&lower_inode->i_mutex);
-	}
-	return rc;
+	return vfs_fsync(ecryptfs_file_to_lower(file),
+			 ecryptfs_dentry_to_lower(dentry),
+			 datasync);
 }
 
 static int ecryptfs_fasync(int fd, struct file *file, int flag)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 5245a3965004..44aa92aba891 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -744,45 +744,16 @@ nfsd_close(struct file *filp)
 	fput(filp);
 }
 
-/*
- * Sync a file
- * As this calls fsync (not fdatasync) there is no need for a write_inode
- * after it.
- */
-static inline int nfsd_dosync(struct file *filp, struct dentry *dp,
-			      const struct file_operations *fop)
-{
-	struct inode *inode = dp->d_inode;
-	int (*fsync) (struct file *, struct dentry *, int);
-	int err;
-
-	err = filemap_fdatawrite(inode->i_mapping);
-	if (err == 0 && fop && (fsync = fop->fsync))
-		err = fsync(filp, dp, 0);
-	if (err == 0)
-		err = filemap_fdatawait(inode->i_mapping);
-
-	return err;
-}
-	
-
 static int
 nfsd_sync(struct file *filp)
 {
-        int err;
-	struct inode *inode = filp->f_path.dentry->d_inode;
-	dprintk("nfsd: sync file %s\n", filp->f_path.dentry->d_name.name);
-	mutex_lock(&inode->i_mutex);
-	err=nfsd_dosync(filp, filp->f_path.dentry, filp->f_op);
-	mutex_unlock(&inode->i_mutex);
-
-	return err;
+	return vfs_fsync(filp, filp->f_path.dentry, 0);
 }
 
 int
-nfsd_sync_dir(struct dentry *dp)
+nfsd_sync_dir(struct dentry *dentry)
 {
-	return nfsd_dosync(NULL, dp, dp->d_inode->i_fop);
+	return vfs_fsync(NULL, dentry, 0);
 }
 
 /*
diff --git a/fs/sync.c b/fs/sync.c
index 2967562d416f..0921d6d4b5e6 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -75,14 +75,39 @@ int file_fsync(struct file *filp, struct dentry *dentry, int datasync)
 	return ret;
 }
 
-long do_fsync(struct file *file, int datasync)
+/**
+ * vfs_fsync - perform a fsync or fdatasync on a file
+ * @file:		file to sync
+ * @dentry:		dentry of @file
+ * @data:		only perform a fdatasync operation
+ *
+ * Write back data and metadata for @file to disk.  If @datasync is
+ * set only metadata needed to access modified file data is written.
+ *
+ * In case this function is called from nfsd @file may be %NULL and
+ * only @dentry is set.  This can only happen when the filesystem
+ * implements the export_operations API.
+ */
+int vfs_fsync(struct file *file, struct dentry *dentry, int datasync)
 {
-	int ret;
-	int err;
-	struct address_space *mapping = file->f_mapping;
+	const struct file_operations *fop;
+	struct address_space *mapping;
+	int err, ret;
+
+	/*
+	 * Get mapping and operations from the file in case we have
+	 * as file, or get the default values for them in case we
+	 * don't have a struct file available.  Damn nfsd..
+	 */
+	if (file) {
+		mapping = file->f_mapping;
+		fop = file->f_op;
+	} else {
+		mapping = dentry->d_inode->i_mapping;
+		fop = dentry->d_inode->i_fop;
+	}
 
-	if (!file->f_op || !file->f_op->fsync) {
-		/* Why?  We can still call filemap_fdatawrite */
+	if (!fop || !fop->fsync) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -94,7 +119,7 @@ long do_fsync(struct file *file, int datasync)
 	 * livelocks in fsync_buffers_list().
 	 */
 	mutex_lock(&mapping->host->i_mutex);
-	err = file->f_op->fsync(file, file->f_path.dentry, datasync);
+	err = fop->fsync(file, dentry, datasync);
 	if (!ret)
 		ret = err;
 	mutex_unlock(&mapping->host->i_mutex);
@@ -104,15 +129,16 @@ long do_fsync(struct file *file, int datasync)
 out:
 	return ret;
 }
+EXPORT_SYMBOL(vfs_fsync);
 
