From f29ac756a40d0f1bb07d682ea521e7b666ff06d5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Fri, 19 Jun 2009 18:27:26 +0200
Subject: perf_counter: Optimize perf_swcounter_event()

Similar to tracepoints, use an enable variable to reduce
overhead when unused.

Only look for a counter of a particular event type when we know
there is at least one in the system.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/perf_counter.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 89698d8aba5c..e7213e46cf9c 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -669,7 +669,16 @@ static inline int is_software_counter(struct perf_counter *counter)
 		(counter->attr.type != PERF_TYPE_HW_CACHE);
 }
 
-extern void perf_swcounter_event(u32, u64, int, struct pt_regs *, u64);
+extern atomic_t perf_swcounter_enabled[PERF_COUNT_SW_MAX];
+
+extern void __perf_swcounter_event(u32, u64, int, struct pt_regs *, u64);
+
+static inline void
+perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+{
+	if (atomic_read(&perf_swcounter_enabled[event]))
+		__perf_swcounter_event(event, nr, nmi, regs, addr);
+}
 
 extern void __perf_counter_mmap(struct vm_area_struct *vma);
 
-- 
cgit v1.2.3


From 92722b1bb1ebcba767f9c6ee499992ee33367268 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Thu, 11 Jun 2009 14:17:48 +0100
Subject: leds: Further document parameters for blink_set()

The documentation for the parameters of blink_set() was a bit hard
to find so put some where I'd expected to find it.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
---
 include/linux/leds.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/leds.h b/include/linux/leds.h
index 376fe07732ea..c7f0b148df06 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -45,7 +45,9 @@ struct led_classdev {
 	/* Get LED brightness level */
 	enum led_brightness (*brightness_get)(struct led_classdev *led_cdev);
 
-	/* Activate hardware accelerated blink */
+	/* Activate hardware accelerated blink, delays are in
+	 * miliseconds and if none is provided then a sensible default
+	 * should be chosen. */
 	int		(*blink_set)(struct led_classdev *led_cdev,
 				     unsigned long *delay_on,
 				     unsigned long *delay_off);
-- 
cgit v1.2.3


From 5054d39e327f76df022163a2ebd02e444c5d65f9 Mon Sep 17 00:00:00 2001
From: Antonio Ospite <ospite@studenti.unina.it>
Date: Fri, 19 Jun 2009 13:55:42 +0200
Subject: leds: LED driver for National Semiconductor LP3944 Funlight Chip

LEDs driver for National Semiconductor LP3944 Funlight Chip
http://www.national.com/pf/LP/LP3944.html

This helper chip can drive up to 8 leds, with two programmable DIM
modes; it could even be used as a gpio expander but this driver assumes
it is used as a led controller.

The DIM modes are used to set _blink_ patterns for leds, the pattern is
specified supplying two parameters:
  - period: from 0s to 1.6s
  - duty cycle: percentage of the period the led is on, from 0 to 100

LP3944 can be found on Motorola A910 smartphone, where it drives the rgb
leds, the camera flash light and the displays backlights.

Signed-off-by: Antonio Ospite <ospite@studenti.unina.it>
Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
---
 Documentation/leds-lp3944.txt |  50 +++++
 drivers/leds/Kconfig          |  11 +
 drivers/leds/Makefile         |   1 +
 drivers/leds/leds-lp3944.c    | 466 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/leds-lp3944.h   |  53 +++++
 5 files changed, 581 insertions(+)
 create mode 100644 Documentation/leds-lp3944.txt
 create mode 100644 drivers/leds/leds-lp3944.c
 create mode 100644 include/linux/leds-lp3944.h

(limited to 'include')

diff --git a/Documentation/leds-lp3944.txt b/Documentation/leds-lp3944.txt
new file mode 100644
index 000000000000..c6eda18b15ef
--- /dev/null
+++ b/Documentation/leds-lp3944.txt
@@ -0,0 +1,50 @@
+Kernel driver lp3944
+====================
+
+  * National Semiconductor LP3944 Fun-light Chip
+    Prefix: 'lp3944'
+    Addresses scanned: None (see the Notes section below)
+    Datasheet: Publicly available at the National Semiconductor website
+               http://www.national.com/pf/LP/LP3944.html
+
+Authors:
+        Antonio Ospite <ospite@studenti.unina.it>
+
+
+Description
+-----------
+The LP3944 is a helper chip that can drive up to 8 leds, with two programmable
+DIM modes; it could even be used as a gpio expander but this driver assumes it
+is used as a led controller.
+
+The DIM modes are used to set _blink_ patterns for leds, the pattern is
+specified supplying two parameters:
+  - period: from 0s to 1.6s
+  - duty cycle: percentage of the period the led is on, from 0 to 100
+
+Setting a led in DIM0 or DIM1 mode makes it blink according to the pattern.
+See the datasheet for details.
+
+LP3944 can be found on Motorola A910 smartphone, where it drives the rgb
+leds, the camera flash light and the lcds power.
+
+
+Notes
+-----
+The chip is used mainly in embedded contexts, so this driver expects it is
+registered using the i2c_board_info mechanism.
+
+To register the chip at address 0x60 on adapter 0, set the platform data
+according to include/linux/leds-lp3944.h, set the i2c board info:
+
+	static struct i2c_board_info __initdata a910_i2c_board_info[] = {
+		{
+			I2C_BOARD_INFO("lp3944", 0x60),
+			.platform_data = &a910_lp3944_leds,
+		},
+	};
+
+and register it in the platform init function
+
+	i2c_register_board_info(0, a910_i2c_board_info,
+			ARRAY_SIZE(a910_i2c_board_info));
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index cfcd6bf831c9..7c8e7122aaa9 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -146,6 +146,17 @@ config LEDS_GPIO_OF
 	  of_platform devices.  For instance, LEDs which are listed in a "dts"
 	  file.
 