-static long __do_fsync(unsigned int fd, int datasync)
+static int do_fsync(unsigned int fd, int datasync)
 {
 	struct file *file;
 	int ret = -EBADF;
 
 	file = fget(fd);
 	if (file) {
-		ret = do_fsync(file, datasync);
+		ret = vfs_fsync(file, file->f_path.dentry, datasync);
 		fput(file);
 	}
 	return ret;
@@ -120,12 +146,12 @@ static long __do_fsync(unsigned int fd, int datasync)
 
 asmlinkage long sys_fsync(unsigned int fd)
 {
-	return __do_fsync(fd, 0);
+	return do_fsync(fd, 0);
 }
 
 asmlinkage long sys_fdatasync(unsigned int fd)
 {
-	return __do_fsync(fd, 1);
+	return do_fsync(fd, 1);
 }
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e2170ee21e18..9ad9eac9eb0c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1827,7 +1827,7 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping,
 extern int filemap_fdatawrite_range(struct address_space *mapping,
 				loff_t start, loff_t end);
 
-extern long do_fsync(struct file *file, int datasync);
+extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync);
 extern void sync_supers(void);
 extern void sync_filesystems(int wait);
 extern void __fsync_super(struct super_block *sb);
diff --git a/mm/msync.c b/mm/msync.c
index 144a7570535d..07dae08cf31c 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -82,7 +82,7 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
 				(vma->vm_flags & VM_SHARED)) {
 			get_file(file);
 			up_read(&mm->mmap_sem);
-			error = do_fsync(file, 0);
+			error = vfs_fsync(file, file->f_path.dentry, 0);
 			fput(file);
 			if (error || start >= end)
 				goto out;
-- 
cgit v1.2.3-70-g09d2


From 4ae8978cf92a96257cd8998a49e781be83571d64 Mon Sep 17 00:00:00 2001
From: Michael Kerrisk <mtk.manpages@googlemail.com>
Date: Mon, 5 Jan 2009 07:19:16 -0500
Subject: inotify: fix type errors in interfaces

The problems lie in the types used for some inotify interfaces, both at the kernel level and at the glibc level. This mail addresses the kernel problem. I will follow up with some suggestions for glibc changes.

For the sys_inotify_rm_watch() interface, the type of the 'wd' argument is
currently 'u32', it should be '__s32' .  That is Robert's suggestion, and
is consistent with the other declarations of watch descriptors in the
kernel source, in particular, the inotify_event structure in
include/linux/inotify.h:

struct inotify_event {
        __s32           wd;             /* watch descriptor */
        __u32           mask;           /* watch mask */
        __u32           cookie;         /* cookie to synchronize two events */
        __u32           len;            /* length (including nulls) of name */
        char            name[0];        /* stub for possible name */
};

The patch makes the changes needed for inotify_rm_watch().

Signed-off-by: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Robert Love <rlove@google.com>
Cc: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/notify/inotify/inotify_user.c | 2 +-
 include/linux/syscalls.h         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 400f8064a548..81b8644b0136 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -704,7 +704,7 @@ fput_and_out:
 	return ret;
 }
 
-asmlinkage long sys_inotify_rm_watch(int fd, u32 wd)
+asmlinkage long sys_inotify_rm_watch(int fd, __s32 wd)
 {
 	struct file *filp;
 	struct inotify_device *dev;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 04fb47bfb920..18d0a243a7b3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -549,7 +549,7 @@ asmlinkage long sys_inotify_init(void);
 asmlinkage long sys_inotify_init1(int flags);
 asmlinkage long sys_inotify_add_watch(int fd, const char __user *path,
 					u32 mask);
-asmlinkage long sys_inotify_rm_watch(int fd, u32 wd);
+asmlinkage long sys_inotify_rm_watch(int fd, __s32 wd);
 
 asmlinkage long sys_spu_run(int fd, __u32 __user *unpc,
 				 __u32 __user *ustatus);
-- 
cgit v1.2.3-70-g09d2


From e8c82c2e23e3527e0c9dc195e432c16784d270fa Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Tue, 6 Jan 2009 03:05:50 +0100
Subject: mm lockless pagecache barrier fix

An XFS workload showed up a bug in the lockless pagecache patch. Basically it
would go into an "infinite" loop, although it would sometimes be able to break
out of the loop! The reason is a missing compiler barrier in the "increment
reference count unless it was zero" case of the lockless pagecache protocol in
the gang lookup functions.