+config LEDS_LP3944
+	tristate "LED Support for N.S. LP3944 (Fun Light) I2C chip"
+	depends on LEDS_CLASS && I2C
+	help
+    This option enables support for LEDs connected to the National
+    Semiconductor LP3944 Lighting Management Unit (LMU) also known as
+    Fun Light Chip.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called leds-lp3944.
+
 config LEDS_CLEVO_MAIL
 	tristate "Mail LED on Clevo notebook"
 	depends on LEDS_CLASS && X86 && SERIO_I8042 && DMI
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 2d41c4dcf92f..e8cdcf77a4c3 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_LEDS_COBALT_RAQ)		+= leds-cobalt-raq.o
 obj-$(CONFIG_LEDS_SUNFIRE)		+= leds-sunfire.o
 obj-$(CONFIG_LEDS_PCA9532)		+= leds-pca9532.o
 obj-$(CONFIG_LEDS_GPIO)			+= leds-gpio.o
+obj-$(CONFIG_LEDS_LP3944)		+= leds-lp3944.o
 obj-$(CONFIG_LEDS_CLEVO_MAIL)		+= leds-clevo-mail.o
 obj-$(CONFIG_LEDS_HP6XX)		+= leds-hp6xx.o
 obj-$(CONFIG_LEDS_FSG)			+= leds-fsg.o
diff --git a/drivers/leds/leds-lp3944.c b/drivers/leds/leds-lp3944.c
new file mode 100644
index 000000000000..5946208ba26e
--- /dev/null
+++ b/drivers/leds/leds-lp3944.c
@@ -0,0 +1,466 @@
+/*
+ * leds-lp3944.c - driver for National Semiconductor LP3944 Funlight Chip
+ *
+ * Copyright (C) 2009 Antonio Ospite <ospite@studenti.unina.it>
+ *
+ * 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.
+ *
+ */
+
+/*
+ * I2C driver for National Semiconductor LP3944 Funlight Chip
+ * http://www.national.com/pf/LP/LP3944.html
+ *
+ * This helper chip can drive up to 8 leds, with two programmable DIM modes;
+ * it could even be used as a gpio expander but this driver assumes it is used
+ * as a led controller.
+ *
+ * The DIM modes are used to set _blink_ patterns for leds, the pattern is
+ * specified supplying two parameters:
+ *   - period: from 0s to 1.6s
+ *   - duty cycle: percentage of the period the led is on, from 0 to 100
+ *
+ * LP3944 can be found on Motorola A910 smartphone, where it drives the rgb
+ * leds, the camera flash light and the displays backlights.
+ */
+
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/leds.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/leds-lp3944.h>
+
+/* Read Only Registers */
+#define LP3944_REG_INPUT1     0x00 /* LEDs 0-7 InputRegister (Read Only) */
+#define LP3944_REG_REGISTER1  0x01 /* None (Read Only) */
+
+#define LP3944_REG_PSC0       0x02 /* Frequency Prescaler 0 (R/W) */
+#define LP3944_REG_PWM0       0x03 /* PWM Register 0 (R/W) */
+#define LP3944_REG_PSC1       0x04 /* Frequency Prescaler 1 (R/W) */
+#define LP3944_REG_PWM1       0x05 /* PWM Register 1 (R/W) */
+#define LP3944_REG_LS0        0x06 /* LEDs 0-3 Selector (R/W) */
+#define LP3944_REG_LS1        0x07 /* LEDs 4-7 Selector (R/W) */
+
+/* These registers are not used to control leds in LP3944, they can store
+ * arbitrary values which the chip will ignore.
+ */
+#define LP3944_REG_REGISTER8  0x08
+#define LP3944_REG_REGISTER9  0x09
+
+#define LP3944_DIM0 0
+#define LP3944_DIM1 1
+
+/* period in ms */
+#define LP3944_PERIOD_MIN 0
+#define LP3944_PERIOD_MAX 1600
+
+/* duty cycle is a percentage */
+#define LP3944_DUTY_CYCLE_MIN 0
+#define LP3944_DUTY_CYCLE_MAX 100
+
+#define ldev_to_led(c)       container_of(c, struct lp3944_led_data, ldev)
+
+/* Saved data */
+struct lp3944_led_data {
+	u8 id;
+	enum lp3944_type type;
+	enum lp3944_status status;
+	struct led_classdev ldev;
+	struct i2c_client *client;
+	struct work_struct work;
+};
+
+struct lp3944_data {
+	struct mutex lock;
+	struct i2c_client *client;
+	struct lp3944_led_data leds[LP3944_LEDS_MAX];
+};
+
+static int lp3944_reg_read(struct i2c_client *client, u8 reg, u8 *value)
+{
+	int tmp;
+
+	tmp = i2c_smbus_read_byte_data(client, reg);
+	if (tmp < 0)
+		return -EINVAL;
+
+	*value = tmp;
+
+	return 0;
+}
+
+static int lp3944_reg_write(struct i2c_client *client, u8 reg, u8 value)
+{
+	return i2c_smbus_write_byte_data(client, reg, value);
+}
+
+/**
+ * Set the period for DIM status
+ *
+ * @client: the i2c client
+ * @dim: either LP3944_DIM0 or LP3944_DIM1
+ * @period: period of a blink, that is a on/off cycle, expressed in ms.
+ */
+static int lp3944_dim_set_period(struct i2c_client *client, u8 dim, u16 period)
+{
+	u8 psc_reg;
+	u8 psc_value;
+	int err;
+
+	if (dim == LP3944_DIM0)
+		psc_reg = LP3944_REG_PSC0;
+	else if (dim == LP3944_DIM1)
+		psc_reg = LP3944_REG_PSC1;
+	else
+		return -EINVAL;
+
+	/* Convert period to Prescaler value */
+	if (period > LP3944_PERIOD_MAX)
+		return -EINVAL;
+
+	psc_value = (period * 255) / LP3944_PERIOD_MAX;
+
+	err = lp3944_reg_write(client, psc_reg, psc_value);
+
+	return err;
+}
+
+/**
+ * Set the duty cycle for DIM status
+ *
+ * @client: the i2c client
+ * @dim: either LP3944_DIM0 or LP3944_DIM1
+ * @duty_cycle: percentage of a period during which a led is ON
+ */
+static int lp3944_dim_set_dutycycle(struct i2c_client *client, u8 dim,
+				    u8 duty_cycle)
+{
+	u8 pwm_reg;
+	u8 pwm_value;
+	int err;
+
+	if (dim == LP3944_DIM0)
+		pwm_reg = LP3944_REG_PWM0;
+	else if (dim == LP3944_DIM1)
+		pwm_reg = LP3944_REG_PWM1;
+	else
+		return -EINVAL;
+
+	/* Convert duty cycle to PWM value */
+	if (duty_cycle > LP3944_DUTY_CYCLE_MAX)
+		return -EINVAL;
+
+	pwm_value = (duty_cycle * 255) / LP3944_DUTY_CYCLE_MAX;
+
+	err = lp3944_reg_write(client, pwm_reg, pwm_value);
+
+	return err;
+}
+
+/**
+ * Set the led status
+ *
+ * @led: a lp3944_led_data structure
+ * @status: one of LP3944_LED_STATUS_OFF
+ *                 LP3944_LED_STATUS_ON
+ *                 LP3944_LED_STATUS_DIM0
+ *                 LP3944_LED_STATUS_DIM1
+ */
+static int lp3944_led_set(struct lp3944_led_data *led, u8 status)
+{
+	struct lp3944_data *data = i2c_get_clientdata(led->client);
+	u8 id = led->id;
+	u8 reg;
+	u8 val = 0;
+	int err;
+
+	dev_dbg(&led->client->dev, "%s: %s, status before normalization:%d\n",
+		__func__, led->ldev.name, status);
+
+	switch (id) {
+	case LP3944_LED0:
+	case LP3944_LED1:
+	case LP3944_LED2:
+	case LP3944_LED3:
+		reg = LP3944_REG_LS0;
+		break;
+	case LP3944_LED4:
+	case LP3944_LED5:
+	case LP3944_LED6:
+	case LP3944_LED7:
+		id -= LP3944_LED4;
+		reg = LP3944_REG_LS1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (status > LP3944_LED_STATUS_DIM1)
+		return -EINVAL;
+
+	/* invert only 0 and 1, leave unchanged the other values,
+	 * remember we are abusing status to set blink patterns
+	 */
+	if (led->type == LP3944_LED_TYPE_LED_INVERTED && status < 2)
+		status = 1 - status;
+
+	mutex_lock(&data->lock);
+	lp3944_reg_read(led->client, reg, &val);
+
+	val &= ~(LP3944_LED_STATUS_MASK << (id << 1));
+	val |= (status << (id << 1));
+
+	dev_dbg(&led->client->dev, "%s: %s, reg:%d id:%d status:%d val:%#x\n",
+		__func__, led->ldev.name, reg, id, status, val);
+
+	/* set led status */
+	err = lp3944_reg_write(led->client, reg, val);
+	mutex_unlock(&data->lock);
+
+	return err;
+}
+
+static int lp3944_led_set_blink(struct led_classdev *led_cdev,
+				unsigned long *delay_on,
+				unsigned long *delay_off)
+{
+	struct lp3944_led_data *led = ldev_to_led(led_cdev);
+	u16 period;
+	u8 duty_cycle;
+	int err;
+
+	/* units are in ms */
+	if (*delay_on + *delay_off > LP3944_PERIOD_MAX)
+		return -EINVAL;
+
+	if (*delay_on == 0 && *delay_off == 0) {
+		/* Special case: the leds subsystem requires a default user
+		 * friendly blink pattern for the LED.  Let's blink the led
+		 * slowly (1Hz).
+		 */
+		*delay_on = 500;
+		*delay_off = 500;
+	}
+
+	period = (*delay_on) + (*delay_off);
+
+	/* duty_cycle is the percentage of period during which the led is ON */
+	duty_cycle = 100 * (*delay_on) / period;
+
+	/* invert duty cycle for inverted leds, this has the same effect of
+	 * swapping delay_on and delay_off
+	 */
+	if (led->type == LP3944_LED_TYPE_LED_INVERTED)
+		duty_cycle = 100 - duty_cycle;
+
+	/* NOTE: using always the first DIM mode, this means that all leds
+	 * will have the same blinking pattern.
+	 *
+	 * We could find a way later to have two leds blinking in hardware
+	 * with different patterns at the same time, falling back to software
+	 * control for the other ones.
+	 */
+	err = lp3944_dim_set_period(led->client, LP3944_DIM0, period);
+	if (err)
+		return err;
+
+	err = lp3944_dim_set_dutycycle(led->client, LP3944_DIM0, duty_cycle);
+	if (err)
+		return err;
+
+	dev_dbg(&led->client->dev, "%s: OK hardware accelerated blink!\n",
+		__func__);
+
+	led->status = LP3944_LED_STATUS_DIM0;
+	schedule_work(&led->work);
+
+	return 0;
+}
+
+static void lp3944_led_set_brightness(struct led_classdev *led_cdev,
+				      enum led_brightness brightness)
+{
+	struct lp3944_led_data *led = ldev_to_led(led_cdev);
+
+	dev_dbg(&led->client->dev, "%s: %s, %d\n",
+		__func__, led_cdev->name, brightness);
+
+	led->status = brightness;
+	schedule_work(&led->work);
+}
+
+static void lp3944_led_work(struct work_struct *work)
+{
+	struct lp3944_led_data *led;
+
+	led = container_of(work, struct lp3944_led_data, work);
+	lp3944_led_set(led, led->status);
+}
+
+static int lp3944_configure(struct i2c_client *client,
+			    struct lp3944_data *data,
+			    struct lp3944_platform_data *pdata)
+{
+	int i, err = 0;
+
+	for (i = 0; i < pdata->leds_size; i++) {
+		struct lp3944_led *pled = &pdata->leds[i];
+		struct lp3944_led_data *led = &data->leds[i];
+		led->client = client;
+		led->id = i;
+
+		switch (pled->type) {
+
+		case LP3944_LED_TYPE_LED:
+		case LP3944_LED_TYPE_LED_INVERTED:
+			led->type = pled->type;
+			led->status = pled->status;
+			led->ldev.name = pled->name;
+			led->ldev.max_brightness = 1;
+			led->ldev.brightness_set = lp3944_led_set_brightness;
+			led->ldev.blink_set = lp3944_led_set_blink;
+			led->ldev.flags = LED_CORE_SUSPENDRESUME;
+
+			INIT_WORK(&led->work, lp3944_led_work);
+			err = led_classdev_register(&client->dev, &led->ldev);
+			if (err < 0) {
+				dev_err(&client->dev,
+					"couldn't register LED %s\n",
+					led->ldev.name);
+				goto exit;
+			}
+
+			/* to expose the default value to userspace */
+			led->ldev.brightness = led->status;
+
+			/* Set the default led status */
+			err = lp3944_led_set(led, led->status);
+			if (err < 0) {
+				dev_err(&client->dev,
+					"%s couldn't set STATUS %d\n",
+					led->ldev.name, led->status);
+				goto exit;
+			}
+			break;
+
+		case LP3944_LED_TYPE_NONE:
+		default:
+			break;
+
+		}
+	}
+	return 0;
+
+exit:
+	if (i > 0)
+		for (i = i - 1; i >= 0; i--)
+			switch (pdata->leds[i].type) {
+
+			case LP3944_LED_TYPE_LED:
+			case LP3944_LED_TYPE_LED_INVERTED:
+				led_classdev_unregister(&data->leds[i].ldev);
+				cancel_work_sync(&data->leds[i].work);
+				break;
+
+			case LP3944_LED_TYPE_NONE:
+			default:
+				break;
+			}
+
+	return err;
+}
+
+static int __devinit lp3944_probe(struct i2c_client *client,
+				  const struct i2c_device_id *id)
+{
+	struct lp3944_platform_data *lp3944_pdata = client->dev.platform_data;
+	struct lp3944_data *data;
+
+	if (lp3944_pdata == NULL) {
+		dev_err(&client->dev, "no platform data\n");
+		return -EINVAL;
+	}
+
+	/* Let's see whether this adapter can support what we need. */
+	if (!i2c_check_functionality(client->adapter,
+				I2C_FUNC_SMBUS_BYTE_DATA)) {
+		dev_err(&client->dev, "insufficient functionality!\n");
+		return -ENODEV;
+	}
+
+	data = kzalloc(sizeof(struct lp3944_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->client = client;
+	i2c_set_clientdata(client, data);
+
+	mutex_init(&data->lock);
+
+	dev_info(&client->dev, "lp3944 enabled\n");
+
+	lp3944_configure(client, data, lp3944_pdata);
+	return 0;
+}
+
+static int __devexit lp3944_remove(struct i2c_client *client)
+{
+	struct lp3944_platform_data *pdata = client->dev.platform_data;
+	struct lp3944_data *data = i2c_get_clientdata(client);
+	int i;
+
+	for (i = 0; i < pdata->leds_size; i++)
+		switch (data->leds[i].type) {
+		case LP3944_LED_TYPE_LED:
+		case LP3944_LED_TYPE_LED_INVERTED:
+			led_classdev_unregister(&data->leds[i].ldev);
+			cancel_work_sync(&data->leds[i].work);
+			break;
+
+		case LP3944_LED_TYPE_NONE:
+		default:
+			break;
+		}
+
+	kfree(data);
+	i2c_set_clientdata(client, NULL);
+
+	return 0;
+}
+
+/* lp3944 i2c driver struct */
+static const struct i2c_device_id lp3944_id[] = {
+	{"lp3944", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, lp3944_id);
+
+static struct i2c_driver lp3944_driver = {
+	.driver   = {
+		   .name = "lp3944",
+	},
+	.probe    = lp3944_probe,
+	.remove   = __devexit_p(lp3944_remove),
+	.id_table = lp3944_id,
+};
+
+static int __init lp3944_module_init(void)
+{
+	return i2c_add_driver(&lp3944_driver);
+}
+
+static void __exit lp3944_module_exit(void)
+{
+	i2c_del_driver(&lp3944_driver);
+}
+
+module_init(lp3944_module_init);
+module_exit(lp3944_module_exit);
+
+MODULE_AUTHOR("Antonio Ospite <ospite@studenti.unina.it>");
+MODULE_DESCRIPTION("LP3944 Fun Light Chip");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/leds-lp3944.h b/include/linux/leds-lp3944.h
new file mode 100644
index 000000000000..afc9f9fd70f5
--- /dev/null
+++ b/include/linux/leds-lp3944.h
@@ -0,0 +1,53 @@
+/*
+ * leds-lp3944.h - platform data structure for lp3944 led controller
+ *
+ * Copyright (C) 2009 Antonio Ospite <ospite@studenti.unina.it>
+ *
+ * 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.
+ *
+ */
+
+#ifndef __LINUX_LEDS_LP3944_H
+#define __LINUX_LEDS_LP3944_H
+
+#include <linux/leds.h>
+#include <linux/workqueue.h>
+
+#define LP3944_LED0 0
+#define LP3944_LED1 1
+#define LP3944_LED2 2
+#define LP3944_LED3 3
+#define LP3944_LED4 4
+#define LP3944_LED5 5
+#define LP3944_LED6 6
+#define LP3944_LED7 7
+#define LP3944_LEDS_MAX 8
+
+#define LP3944_LED_STATUS_MASK	0x03
+enum lp3944_status {
+	LP3944_LED_STATUS_OFF  = 0x0,
+	LP3944_LED_STATUS_ON   = 0x1,
+	LP3944_LED_STATUS_DIM0 = 0x2,
+	LP3944_LED_STATUS_DIM1 = 0x3
+};
+
+enum lp3944_type {
+	LP3944_LED_TYPE_NONE,
+	LP3944_LED_TYPE_LED,
+	LP3944_LED_TYPE_LED_INVERTED,
+};
+
+struct lp3944_led {
+	char *name;
+	enum lp3944_type type;
+	enum lp3944_status status;
+};
+
+struct lp3944_platform_data {
+	struct lp3944_led leds[LP3944_LEDS_MAX];
+	u8 leds_size;
+};
+
+#endif /* __LINUX_LEDS_LP3944_H */
-- 
cgit v1.2.3


From ed88bae6918fa990cbfe47316bd0f790121aaf00 Mon Sep 17 00:00:00 2001
From: Trent Piepho <xyzzy@speakeasy.org>
Date: Tue, 12 May 2009 15:33:12 -0700
Subject: leds: Add options to have GPIO LEDs start on or keep their state

There already is a "default-on" trigger but there are problems with it.

For one, it's a inefficient way to do it and requires led trigger support
to be compiled in.

But the real reason is that is produces a glitch on the LED.  The GPIO is
allocate with the LED *off*, then *later* when the trigger runs it is
turned back on.  If the LED was already on via the GPIO's reset default or
action of the firmware, this produces a glitch where the LED goes from on
to off to on.  While normally this is fast enough that it wouldn't be
noticeable to a human observer, there are still serious problems.

One is that there may be something else on the GPIO line, like a hardware
alarm or watchdog, that is fast enough to notice the glitch.

Another is that the kernel may panic before the LED is turned back on, thus
hanging with the LED in the wrong state.  This is not just speculation, but
actually happened to me with an embedded system that has an LED which
should turn off when the kernel finishes booting, which was left in the
incorrect state due to a bug in the OF LED binding code.

We also let GPIO LEDs get their initial value from whatever the current
state of the GPIO line is.  On some systems the LEDs are put into some
state by the firmware or hardware before Linux boots, and it is desired to
have them keep this state which is otherwise unknown to Linux.

This requires that the underlying GPIO driver support reading the value of
output GPIOs.  Some drivers support this and some do not.

The platform device binding gains a field in the platform data
"default_state" that controls this.  There are three constants defined to
select from on, off, or keeping the current state.  The OpenFirmware
binding uses a property named "default-state" that can be set to "on",
"off", or "keep".  The default if the property isn't present is off.

Signed-off-by: Trent Piepho <xyzzy@speakeasy.org>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: Wolfram Sang <w.sang@pengutronix.de>
Acked-by: Sean MacLennan <smaclennan@pikatech.com>
Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
---
 Documentation/powerpc/dts-bindings/gpio/led.txt | 17 ++++++++++++++++-
 drivers/leds/leds-gpio.c                        | 20 +++++++++++++++++---
 include/linux/leds.h                            |  9 +++++++--
 3 files changed, 40 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/powerpc/dts-bindings/gpio/led.txt b/Documentation/powerpc/dts-bindings/gpio/led.txt
index 4fe14deedc0a..064db928c3c1 100644
--- a/Documentation/powerpc/dts-bindings/gpio/led.txt
+++ b/Documentation/powerpc/dts-bindings/gpio/led.txt
@@ -16,10 +16,17 @@ LED sub-node properties:
   string defining the trigger assigned to the LED.  Current triggers are:
     "backlight" - LED will act as a back-light, controlled by the framebuffer
 		  system
-    "default-on" - LED will turn on
+    "default-on" - LED will turn on, but see "default-state" below
     "heartbeat" - LED "double" flashes at a load average based rate
     "ide-disk" - LED indicates disk activity
     "timer" - LED flashes at a fixed, configurable rate
+- default-state:  (optional) The initial state of the LED.  Valid
+  values are "on", "off", and "keep".  If the LED is already on or off
+  and the default-state property is set the to same value, then no
+  glitch should be produced where the LED momentarily turns off (or
+  on).  The "keep" setting will keep the LED at whatever its current
+  state is, without producing a glitch.  The default is off if this
+  property is not present.
 
 Examples:
 
@@ -30,14 +37,22 @@ leds {
 		gpios = <&mcu_pio 0 1>; /* Active low */
 		linux,default-trigger = "ide-disk";
 	};
+
+	fault {
+		gpios = <&mcu_pio 1 0>;
+		/* Keep LED on if BIOS detected hardware fault */
+		default-state = "keep";
+	};
 };
 
 run-control {
 	compatible = "gpio-leds";
 	red {
 		gpios = <&mpc8572 6 0>;
+		default-state = "off";
 	};
 	green {
 		gpios = <&mpc8572 7 0>;
+		default-state = "on";
 	};
 }
diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
index 76895e691042..6b06638eb5b4 100644
--- a/drivers/leds/leds-gpio.c
+++ b/drivers/leds/leds-gpio.c
@@ -76,7 +76,7 @@ static int __devinit create_gpio_led(const struct gpio_led *template,
 	struct gpio_led_data *led_dat, struct device *parent,
 	int (*blink_set)(unsigned, unsigned long *, unsigned long *))
 {
-	int ret;
+	int ret, state;
 
 	/* skip leds that aren't available */
 	if (!gpio_is_valid(template->gpio)) {
@@ -99,11 +99,15 @@ static int __devinit create_gpio_led(const struct gpio_led *template,
 		led_dat->cdev.blink_set = gpio_blink_set;
 	}
 	led_dat->cdev.brightness_set = gpio_led_set;
-	led_dat->cdev.brightness = LED_OFF;
+	if (template->default_state == LEDS_GPIO_DEFSTATE_KEEP)
+		state = !!gpio_get_value(led_dat->gpio) ^ led_dat->active_low;
+	else
+		state = (template->default_state == LEDS_GPIO_DEFSTATE_ON);
+	led_dat->cdev.brightness = state ? LED_FULL : LED_OFF;
 	if (!template->retain_state_suspended)
 		led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
 
-	ret = gpio_direction_output(led_dat->gpio, led_dat->active_low);
+	ret = gpio_direction_output(led_dat->gpio, led_dat->active_low ^ state);
 	if (ret < 0)
 		goto err;
 
@@ -223,12 +227,22 @@ static int __devinit of_gpio_leds_probe(struct of_device *ofdev,
 	memset(&led, 0, sizeof(led));
 	for_each_child_of_node(np, child) {
 		enum of_gpio_flags flags;
+		const char *state;
 
 		led.gpio = of_get_gpio_flags(child, 0, &flags);
 		led.active_low = flags & OF_GPIO_ACTIVE_LOW;
 		led.name = of_get_property(child, "label", NULL) ? : child->name;
 		led.default_trigger =
 			of_get_property(child, "linux,default-trigger", NULL);
+		state = of_get_property(child, "default-state", NULL);
+		if (state) {
+			if (!strcmp(state, "keep"))
+				led.default_state = LEDS_GPIO_DEFSTATE_KEEP;
+			else if(!strcmp(state, "on"))
+				led.default_state = LEDS_GPIO_DEFSTATE_ON;
+			else
+				led.default_state = LEDS_GPIO_DEFSTATE_OFF;
+		}
 
 		ret = create_gpio_led(&led, &pdata->led_data[pdata->num_leds++],
 				      &ofdev->dev, NULL);
diff --git a/include/linux/leds.h b/include/linux/leds.h
index c7f0b148df06..62af62915cf7 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -143,9 +143,14 @@ struct gpio_led {
 	const char *name;
 	const char *default_trigger;
 	unsigned 	gpio;
-	u8 		active_low : 1;
-	u8		retain_state_suspended : 1;
+	unsigned	active_low : 1;
+	unsigned	retain_state_suspended : 1;
+	unsigned	default_state : 2;
+	/* default_state should be one of LEDS_GPIO_DEFSTATE_(ON|OFF|KEEP) */
 };
+#define LEDS_GPIO_DEFSTATE_OFF	0
+#define LEDS_GPIO_DEFSTATE_ON	1
+#define LEDS_GPIO_DEFSTATE_KEEP	2
 
 struct gpio_led_platform_data {
 	int 		num_leds;
-- 
cgit v1.2.3


From a1dd8c617217322614f0465ae347895c4b58e1ab Mon Sep 17 00:00:00 2001
From: Richard Purdie <rpurdie@linux.intel.com>
Date: Mon, 22 Jun 2009 14:54:13 +0100
Subject: leds: Futher document blink_set