This would cause the compiler to use a cached value of struct page pointer to
retry the operation with, rather than reload it. So the page might have been
removed from pagecache and freed (refcount==0) but the lookup would not correctly
notice the page is no longer in pagecache, and keep attempting to increment the
refcount and failing, until the page gets reallocated for something else. This
isn't a data corruption because the condition will be detected if the page has
been reallocated. However it can result in a lockup.

Linus points out that ACCESS_ONCE is also required in that pointer load, even
if it's absence is not causing a bug on our particular build. The most general
way to solve this is just to put an rcu_dereference in radix_tree_deref_slot.

Assembly of find_get_pages,
before:
.L220:
        movq    (%rbx), %rax    #* ivtmp.1162, tmp82
        movq    (%rax), %rdi    #, prephitmp.1149
.L218:
        testb   $1, %dil        #, prephitmp.1149
        jne     .L217   #,
        testq   %rdi, %rdi      # prephitmp.1149
        je      .L203   #,
        cmpq    $-1, %rdi       #, prephitmp.1149
        je      .L217   #,
        movl    8(%rdi), %esi   # <variable>._count.counter, c
        testl   %esi, %esi      # c
        je      .L218   #,

after:
.L212:
        movq    (%rbx), %rax    #* ivtmp.1109, tmp81
        movq    (%rax), %rdi    #, ret
        testb   $1, %dil        #, ret
        jne     .L211   #,
        testq   %rdi, %rdi      # ret
        je      .L197   #,
        cmpq    $-1, %rdi       #, ret
        je      .L211   #,
        movl    8(%rdi), %esi   # <variable>._count.counter, c
        testl   %esi, %esi      # c
        je      .L212   #,

(notice the obvious infinite loop in the first example, if page->count remains 0)

Signed-off-by: Nick Piggin <npiggin@suse.de>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/radix-tree.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index a916c6660dfa..355f6e80db0d 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -136,7 +136,7 @@ do {									\
  */
 static inline void *radix_tree_deref_slot(void **pslot)
 {
-	void *ret = *pslot;
+	void *ret = rcu_dereference(*pslot);
 	if (unlikely(radix_tree_is_indirect_ptr(ret)))
 		ret = RADIX_TREE_RETRY;
 	return ret;
-- 
cgit v1.2.3-70-g09d2


From 10d3bd09a3c25df114f74f7f86e1b58d070bef32 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 6 Jan 2009 03:04:58 +0000
Subject: dm: consolidate target deregistration error handling

Change dm_unregister_target to return void and use BUG() for error
reporting.

dm_unregister_target can only fail because of programming bug in the
target driver. It can't fail because of user's behavior or disk errors.

This patch changes unregister_target to return void and use BUG if
someone tries to unregister non-registered target or unregister target
that is in use.

This patch removes code duplication (testing of error codes in all dm
targets) and reports bugs in just one place, in dm_unregister_target. In
some target drivers, these return codes were ignored, which could lead
to a situation where bugs could be missed.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-crypt.c         |  6 +-----
 drivers/md/dm-delay.c         |  6 +-----
 drivers/md/dm-linear.c        |  5 +----
 drivers/md/dm-mpath.c         |  6 +-----
 drivers/md/dm-raid1.c         |  6 +-----
 drivers/md/dm-snap.c          | 11 ++---------
 drivers/md/dm-stripe.c        |  4 +---
 drivers/md/dm-target.c        | 15 +++++++--------
 drivers/md/dm-zero.c          |  5 +----
 include/linux/device-mapper.h |  6 ++++--
 10 files changed, 20 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 3326750ec02c..35bda49796fb 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1322,11 +1322,7 @@ static int __init dm_crypt_init(void)
 
 static void __exit dm_crypt_exit(void)
 {
-	int r = dm_unregister_target(&crypt_target);
-
-	if (r < 0)
-		DMERR("unregister failed %d", r);
-
+	dm_unregister_target(&crypt_target);
 	kmem_cache_destroy(_crypt_io_pool);
 }
 
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 848b381f1173..59ee1b015d2d 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -364,11 +364,7 @@ bad_queue:
 
 static void __exit dm_delay_exit(void)
 {
-	int r = dm_unregister_target(&delay_target);
-
-	if (r < 0)
-		DMERR("unregister failed %d", r);
-
+	dm_unregister_target(&delay_target);
 	kmem_cache_destroy(delayed_cache);
 	destroy_workqueue(kdelayd_wq);
 }
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 44042becad8a..79fb53e51c70 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -156,8 +156,5 @@ int __init dm_linear_init(void)
 
 void dm_linear_exit(void)
 {
-	int r = dm_unregister_target(&linear_target);
-
-	if (r < 0)
-		DMERR("unregister failed %d", r);
+	dm_unregister_target(&linear_target);
 }
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 3d7f4923cd13..345a26047ae0 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1495,14 +1495,10 @@ static int __init dm_multipath_init(void)
 
 static void __exit dm_multipath_exit(void)
 {
-	int r;
-
 	destroy_workqueue(kmpath_handlerd);
 	destroy_workqueue(kmultipathd);
 
-	r = dm_unregister_target(&multipath_target);
-	if (r < 0)
-		DMERR("target unregister failed %d", r);
+	dm_unregister_target(&multipath_target);
 	kmem_cache_destroy(_mpio_cache);
 }
 
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index d0fed2b21b08..250f401668d5 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1300,11 +1300,7 @@ static int __init dm_mirror_init(void)
 
 static void __exit dm_mirror_exit(void)
 {
-	int r;
-
-	r = dm_unregister_target(&mirror_target);
-	if (r < 0)
-		DMERR("unregister failed %d", r);
+	dm_unregister_target(&mirror_target);
 }
 
 /* Module hooks */
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 4ceedd4f22af..a8005b43a06b 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1470,17 +1470,10 @@ static int __init dm_snapshot_init(void)
 
 static void __exit dm_snapshot_exit(void)
 {
-	int r;
-
 	destroy_workqueue(ksnapd);
 
-	r = dm_unregister_target(&snapshot_target);
-	if (r)
-		DMERR("snapshot unregister failed %d", r);
-
-	r = dm_unregister_target(&origin_target);
-	if (r)
-		DMERR("origin unregister failed %d", r);
+	dm_unregister_target(&snapshot_target);
+	dm_unregister_target(&origin_target);
 
 	exit_origin_hash();
 	kmem_cache_destroy(pending_cache);
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 9e4ef88d421e..41569bc60abc 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -337,9 +337,7 @@ int __init dm_stripe_init(void)
 
 void dm_stripe_exit(void)
 {
-	if (dm_unregister_target(&stripe_target))
-		DMWARN("target unregistration failed");
-
+	dm_unregister_target(&stripe_target);
 	destroy_workqueue(kstriped);
 
 	return;
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 835cf95b857f..7decf10006e4 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -130,26 +130,26 @@ int dm_register_target(struct target_type *t)
 	return rv;
 }
 
-int dm_unregister_target(struct target_type *t)
+void dm_unregister_target(struct target_type *t)
 {
 	struct tt_internal *ti;
 
 	down_write(&_lock);
 	if (!(ti = __find_target_type(t->name))) {
-		up_write(&_lock);
-		return -EINVAL;
+		DMCRIT("Unregistering unrecognised target: %s", t->name);
+		BUG();
 	}
 
 	if (ti->use) {
-		up_write(&_lock);
-		return -ETXTBSY;
+		DMCRIT("Attempt to unregister target still in use: %s",
+		       t->name);
+		BUG();
 	}
 
 	list_del(&ti->list);
 	kfree(ti);
 
 	up_write(&_lock);
-	return 0;
 }
 
 /*
@@ -187,8 +187,7 @@ int __init dm_target_init(void)
 
 void dm_target_exit(void)
 {
-	if (dm_unregister_target(&error_target))
-		DMWARN("error target unregistration failed");
+	dm_unregister_target(&error_target);
 }
 