Futher document blink_set function pointer

Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
---
 include/linux/leds.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/leds.h b/include/linux/leds.h
index 62af62915cf7..d8bf9665e70c 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -47,7 +47,8 @@ struct led_classdev {
 
 	/* Activate hardware accelerated blink, delays are in
 	 * miliseconds and if none is provided then a sensible default
-	 * should be chosen. */
+	 * should be chosen. The call can adjust the timings if it can't
+	 * match the values specified exactly. */
 	int		(*blink_set)(struct led_classdev *led_cdev,
 				     unsigned long *delay_on,
 				     unsigned long *delay_off);
-- 
cgit v1.2.3


From e14cbee401cd00779a5267128371506b22c77bc9 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel@daenzer.net>
Date: Tue, 23 Jun 2009 12:36:32 +0200
Subject: drm: Fix shifts which were miscalculated when converting from
 bitfields.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Looks like I managed to mess up most shifts when converting from bitfields. :(

The patch below works on my Thinkpad T500 (as well as on my PowerBook,
where the previous change worked as well, maybe out of luck...). I'd
appreciate more testing and eyes looking over it though.

Signed-off-by: Michel Dänzer <daenzer@vmware.com>
Tested-by: Michael Pyne <mpyne@kde.org>
Signed-off-by: Dave Airlie <airlied@linux.ie>
---
 drivers/gpu/drm/drm_edid.c | 12 ++++++------
 include/drm/drm_edid.h     | 38 +++++++++++++++++++-------------------
 2 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 7d0835226f6e..80cc6d06d61b 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -294,10 +294,10 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev,
 	unsigned vactive = (pt->vactive_vblank_hi & 0xf0) << 4 | pt->vactive_lo;
 	unsigned hblank = (pt->hactive_hblank_hi & 0xf) << 8 | pt->hblank_lo;
 	unsigned vblank = (pt->vactive_vblank_hi & 0xf) << 8 | pt->vblank_lo;
-	unsigned hsync_offset = (pt->hsync_vsync_offset_pulse_width_hi & 0x3) << 8 | pt->hsync_offset_lo;
-	unsigned hsync_pulse_width = (pt->hsync_vsync_offset_pulse_width_hi & 0xc) << 6 | pt->hsync_pulse_width_lo;
-	unsigned vsync_offset = (pt->hsync_vsync_offset_pulse_width_hi & 0x30) | (pt->vsync_offset_pulse_width_lo & 0xf);
-	unsigned vsync_pulse_width = (pt->hsync_vsync_offset_pulse_width_hi & 0xc0) >> 2 | pt->vsync_offset_pulse_width_lo >> 4;
+	unsigned hsync_offset = (pt->hsync_vsync_offset_pulse_width_hi & 0xc0) << 2 | pt->hsync_offset_lo;
+	unsigned hsync_pulse_width = (pt->hsync_vsync_offset_pulse_width_hi & 0x30) << 4 | pt->hsync_pulse_width_lo;
+	unsigned vsync_offset = (pt->hsync_vsync_offset_pulse_width_hi & 0xc) >> 2 | pt->vsync_offset_pulse_width_lo >> 4;
+	unsigned vsync_pulse_width = (pt->hsync_vsync_offset_pulse_width_hi & 0x3) << 4 | (pt->vsync_offset_pulse_width_lo & 0xf);
 
 	/* ignore tiny modes */
 	if (hactive < 64 || vactive < 64)
@@ -347,8 +347,8 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev,
 	mode->flags |= (pt->misc & DRM_EDID_PT_VSYNC_POSITIVE) ?
 		DRM_MODE_FLAG_PVSYNC : DRM_MODE_FLAG_NVSYNC;
 
-	mode->width_mm = pt->width_mm_lo | (pt->width_height_mm_hi & 0xf) << 8;
-	mode->height_mm = pt->height_mm_lo | (pt->width_height_mm_hi & 0xf0) << 4;
+	mode->width_mm = pt->width_mm_lo | (pt->width_height_mm_hi & 0xf0) << 4;
+	mode->height_mm = pt->height_mm_lo | (pt->width_height_mm_hi & 0xf) << 8;
 
 	if (quirks & EDID_QUIRK_DETAILED_IN_CM) {
 		mode->width_mm *= 10;
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index c263e4d71754..7d6c9a2dfcbb 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -35,11 +35,11 @@ struct est_timings {
 } __attribute__((packed));
 
 /* 00=16:10, 01=4:3, 10=5:4, 11=16:9 */
-#define EDID_TIMING_ASPECT_SHIFT 0
+#define EDID_TIMING_ASPECT_SHIFT 6
 #define EDID_TIMING_ASPECT_MASK  (0x3 << EDID_TIMING_ASPECT_SHIFT)
 
 /* need to add 60 */
-#define EDID_TIMING_VFREQ_SHIFT  2
+#define EDID_TIMING_VFREQ_SHIFT  0
 #define EDID_TIMING_VFREQ_MASK   (0x3f << EDID_TIMING_VFREQ_SHIFT)
 
 struct std_timing {
@@ -47,11 +47,11 @@ struct std_timing {
 	u8 vfreq_aspect;
 } __attribute__((packed));
 
-#define DRM_EDID_PT_HSYNC_POSITIVE (1 << 6)
-#define DRM_EDID_PT_VSYNC_POSITIVE (1 << 5)
+#define DRM_EDID_PT_HSYNC_POSITIVE (1 << 1)
+#define DRM_EDID_PT_VSYNC_POSITIVE (1 << 2)
 #define DRM_EDID_PT_SEPARATE_SYNC  (3 << 3)
-#define DRM_EDID_PT_STEREO         (1 << 2)
-#define DRM_EDID_PT_INTERLACED     (1 << 1)
+#define DRM_EDID_PT_STEREO         (1 << 5)
+#define DRM_EDID_PT_INTERLACED     (1 << 7)
 
 /* If detailed data is pixel timing */
 struct detailed_pixel_timing {
@@ -93,7 +93,7 @@ struct detailed_data_monitor_range {
 } __attribute__((packed));
 
 struct detailed_data_wpindex {
-	u8 white_xy_lo; /* Upper 2 bits each */
+	u8 white_yx_lo; /* Lower 2 bits each */
 	u8 white_x_hi;
 	u8 white_y_hi;
 	u8 gamma; /* need to divide by 100 then add 1 */
@@ -135,21 +135,21 @@ struct detailed_timing {
 	} data;
 } __attribute__((packed));
 
-#define DRM_EDID_INPUT_SERRATION_VSYNC (1 << 7)
-#define DRM_EDID_INPUT_SYNC_ON_GREEN   (1 << 5)
-#define DRM_EDID_INPUT_COMPOSITE_SYNC  (1 << 4)
+#define DRM_EDID_INPUT_SERRATION_VSYNC (1 << 0)
+#define DRM_EDID_INPUT_SYNC_ON_GREEN   (1 << 1)
+#define DRM_EDID_INPUT_COMPOSITE_SYNC  (1 << 2)
 #define DRM_EDID_INPUT_SEPARATE_SYNCS  (1 << 3)
-#define DRM_EDID_INPUT_BLANK_TO_BLACK  (1 << 2)
-#define DRM_EDID_INPUT_VIDEO_LEVEL     (3 << 1)
-#define DRM_EDID_INPUT_DIGITAL         (1 << 0) /* bits above must be zero if set */
+#define DRM_EDID_INPUT_BLANK_TO_BLACK  (1 << 4)
+#define DRM_EDID_INPUT_VIDEO_LEVEL     (3 << 5)
+#define DRM_EDID_INPUT_DIGITAL         (1 << 7) /* bits below must be zero if set */
 
-#define DRM_EDID_FEATURE_DEFAULT_GTF      (1 << 7)
-#define DRM_EDID_FEATURE_PREFERRED_TIMING (1 << 6)
-#define DRM_EDID_FEATURE_STANDARD_COLOR   (1 << 5)
+#define DRM_EDID_FEATURE_DEFAULT_GTF      (1 << 0)
+#define DRM_EDID_FEATURE_PREFERRED_TIMING (1 << 1)
+#define DRM_EDID_FEATURE_STANDARD_COLOR   (1 << 2)
 #define DRM_EDID_FEATURE_DISPLAY_TYPE     (3 << 3) /* 00=mono, 01=rgb, 10=non-rgb, 11=unknown */
-#define DRM_EDID_FEATURE_PM_ACTIVE_OFF    (1 << 2)
-#define DRM_EDID_FEATURE_PM_SUSPEND       (1 << 1)
-#define DRM_EDID_FEATURE_PM_STANDBY       (1 << 0)
+#define DRM_EDID_FEATURE_PM_ACTIVE_OFF    (1 << 5)
+#define DRM_EDID_FEATURE_PM_SUSPEND       (1 << 6)
+#define DRM_EDID_FEATURE_PM_STANDBY       (1 << 7)
 
 struct edid {
 	u8 header[8];
-- 
cgit v1.2.3


From 346c17a6cf60375323adfaa4b8a9d841049f890e Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Mon, 22 Jun 2009 07:38:26 +0000
Subject: ide: relax DMA info validity checking

There are some broken devices that report multiple DMA xfer modes
enabled at once (ATA spec doesn't allow it) but otherwise work fine
with DMA so just delete ide_id_dma_bug().

[ As discovered by detective work by Frans and Bart, due to how
  handling of the ID block was handled before commit c419993
  ("ide-iops: only clear DMA words on setting DMA mode") this
  check was always seeing zeros in the fields or other similar
  garbage.  Therefore this check wasn't actually checking anything.
  Now that the tests actually check the real bits, all we see are
  devices that trigger the check yet work perfectly fine, therefore
  killing this useless check is the best thing to do. -DaveM ]

Reported-by: Frans Pop <elendil@planet.nl>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ide/ide-dma.c  | 21 ---------------------
 drivers/ide/ide-iops.c |  3 ---
 include/linux/ide.h    |  2 --
 3 files changed, 26 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c
index 219e6fb78dc6..ee58c88dee5a 100644
--- a/drivers/ide/ide-dma.c
+++ b/drivers/ide/ide-dma.c
@@ -361,9 +361,6 @@ static int ide_tune_dma(ide_drive_t *drive)
 	if (__ide_dma_bad_drive(drive))
 		return 0;
 
-	if (ide_id_dma_bug(drive))
-		return 0;
-
 	if (hwif->host_flags & IDE_HFLAG_TRUST_BIOS_FOR_DMA)
 		return config_drive_for_dma(drive);
 
@@ -394,24 +391,6 @@ static int ide_dma_check(ide_drive_t *drive)
 	return -1;
 }
 
-int ide_id_dma_bug(ide_drive_t *drive)
-{
-	u16 *id = drive->id;
-
-	if (id[ATA_ID_FIELD_VALID] & 4) {
-		if ((id[ATA_ID_UDMA_MODES] >> 8) &&
-		    (id[ATA_ID_MWDMA_MODES] >> 8))
-			goto err_out;
-	} else if ((id[ATA_ID_MWDMA_MODES] >> 8) &&
-		   (id[ATA_ID_SWDMA_MODES] >> 8))
-		goto err_out;
-
-	return 0;
-err_out:
-	printk(KERN_ERR "%s: bad DMA info in identify block\n", drive->name);
-	return 1;
-}
-
 int ide_set_dma(ide_drive_t *drive)
 {
 	int rc;
diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c
index fa047150a1c6..917186ec4966 100644
--- a/drivers/ide/ide-iops.c
+++ b/drivers/ide/ide-iops.c
@@ -329,9 +329,6 @@ int ide_driveid_update(ide_drive_t *drive)
 
 	kfree(id);
 
-	if ((drive->dev_flags & IDE_DFLAG_USING_DMA) && ide_id_dma_bug(drive))
-		ide_dma_off(drive);
-
 	return 1;
 out_err:
 	if (rc == 2)
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 95c6e00a72e8..cf1f3888067c 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1361,7 +1361,6 @@ int ide_in_drive_list(u16 *, const struct drive_list_entry *);
 #ifdef CONFIG_BLK_DEV_IDEDMA
 int ide_dma_good_drive(ide_drive_t *);
 int __ide_dma_bad_drive(ide_drive_t *);
-int ide_id_dma_bug(ide_drive_t *);
 
 u8 ide_find_dma_mode(ide_drive_t *, u8);
 
@@ -1402,7 +1401,6 @@ void ide_dma_lost_irq(ide_drive_t *);
 ide_startstop_t ide_dma_timeout_retry(ide_drive_t *, int);
 
 #else
-static inline int ide_id_dma_bug(ide_drive_t *drive) { return 0; }
 static inline u8 ide_find_dma_mode(ide_drive_t *drive, u8 speed) { return 0; }
 static inline u8 ide_max_dma_mode(ide_drive_t *drive) { return 0; }
 static inline void ide_dma_off_quietly(ide_drive_t *drive) { ; }
-- 
cgit v1.2.3


From 507e123151149e578c9aae33eb876c49824da5f8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 23 Jun 2009 17:38:15 +0200
Subject: timer stats: Optimize by adding quick check to avoid function calls

When the kernel is configured with CONFIG_TIMER_STATS but timer
stats are runtime disabled we still get calls to
__timer_stats_timer_set_start_info which initializes some
fields in the corresponding struct timer_list.

So add some quick checks in the the timer stats setup functions
to avoid function calls to __timer_stats_timer_set_start_info
when timer stats are disabled.

In an artificial workload that does nothing but playing ping
pong with a single tcp packet via loopback this decreases cpu
consumption by 1 - 1.5%.

This is part of a modified function trace output on SLES11:

 perl-2497  [00] 28630647177732388 [+  125]: sk_reset_timer <-tcp_v4_rcv
 perl-2497  [00] 28630647177732513 [+  125]: mod_timer <-sk_reset_timer
 perl-2497  [00] 28630647177732638 [+  125]: __timer_stats_timer_set_start_info <-mod_timer
 perl-2497  [00] 28630647177732763 [+  125]: __mod_timer <-mod_timer
 perl-2497  [00] 28630647177732888 [+  125]: __timer_stats_timer_set_start_info <-__mod_timer
 perl-2497  [00] 28630647177733013 [+   93]: lock_timer_base <-__mod_timer

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mustafa Mesanovic <mustafa.mesanovic@de.ibm.com>
Cc: Arjan van de Ven <arjan@infradead.org>
LKML-Reference: <20090623153811.GA4641@osiris.boeblingen.de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/hrtimer.h   |  5 +++++
 include/linux/timer.h     |  4 ++++
 kernel/time/timer_stats.c | 16 ++++++++--------
 kernel/timer.c            |  2 ++
 4 files changed, 19 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 7400900de94a..54648e625efd 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -21,6 +21,7 @@
 #include <linux/list.h>
 #include <linux/wait.h>
 #include <linux/percpu.h>
+#include <linux/timer.h>
 
 
 struct hrtimer_clock_base;
@@ -447,6 +448,8 @@ extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 
 static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
 {
+	if (likely(!timer->start_pid))
+		return;
 	timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
 				 timer->function, timer->start_comm, 0);
 }
@@ -456,6 +459,8 @@ extern void __timer_stats_hrtimer_set_start_info(struct hrtimer *timer,
 
 static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
 {
+	if (likely(!timer_stats_active))
+		return;
 	__timer_stats_hrtimer_set_start_info(timer, __builtin_return_address(0));
 }
 
diff --git a/include/linux/timer.h b/include/linux/timer.h
index ccf882eed8f8..be62ec2ebea5 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -190,6 +190,8 @@ extern unsigned long get_next_timer_interrupt(unsigned long now);
  */
 #ifdef CONFIG_TIMER_STATS
 
+extern int timer_stats_active;
+
 #define TIMER_STATS_FLAG_DEFERRABLE	0x1
 
 extern void init_timer_stats(void);
@@ -203,6 +205,8 @@ extern void __timer_stats_timer_set_start_info(struct timer_list *timer,
 
 static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
 {
+	if (likely(!timer_stats_active))
+		return;
 	__timer_stats_timer_set_start_info(timer, __builtin_return_address(0));
 }
 
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index c994530d166d..4cde8b9c716f 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -96,7 +96,7 @@ static DEFINE_MUTEX(show_mutex);
 /*
  * Collection status, active/inactive:
  */
-static int __read_mostly active;
+int __read_mostly timer_stats_active;
 
 /*
  * Beginning/end timestamps of measurement:
@@ -242,7 +242,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	struct entry *entry, input;
 	unsigned long flags;
 
-	if (likely(!active))
+	if (likely(!timer_stats_active))
 		return;
 
 	lock = &per_cpu(lookup_lock, raw_smp_processor_id());
@@ -254,7 +254,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
 	input.timer_flag = timer_flag;
 
 	spin_lock_irqsave(lock, flags);
-	if (!active)
+	if (!timer_stats_active)
 		goto out_unlock;
 
 	entry = tstat_lookup(&input, comm);
@@ -290,7 +290,7 @@ static int tstats_show(struct seq_file *m, void *v)
 	/*
 	 * If still active then calculate up to now:
 	 */
-	if (active)
+	if (timer_stats_active)
 		time_stop = ktime_get();
 
 	time = ktime_sub(time_stop, time_start);
@@ -368,18 +368,18 @@ static ssize_t tstats_write(struct file *file, const char __user *buf,
 	mutex_lock(&show_mutex);
 	switch (ctl[0]) {
 	case '0':
-		if (active) {
-			active = 0;
+		if (timer_stats_active) {
+			timer_stats_active = 0;
 			time_stop = ktime_get();
 			sync_access();
 		}
 		break;
 	case '1':
-		if (!active) {
+		if (!timer_stats_active) {
 			reset_entries();
 			time_start = ktime_get();
 			smp_mb();
-			active = 1;
+			timer_stats_active = 1;
 		}
 		break;
 	default:
diff --git a/kernel/timer.c b/kernel/timer.c
index 54d3912f8cad..0b36b9e5cc8b 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -380,6 +380,8 @@ static void timer_stats_account_timer(struct timer_list *timer)
 {
 	unsigned int flag = 0;
 
+	if (likely(!timer->start_site))
+		return;
 	if (unlikely(tbase_get_deferrable(timer->base)))
 		flag |= TIMER_STATS_FLAG_DEFERRABLE;
 
-- 
cgit v1.2.3


From c7a1a4c80f873d5d6ecd173035bb80eba489f380 Mon Sep 17 00:00:00 2001
From: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Date: Wed, 24 Jun 2009 01:07:44 +0000
Subject: Phonet: publicize the Netlink notification function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/phonet/pn_dev.h | 1 +
 net/phonet/pn_netlink.c     | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/phonet/pn_dev.h b/include/net/phonet/pn_dev.h
index 5054dc5ea2c2..29d126736611 100644
--- a/include/net/phonet/pn_dev.h
+++ b/include/net/phonet/pn_dev.h
@@ -45,6 +45,7 @@ int phonet_address_add(struct net_device *dev, u8 addr);
 int phonet_address_del(struct net_device *dev, u8 addr);
 u8 phonet_address_get(struct net_device *dev, u8 addr);
 int phonet_address_lookup(struct net *net, u8 addr);
+void phonet_address_notify(int event, struct net_device *dev, u8 addr);
 
 #define PN_NO_ADDR	0xff
 
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index cec4e5951681..f8b4cee434c2 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -32,7 +32,7 @@
 static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr,
 		     u32 pid, u32 seq, int event);
 
-static void rtmsg_notify(int event, struct net_device *dev, u8 addr)
+void phonet_address_notify(int event, struct net_device *dev, u8 addr)
 {
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -94,7 +94,7 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr)
 	else
 		err = phonet_address_del(dev, pnaddr);
 	if (!err)
-		rtmsg_notify(nlh->nlmsg_type, dev, pnaddr);
+		phonet_address_notify(nlh->nlmsg_type, dev, pnaddr);
 	return err;
 }
 
-- 
cgit v1.2.3


From 6fdc03709433ccc2005f0f593ae9d9dd04f7b485 Mon Sep 17 00:00:00 2001
From: Stefan Richter <stefanr@s5r6.in-berlin.de>
Date: Sat, 20 Jun 2009 13:23:59 +0200
Subject: firewire: core: do not DMA-map stack addresses

The DMA mapping API cannot map on-stack addresses, as explained in
Documentation/DMA-mapping.txt.  Convert the two cases of on-stack packet
payload buffers in firewire-core (payload of lock requests in the bus
manager work and in iso resource management) to slab-allocated memory.