 EXPORT_SYMBOL(dm_register_target);
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index cdbf126ec106..bbc97030c0c2 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -69,10 +69,7 @@ static int __init dm_zero_init(void)
 
 static void __exit dm_zero_exit(void)
 {
-	int r = dm_unregister_target(&zero_target);
-
-	if (r < 0)
-		DMERR("unregister failed %d", r);
+	dm_unregister_target(&zero_target);
 }
 
 module_init(dm_zero_init)
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index c17fd334e574..89ff2df40240 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -157,8 +157,7 @@ struct dm_target {
 };
 
 int dm_register_target(struct target_type *t);
-int dm_unregister_target(struct target_type *t);
-
+void dm_unregister_target(struct target_type *t);
 
 /*-----------------------------------------------------------------
  * Functions for creating and manipulating mapped devices.
@@ -276,6 +275,9 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size);
  *---------------------------------------------------------------*/
 #define DM_NAME "device-mapper"
 
+#define DMCRIT(f, arg...) \
+	printk(KERN_CRIT DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
+
 #define DMERR(f, arg...) \
 	printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
 #define DMERR_LIMIT(f, arg...) \
-- 
cgit v1.2.3-70-g09d2


From 7d76345da6ed3927c9cbf5d3f7a7021e8bba7374 Mon Sep 17 00:00:00 2001
From: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Date: Tue, 6 Jan 2009 03:05:07 +0000
Subject: dm request: extend target interface

This patch adds the following target interfaces for request-based dm.

  map_rq    : for mapping a request

  rq_end_io : for finishing a request

  busy      : for avoiding performance regression from bio-based dm.
              Target can tell dm core not to map requests now, and
              that may help requests in the block layer queue to be
              bigger by I/O merging.
              In bio-based dm, this behavior is done by device
              drivers managing the block layer queue.
              But in request-based dm, dm core has to do that
              since dm core manages the block layer queue.

Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 include/linux/device-mapper.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 89ff2df40240..c1ba76c7c0e5 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -45,6 +45,8 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti);
  */
 typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio,
 			  union map_info *map_context);
+typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone,
+				  union map_info *map_context);
 
 /*
  * Returns:
@@ -57,6 +59,9 @@ typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio,
 typedef int (*dm_endio_fn) (struct dm_target *ti,
 			    struct bio *bio, int error,
 			    union map_info *map_context);
+typedef int (*dm_request_endio_fn) (struct dm_target *ti,
+				    struct request *clone, int error,
+				    union map_info *map_context);
 
 typedef void (*dm_flush_fn) (struct dm_target *ti);
 typedef void (*dm_presuspend_fn) (struct dm_target *ti);
@@ -75,6 +80,13 @@ typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
 typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm,
 			    struct bio_vec *biovec, int max_size);
 
+/*
+ * Returns:
+ *    0: The target can handle the next I/O immediately.
+ *    1: The target can't handle the next I/O immediately.
+ */
+typedef int (*dm_busy_fn) (struct dm_target *ti);
+
 void dm_error(const char *message);
 
 /*
@@ -107,7 +119,9 @@ struct target_type {
 	dm_ctr_fn ctr;
 	dm_dtr_fn dtr;
 	dm_map_fn map;
+	dm_map_request_fn map_rq;
 	dm_endio_fn end_io;
+	dm_request_endio_fn rq_end_io;
 	dm_flush_fn flush;
 	dm_presuspend_fn presuspend;
 	dm_postsuspend_fn postsuspend;
@@ -117,6 +131,7 @@ struct target_type {
 	dm_message_fn message;
 	dm_ioctl_fn ioctl;
 	dm_merge_fn merge;
+	dm_busy_fn busy;
 };
 
 struct io_restrictions {
-- 
cgit v1.2.3-70-g09d2


From ab4c1424882be9cd70b89abf2b484add355712fa Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@suse.de>
Date: Tue, 6 Jan 2009 03:05:09 +0000
Subject: dm: support barriers on simple devices

Implement barrier support for single device DM devices

This patch implements barrier support in DM for the common case of dm linear
just remapping a single underlying device. In this case we can safely
pass the barrier through because there can be no reordering between
devices.