There are a number on-stack buffers for quadlet write or quadlet read
requests in firewire-core and firewire-sbp2.  These are harmless; they
are copied to/ from card driver internal DMA buffers since quadlet
payloads are inlined with packet headers.

Signed-off-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
---
 drivers/firewire/core-card.c | 14 +++++++-------
 drivers/firewire/core-cdev.c |  4 +++-
 drivers/firewire/core-iso.c  | 24 +++++++++++++-----------
 drivers/firewire/core.h      |  3 ++-
 include/linux/firewire.h     |  1 +
 5 files changed, 26 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c
index 543fccac81bb..f74edae5cb4c 100644
--- a/drivers/firewire/core-card.c
+++ b/drivers/firewire/core-card.c
@@ -196,8 +196,8 @@ static void allocate_broadcast_channel(struct fw_card *card, int generation)
 {
 	int channel, bandwidth = 0;
 
-	fw_iso_resource_manage(card, generation, 1ULL << 31,
-			       &channel, &bandwidth, true);
+	fw_iso_resource_manage(card, generation, 1ULL << 31, &channel,
+			       &bandwidth, true, card->bm_transaction_data);
 	if (channel == 31) {
 		card->broadcast_channel_allocated = true;
 		device_for_each_child(card->device, (void *)(long)generation,
@@ -230,7 +230,6 @@ static void fw_card_bm_work(struct work_struct *work)
 	bool do_reset = false;
 	bool root_device_is_running;
 	bool root_device_is_cmc;
-	__be32 lock_data[2];
 
 	spin_lock_irqsave(&card->lock, flags);
 
@@ -273,22 +272,23 @@ static void fw_card_bm_work(struct work_struct *work)
 			goto pick_me;
 		}
 
-		lock_data[0] = cpu_to_be32(0x3f);
-		lock_data[1] = cpu_to_be32(local_id);
+		card->bm_transaction_data[0] = cpu_to_be32(0x3f);
+		card->bm_transaction_data[1] = cpu_to_be32(local_id);
 
 		spin_unlock_irqrestore(&card->lock, flags);
 
 		rcode = fw_run_transaction(card, TCODE_LOCK_COMPARE_SWAP,
 				irm_id, generation, SCODE_100,
 				CSR_REGISTER_BASE + CSR_BUS_MANAGER_ID,
-				lock_data, sizeof(lock_data));
+				card->bm_transaction_data,
+				sizeof(card->bm_transaction_data));
 
 		if (rcode == RCODE_GENERATION)
 			/* Another bus reset, BM work has been rescheduled. */
 			goto out;
 
 		if (rcode == RCODE_COMPLETE &&
-		    lock_data[0] != cpu_to_be32(0x3f)) {
+		    card->bm_transaction_data[0] != cpu_to_be32(0x3f)) {
 
 			/* Somebody else is BM.  Only act as IRM. */
 			if (local_id == irm_id)
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index d1d30c615b0f..ced186d7e9a9 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -125,6 +125,7 @@ struct iso_resource {
 	int generation;
 	u64 channels;
 	s32 bandwidth;
+	__be32 transaction_data[2];
 	struct iso_resource_event *e_alloc, *e_dealloc;
 };
 
@@ -1049,7 +1050,8 @@ static void iso_resource_work(struct work_struct *work)
 			r->channels, &channel, &bandwidth,
 			todo == ISO_RES_ALLOC ||
 			todo == ISO_RES_REALLOC ||
-			todo == ISO_RES_ALLOC_ONCE);
+			todo == ISO_RES_ALLOC_ONCE,
+			r->transaction_data);
 	/*
 	 * Is this generation outdated already?  As long as this resource sticks
 	 * in the idr, it will be scheduled again for a newer generation or at
diff --git a/drivers/firewire/core-iso.c b/drivers/firewire/core-iso.c
index 166f19c6d38d..110e731f5574 100644
--- a/drivers/firewire/core-iso.c
+++ b/drivers/firewire/core-iso.c
@@ -177,9 +177,8 @@ EXPORT_SYMBOL(fw_iso_context_stop);
  */
 
 static int manage_bandwidth(struct fw_card *card, int irm_id, int generation,
-			    int bandwidth, bool allocate)
+			    int bandwidth, bool allocate, __be32 data[2])
 {
-	__be32 data[2];
 	int try, new, old = allocate ? BANDWIDTH_AVAILABLE_INITIAL : 0;
 
 	/*
@@ -215,9 +214,9 @@ static int manage_bandwidth(struct fw_card *card, int irm_id, int generation,
 }
 
 static int manage_channel(struct fw_card *card, int irm_id, int generation,
-			  u32 channels_mask, u64 offset, bool allocate)
+		u32 channels_mask, u64 offset, bool allocate, __be32 data[2])
 {
-	__be32 data[2], c, all, old;
+	__be32 c, all, old;
 	int i, retry = 5;
 
 	old = all = allocate ? cpu_to_be32(~0) : 0;
@@ -260,7 +259,7 @@ static int manage_channel(struct fw_card *card, int irm_id, int generation,
 }
 
 static void deallocate_channel(struct fw_card *card, int irm_id,
-			       int generation, int channel)
+			       int generation, int channel, __be32 buffer[2])
 {
 	u32 mask;
 	u64 offset;
@@ -269,7 +268,7 @@ static void deallocate_channel(struct fw_card *card, int irm_id,
 	offset = channel < 32 ? CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_HI :
 				CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_LO;
 
-	manage_channel(card, irm_id, generation, mask, offset, false);
+	manage_channel(card, irm_id, generation, mask, offset, false, buffer);
 }
 
 /**
@@ -298,7 +297,7 @@ static void deallocate_channel(struct fw_card *card, int irm_id,
  */
 void fw_iso_resource_manage(struct fw_card *card, int generation,
 			    u64 channels_mask, int *channel, int *bandwidth,
-			    bool allocate)
+			    bool allocate, __be32 buffer[2])
 {
 	u32 channels_hi = channels_mask;	/* channels 31...0 */
 	u32 channels_lo = channels_mask >> 32;	/* channels 63...32 */
@@ -310,10 +309,12 @@ void fw_iso_resource_manage(struct fw_card *card, int generation,
 
 	if (channels_hi)
 		c = manage_channel(card, irm_id, generation, channels_hi,
-		    CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_HI, allocate);
+				CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_HI,
+				allocate, buffer);
 	if (channels_lo && c < 0) {
 		c = manage_channel(card, irm_id, generation, channels_lo,
-		    CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_LO, allocate);
+				CSR_REGISTER_BASE + CSR_CHANNELS_AVAILABLE_LO,
+				allocate, buffer);
 		if (c >= 0)
 			c += 32;
 	}
@@ -325,12 +326,13 @@ void fw_iso_resource_manage(struct fw_card *card, int generation,
 	if (*bandwidth == 0)
 		return;
 
-	ret = manage_bandwidth(card, irm_id, generation, *bandwidth, allocate);
+	ret = manage_bandwidth(card, irm_id, generation, *bandwidth,
+			       allocate, buffer);
 	if (ret < 0)
 		*bandwidth = 0;
 
 	if (allocate && ret < 0 && c >= 0) {
-		deallocate_channel(card, irm_id, generation, c);
+		deallocate_channel(card, irm_id, generation, c, buffer);
 		*channel = ret;
 	}
 }
diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h
index c3cfc647e5e3..6052816be353 100644
--- a/drivers/firewire/core.h
+++ b/drivers/firewire/core.h
@@ -120,7 +120,8 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event);
 
 int fw_iso_buffer_map(struct fw_iso_buffer *buffer, struct vm_area_struct *vma);
 void fw_iso_resource_manage(struct fw_card *card, int generation,
-		u64 channels_mask, int *channel, int *bandwidth, bool allocate);
+			    u64 channels_mask, int *channel, int *bandwidth,
+			    bool allocate, __be32 buffer[2]);
 
 
 /* -topology */
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 9823946adbc5..192d1e43c43c 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -127,6 +127,7 @@ struct fw_card {
 	struct delayed_work work;
 	int bm_retries;
 	int bm_generation;
+	__be32 bm_transaction_data[2];
 
 	bool broadcast_channel_allocated;
 	u32 broadcast_channel;
-- 
cgit v1.2.3


From 9d73777e500929b71dcfed16eec05f6760e345a6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 25 Jun 2009 11:58:55 +0200
Subject: clarify get_user_pages() prototype

Currently the 4th parameter of get_user_pages() is called len, but its
in pages, not bytes. Rename the thing to nr_pages to avoid future
confusion.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  2 +-
 mm/memory.c        | 26 ++++++++++++--------------
 mm/nommu.c         | 12 +++++-------
 3 files changed, 18 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index d006e93d5c93..ba3a7cb1eaa0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -826,7 +826,7 @@ extern int make_pages_present(unsigned long addr, unsigned long end);
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
 
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-			unsigned long start, int len, int write, int force,
+			unsigned long start, int nr_pages, int write, int force,
 			struct page **pages, struct vm_area_struct **vmas);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
diff --git a/mm/memory.c b/mm/memory.c
index f46ac18ba231..65216194eb8d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1207,8 +1207,8 @@ static inline int use_zero_page(struct vm_area_struct *vma)
 
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long start, int len, int flags,
-		struct page **pages, struct vm_area_struct **vmas)
+		     unsigned long start, int nr_pages, int flags,
+		     struct page **pages, struct vm_area_struct **vmas)
 {
 	int i;
 	unsigned int vm_flags = 0;
@@ -1217,7 +1217,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
 	int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL);
 
-	if (len <= 0)
+	if (nr_pages <= 0)
 		return 0;
 	/* 
 	 * Require read or write permissions.
@@ -1269,7 +1269,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				vmas[i] = gate_vma;
 			i++;
 			start += PAGE_SIZE;
-			len--;
+			nr_pages--;
 			continue;
 		}
 
@@ -1280,7 +1280,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 		if (is_vm_hugetlb_page(vma)) {
 			i = follow_hugetlb_page(mm, vma, pages, vmas,
-						&start, &len, i, write);
+						&start, &nr_pages, i, write);
 			continue;
 		}
 
@@ -1357,9 +1357,9 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				vmas[i] = vma;
 			i++;
 			start += PAGE_SIZE;
-			len--;
-		} while (len && start < vma->vm_end);
-	} while (len);
+			nr_pages--;
+		} while (nr_pages && start < vma->vm_end);
+	} while (nr_pages);
 	return i;
 }
 
@@ -1368,7 +1368,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
  * @tsk:	task_struct of target task
  * @mm:		mm_struct of target mm
  * @start:	starting user address
- * @len:	number of pages from start to pin
+ * @nr_pages:	number of pages from start to pin
  * @write:	whether pages will be written to by the caller
  * @force:	whether to force write access even if user mapping is
  *		readonly. This will result in the page being COWed even
@@ -1380,7 +1380,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
  *		Or NULL if the caller does not require them.
  *
  * Returns number of pages pinned. This may be fewer than the number
- * requested. If len is 0 or negative, returns 0. If no pages
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
  * were pinned, returns -errno. Each page returned must be released
  * with a put_page() call when it is finished with. vmas will only
  * remain valid while mmap_sem is held.
@@ -1414,7 +1414,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
  * See also get_user_pages_fast, for performance critical applications.
  */
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, int len, int write, int force,
+		unsigned long start, int nr_pages, int write, int force,
 		struct page **pages, struct vm_area_struct **vmas)
 {
 	int flags = 0;
@@ -1424,9 +1424,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (force)
 		flags |= GUP_FLAGS_FORCE;
 
-	return __get_user_pages(tsk, mm,
-				start, len, flags,
-				pages, vmas);
+	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
 }
 
 EXPORT_SYMBOL(get_user_pages);
diff --git a/mm/nommu.c b/mm/nommu.c
index 2fd2ad5da98e..bf0cc762a7d2 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -173,8 +173,8 @@ unsigned int kobjsize(const void *objp)
 }
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		     unsigned long start, int len, int flags,
-		struct page **pages, struct vm_area_struct **vmas)
+		     unsigned long start, int nr_pages, int flags,
+		     struct page **pages, struct vm_area_struct **vmas)
 {
 	struct vm_area_struct *vma;
 	unsigned long vm_flags;
@@ -189,7 +189,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	vm_flags  = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
 	vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
 
-	for (i = 0; i < len; i++) {
+	for (i = 0; i < nr_pages; i++) {
 		vma = find_vma(mm, start);
 		if (!vma)
 			goto finish_or_fault;
@@ -224,7 +224,7 @@ finish_or_fault:
  * - don't permit access to VMAs that don't support it, such as I/O mappings
  */
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-	unsigned long start, int len, int write, int force,
+	unsigned long start, int nr_pages, int write, int force,
 	struct page **pages, struct vm_area_struct **vmas)
 {
 	int flags = 0;
@@ -234,9 +234,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (force)
 		flags |= GUP_FLAGS_FORCE;
 
-	return __get_user_pages(tsk, mm,
-				start, len, flags,
-				pages, vmas);
+	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
 }
 EXPORT_SYMBOL(get_user_pages);
 
-- 
cgit v1.2.3


From 41f95331b972a039f519ae0c70f051b7121f7346 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Tue, 23 Jun 2009 17:55:18 +0200
Subject: perf_counter: Split the mmap control page in two parts

Since there are two distinct sections to the control page,
move them apart so that possible extentions don't overlap.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/perf_counter.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index e7213e46cf9c..489d5cbfbcca 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -233,6 +233,12 @@ struct perf_counter_mmap_page {
 	__u32	index;			/* hardware counter identifier */
 	__s64	offset;			/* add to hardware counter value */
 
+		/*
+		 * Hole for extension of the self monitor capabilities
+		 */
+
+	__u64	__reserved[125];	/* align to 1k */
+
 	/*
 	 * Control data for the mmap() data buffer.
 	 *
-- 
cgit v1.2.3


From 7f8b4e4e0988dadfd22330fd147ad2453e19f510 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Mon, 22 Jun 2009 14:34:35 +0200
Subject: perf_counter: Add scale information to the mmap control page

Add the needed time scale to the self-profile mmap information.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/perf_counter.h | 4 +++-
 kernel/perf_counter.c        | 6 ++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 489d5cbfbcca..bcbf1c43ed42 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -232,12 +232,14 @@ struct perf_counter_mmap_page {
 	__u32	lock;			/* seqlock for synchronization */
 	__u32	index;			/* hardware counter identifier */
 	__s64	offset;			/* add to hardware counter value */
+	__u64	time_enabled;		/* time counter active */
+	__u64	time_running;		/* time counter on cpu */
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u64	__reserved[125];	/* align to 1k */
+	__u64	__reserved[123];	/* align to 1k */
 
 	/*
 	 * Control data for the mmap() data buffer.
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index c2b19c111718..23614adab475 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -1782,6 +1782,12 @@ void perf_counter_update_userpage(struct perf_counter *counter)
 	if (counter->state == PERF_COUNTER_STATE_ACTIVE)
 		userpg->offset -= atomic64_read(&counter->hw.prev_count);
 
+	userpg->time_enabled = counter->total_time_enabled +
+			atomic64_read(&counter->child_total_time_enabled);
+
+	userpg->time_running = counter->total_time_running +
+			atomic64_read(&counter->child_total_time_running);
+
 	barrier();
 	++userpg->lock;
 	preempt_enable();
-- 
cgit v1.2.3


From 38b200d67636a30cb8dc1508137908e7a649b5c9 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Tue, 23 Jun 2009 20:13:11 +0200
Subject: perf_counter: Add PERF_EVENT_READ

Provide a read() like event which can be used to log the
counter value at specific sites such as child->parent
folding on exit.

In order to be useful, we log the counter parent ID, not the
actual counter ID, since userspace can only relate parent
IDs to perf_counter_attr constructs.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/perf_counter.h | 12 ++++++++
 kernel/perf_counter.c        | 72 +++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 80 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index bcbf1c43ed42..6a384f04755a 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -334,6 +334,18 @@ enum perf_event_type {
 	 */
 	PERF_EVENT_FORK			= 7,
 
+	/*
+	 * struct {
+	 * 	struct perf_event_header	header;
+	 * 	u32				pid, tid;
+	 * 	u64				value;
+	 * 	{ u64		time_enabled; 	} && PERF_FORMAT_ENABLED
+	 * 	{ u64		time_running; 	} && PERF_FORMAT_RUNNING
+	 * 	{ u64		parent_id;	} && PERF_FORMAT_ID
+	 * };
+	 */
+	PERF_EVENT_READ			= 8,
+
 	/*
 	 * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field
 	 * will be PERF_SAMPLE_*
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 02994a719e27..a72c20e91953 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -2623,6 +2623,66 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 	perf_output_end(&handle);
 }
 
+/*
+ * read event
+ */
+
+struct perf_read_event {
+	struct perf_event_header	header;
+
+	u32				pid;
+	u32				tid;
+	u64				value;
+	u64				format[3];
+};
+
+static void
+perf_counter_read_event(struct perf_counter *counter,
+			struct task_struct *task)
+{
+	struct perf_output_handle handle;
+	struct perf_read_event event = {
+		.header = {
+			.type = PERF_EVENT_READ,
+			.misc = 0,
+			.size = sizeof(event) - sizeof(event.format),
+		},
+		.pid = perf_counter_pid(counter, task),
+		.tid = perf_counter_tid(counter, task),
+		.value = atomic64_read(&counter->count),
+	};
+	int ret, i = 0;
+
+	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
+		event.header.size += sizeof(u64);
+		event.format[i++] = counter->total_time_enabled;
+	}
+
+	if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
+		event.header.size += sizeof(u64);
+		event.format[i++] = counter->total_time_running;
+	}
+
+	if (counter->attr.read_format & PERF_FORMAT_ID) {
+		u64 id;
+
+		event.header.size += sizeof(u64);
+		if (counter->parent)
+			id = counter->parent->id;
+		else
+			id = counter->id;
+
+		event.format[i++] = id;
+	}
+
+	ret = perf_output_begin(&handle, counter, event.header.size, 0, 0);
+	if (ret)
+		return;
+
+	perf_output_copy(&handle, &event, event.header.size);
+	perf_output_end(&handle);
+}
+
 /*
  * fork tracking
  */
@@ -3985,10 +4045,13 @@ static int inherit_group(struct perf_counter *parent_counter,
 }
 
 static void sync_child_counter(struct perf_counter *child_counter,
-			       struct perf_counter *parent_counter)
+			       struct task_struct *child)
 {
+	struct perf_counter *parent_counter = child_counter->parent;
 	u64 child_val;
 
+	perf_counter_read_event(child_counter, child);
+
 	child_val = atomic64_read(&child_counter->count);
 
 	/*
@@ -4017,7 +4080,8 @@ static void sync_child_counter(struct perf_counter *child_counter,
 
 static void
 __perf_counter_exit_task(struct perf_counter *child_counter,
-			 struct perf_counter_context *child_ctx)
+			 struct perf_counter_context *child_ctx,
+			 struct task_struct *child)
 {
 	struct perf_counter *parent_counter;
 
@@ -4031,7 +4095,7 @@ __perf_counter_exit_task(struct perf_counter *child_counter,
 	 * counters need to be zapped - but otherwise linger.
 	 */
 	if (parent_counter) {
-		sync_child_counter(child_counter, parent_counter);
+		sync_child_counter(child_counter, child);
 		free_counter(child_counter);
 	}
 }
@@ -4093,7 +4157,7 @@ void perf_counter_exit_task(struct task_struct *child)
 again:
 	list_for_each_entry_safe(child_counter, tmp, &child_ctx->counter_list,
 				 list_entry)
-		__perf_counter_exit_task(child_counter, child_ctx);
+		__perf_counter_exit_task(child_counter, child_ctx, child);
 
 	/*
 	 * If the last counter was a group counter, it will have appended all
-- 
cgit v1.2.3


From bfbd3381e63aa2a14c6706afb50ce4630aa0d9a2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 24 Jun 2009 21:11:59 +0200
Subject: perf_counter: Implement more accurate per task statistics

With the introduction of PERF_EVENT_READ we have the
possibility to provide accurate counter values for
individual tasks in a task hierarchy.