 NB. Any DM device might cease to support barriers if it gets
     reconfigured so code must continue to allow for a possible
     -EOPNOTSUPP on every barrier bio submitted.  - agk

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-linear.c        |  1 +
 drivers/md/dm-table.c         | 19 +++++++++++++++++++
 drivers/md/dm.c               | 15 +++++----------
 drivers/md/dm.h               |  1 +
 include/linux/device-mapper.h |  7 +++++++
 5 files changed, 33 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 79fb53e51c70..bfa107f59d96 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -142,6 +142,7 @@ static struct target_type linear_target = {
 	.status = linear_status,
 	.ioctl  = linear_ioctl,
 	.merge  = linear_merge,
+	.features = DM_TARGET_SUPPORTS_BARRIERS,
 };
 
 int __init dm_linear_init(void)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 04e5fd742c2c..ebaaf72cd822 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -38,6 +38,8 @@ struct dm_table {
 	sector_t *highs;
 	struct dm_target *targets;
 
+	unsigned barriers_supported:1;
+
 	/*
 	 * Indicates the rw permissions for the new logical
 	 * device.  This should be a combination of FMODE_READ
@@ -227,6 +229,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 
 	INIT_LIST_HEAD(&t->devices);
 	atomic_set(&t->holders, 1);
+	t->barriers_supported = 1;
 
 	if (!num_targets)
 		num_targets = KEYS_PER_NODE;
@@ -728,6 +731,10 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 	/* FIXME: the plan is to combine high here and then have
 	 * the merge fn apply the target level restrictions. */
 	combine_restrictions_low(&t->limits, &tgt->limits);
+
+	if (!(tgt->type->features & DM_TARGET_SUPPORTS_BARRIERS))
+		t->barriers_supported = 0;
+
 	return 0;
 
  bad:
@@ -772,6 +779,12 @@ int dm_table_complete(struct dm_table *t)
 
 	check_for_valid_limits(&t->limits);
 
+	/*
+	 * We only support barriers if there is exactly one underlying device.
+	 */
+	if (!list_is_singular(&t->devices))
+		t->barriers_supported = 0;
+
 	/* how many indexes will the btree have ? */
 	leaf_nodes = dm_div_up(t->num_targets, KEYS_PER_NODE);
 	t->depth = 1 + int_log(leaf_nodes, CHILDREN_PER_NODE);
@@ -986,6 +999,12 @@ struct mapped_device *dm_table_get_md(struct dm_table *t)
 	return t->md;
 }
 
+int dm_table_barrier_ok(struct dm_table *t)
+{
+	return t->barriers_supported;
+}
+EXPORT_SYMBOL(dm_table_barrier_ok);
+
 EXPORT_SYMBOL(dm_vcalloc);
 EXPORT_SYMBOL(dm_get_device);
 EXPORT_SYMBOL(dm_put_device);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4882ce7e88a3..dd953b189f45 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -835,7 +835,11 @@ static int __split_bio(struct mapped_device *md, struct bio *bio)
 	ci.map = dm_get_table(md);
 	if (unlikely(!ci.map))
 		return -EIO;
-
+	if (unlikely(bio_barrier(bio) && !dm_table_barrier_ok(ci.map))) {
+		dm_table_put(ci.map);
+		bio_endio(bio, -EOPNOTSUPP);
+		return 0;
+	}
 	ci.md = md;
 	ci.bio = bio;
 	ci.io = alloc_io(md);
@@ -919,15 +923,6 @@ static int dm_request(struct request_queue *q, struct bio *bio)
 	struct mapped_device *md = q->queuedata;
 	int cpu;
 
-	/*
-	 * There is no use in forwarding any barrier request since we can't
-	 * guarantee it is (or can be) handled by the targets correctly.
-	 */
-	if (unlikely(bio_barrier(bio))) {
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
-	}
-
 	down_read(&md->io_lock);
 
 	cpu = part_stat_lock();
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 0ade60cdef42..5b5d08ba9e92 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -51,6 +51,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits);
  * To check the return value from dm_table_find_target().
  */
 #define dm_target_is_valid(t) ((t)->table)
+int dm_table_barrier_ok(struct dm_table *t);
 
 /*-----------------------------------------------------------------
  * A registry of target types.
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index c1ba76c7c0e5..8209e08969f9 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -112,7 +112,14 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d);
 /*
  * Information about a target type
  */
+
+/*
+ * Target features
+ */
+#define DM_TARGET_SUPPORTS_BARRIERS 0x00000001
+
 struct target_type {
+	uint64_t features;
 	const char *name;
 	struct module *module;
 	unsigned version[3];
-- 
cgit v1.2.3-70-g09d2