However, due to the lazy context switching used for similar
counter contexts our current per task counts are way off.

In order to maintain some of the lazy switch benefits we
don't disable it out-right, but simply iterate the active
counters and flip the values between the contexts.

This only reads the counters but does not need to reprogram
the full PMU.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/perf_counter.h |  4 ++-
 kernel/perf_counter.c        | 83 ++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 83 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 6a384f04755a..de70a10b5ec8 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -178,8 +178,9 @@ struct perf_counter_attr {
 				mmap           :  1, /* include mmap data     */
 				comm	       :  1, /* include comm data     */
 				freq           :  1, /* use freq, not period  */
+				inherit_stat   :  1, /* per task counts       */
 
-				__reserved_1   : 53;
+				__reserved_1   : 52;
 
 	__u32			wakeup_events;	/* wakeup every n events */
 	__u32			__reserved_2;
@@ -602,6 +603,7 @@ struct perf_counter_context {
 	int				nr_counters;
 	int				nr_active;
 	int				is_active;
+	int				nr_stat;
 	atomic_t			refcount;
 	struct task_struct		*task;
 
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index a72c20e91953..385ca51c6e60 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -236,6 +236,8 @@ list_add_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
 
 	list_add_rcu(&counter->event_entry, &ctx->event_list);
 	ctx->nr_counters++;
+	if (counter->attr.inherit_stat)
+		ctx->nr_stat++;
 }
 
 /*
@@ -250,6 +252,8 @@ list_del_counter(struct perf_counter *counter, struct perf_counter_context *ctx)
 	if (list_empty(&counter->list_entry))
 		return;
 	ctx->nr_counters--;
+	if (counter->attr.inherit_stat)
+		ctx->nr_stat--;
 
 	list_del_init(&counter->list_entry);
 	list_del_rcu(&counter->event_entry);
@@ -1006,6 +1010,76 @@ static int context_equiv(struct perf_counter_context *ctx1,
 		&& !ctx1->pin_count && !ctx2->pin_count;
 }
 
+static void __perf_counter_read(void *counter);
+
+static void __perf_counter_sync_stat(struct perf_counter *counter,
+				     struct perf_counter *next_counter)
+{
+	u64 value;
+
+	if (!counter->attr.inherit_stat)
+		return;
+
+	/*
+	 * Update the counter value, we cannot use perf_counter_read()
+	 * because we're in the middle of a context switch and have IRQs
+	 * disabled, which upsets smp_call_function_single(), however
+	 * we know the counter must be on the current CPU, therefore we
+	 * don't need to use it.
+	 */
+	switch (counter->state) {
+	case PERF_COUNTER_STATE_ACTIVE:
+		__perf_counter_read(counter);
+		break;
+
+	case PERF_COUNTER_STATE_INACTIVE:
+		update_counter_times(counter);
+		break;
+
+	default:
+		break;
+	}
+
+	/*
+	 * In order to keep per-task stats reliable we need to flip the counter
+	 * values when we flip the contexts.
+	 */
+	value = atomic64_read(&next_counter->count);
+	value = atomic64_xchg(&counter->count, value);
+	atomic64_set(&next_counter->count, value);
+
+	/*
+	 * XXX also sync time_enabled and time_running ?
+	 */
+}
+
+#define list_next_entry(pos, member) \
+	list_entry(pos->member.next, typeof(*pos), member)
+
+static void perf_counter_sync_stat(struct perf_counter_context *ctx,
+				   struct perf_counter_context *next_ctx)
+{
+	struct perf_counter *counter, *next_counter;
+
+	if (!ctx->nr_stat)
+		return;
+
+	counter = list_first_entry(&ctx->event_list,
+				   struct perf_counter, event_entry);
+
+	next_counter = list_first_entry(&next_ctx->event_list,
+					struct perf_counter, event_entry);
+
+	while (&counter->event_entry != &ctx->event_list &&
+	       &next_counter->event_entry != &next_ctx->event_list) {
+
+		__perf_counter_sync_stat(counter, next_counter);
+
+		counter = list_next_entry(counter, event_entry);
+		next_counter = list_next_entry(counter, event_entry);
+	}
+}
+
 /*
  * Called from scheduler to remove the counters of the current task,
  * with interrupts disabled.
@@ -1061,6 +1135,8 @@ void perf_counter_task_sched_out(struct task_struct *task,
 			ctx->task = next;
 			next_ctx->task = task;
 			do_switch = 0;
+
+			perf_counter_sync_stat(ctx, next_ctx);
 		}
 		spin_unlock(&next_ctx->lock);
 		spin_unlock(&ctx->lock);
@@ -1350,7 +1426,7 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu)
 /*
  * Cross CPU call to read the hardware counter
  */
-static void __read(void *info)
+static void __perf_counter_read(void *info)
 {
 	struct perf_counter *counter = info;
 	struct perf_counter_context *ctx = counter->ctx;
@@ -1372,7 +1448,7 @@ static u64 perf_counter_read(struct perf_counter *counter)
 	 */
 	if (counter->state == PERF_COUNTER_STATE_ACTIVE) {
 		smp_call_function_single(counter->oncpu,
-					 __read, counter, 1);
+					 __perf_counter_read, counter, 1);
 	} else if (counter->state == PERF_COUNTER_STATE_INACTIVE) {
 		update_counter_times(counter);
 	}
@@ -4050,7 +4126,8 @@ static void sync_child_counter(struct perf_counter *child_counter,
 	struct perf_counter *parent_counter = child_counter->parent;
 	u64 child_val;
 
-	perf_counter_read_event(child_counter, child);
+	if (child_counter->attr.inherit_stat)
+		perf_counter_read_event(child_counter, child);
 
 	child_val = atomic64_read(&child_counter->count);
 
-- 
cgit v1.2.3


From e6e18ec79b023d5fe84226cef533cf0e3770ce93 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Thu, 25 Jun 2009 11:27:12 +0200
Subject: perf_counter: Rework the sample ABI

The PERF_EVENT_READ implementation made me realize we don't
actually need the sample_type int the output sample, since
we already have that in the perf_counter_attr information.

Therefore, remove the PERF_EVENT_MISC_OVERFLOW bit and the
event->type overloading, and imply put counter overflow
samples in a PERF_EVENT_SAMPLE type.

This also fixes the issue that event->type was only 32-bit
and sample_type had 64 usable bits.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/perf_counter.h  | 10 +++++-----
 kernel/perf_counter.c         | 36 +++++++++++++++---------------------
 tools/perf/builtin-annotate.c |  8 ++++----
 tools/perf/builtin-report.c   | 32 +++++++++++++++++++-------------
 tools/perf/builtin-top.c      | 11 ++++++-----
 5 files changed, 49 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index de70a10b5ec8..3078e23c91eb 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -262,7 +262,6 @@ struct perf_counter_mmap_page {
 #define PERF_EVENT_MISC_KERNEL			(1 << 0)
 #define PERF_EVENT_MISC_USER			(2 << 0)
 #define PERF_EVENT_MISC_HYPERVISOR		(3 << 0)
-#define PERF_EVENT_MISC_OVERFLOW		(1 << 2)
 
 struct perf_event_header {
 	__u32	type;
@@ -348,9 +347,6 @@ enum perf_event_type {
 	PERF_EVENT_READ			= 8,
 
 	/*
-	 * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field
-	 * will be PERF_SAMPLE_*
-	 *
 	 * struct {
 	 *	struct perf_event_header	header;
 	 *
@@ -358,8 +354,9 @@ enum perf_event_type {
 	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
 	 *	{ u64			time;     } && PERF_SAMPLE_TIME
 	 *	{ u64			addr;     } && PERF_SAMPLE_ADDR
-	 *	{ u64			config;   } && PERF_SAMPLE_CONFIG
+	 *	{ u64			id;	  } && PERF_SAMPLE_ID
 	 *	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 * 	{ u64			period;   } && PERF_SAMPLE_PERIOD
 	 *
 	 *	{ u64			nr;
 	 *	  { u64 id, val; }	cnt[nr];  } && PERF_SAMPLE_GROUP
@@ -368,6 +365,9 @@ enum perf_event_type {
 	 *	  u64			ips[nr];  } && PERF_SAMPLE_CALLCHAIN
 	 * };
 	 */
+	PERF_EVENT_SAMPLE		= 9,
+
+	PERF_EVENT_MAX,			/* non-ABI */
 };
 
 enum perf_callchain_context {
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 385ca51c6e60..f2f232696587 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -2575,15 +2575,14 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		u32 cpu, reserved;
 	} cpu_entry;
 
-	header.type = 0;
+	header.type = PERF_EVENT_SAMPLE;
 	header.size = sizeof(header);
 
-	header.misc = PERF_EVENT_MISC_OVERFLOW;
+	header.misc = 0;
 	header.misc |= perf_misc_flags(data->regs);
 
 	if (sample_type & PERF_SAMPLE_IP) {
 		ip = perf_instruction_pointer(data->regs);
-		header.type |= PERF_SAMPLE_IP;
 		header.size += sizeof(ip);
 	}
 
@@ -2592,7 +2591,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		tid_entry.pid = perf_counter_pid(counter, current);
 		tid_entry.tid = perf_counter_tid(counter, current);
 
-		header.type |= PERF_SAMPLE_TID;
 		header.size += sizeof(tid_entry);
 	}
 
@@ -2602,34 +2600,25 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		 */
 		time = sched_clock();
 
-		header.type |= PERF_SAMPLE_TIME;
 		header.size += sizeof(u64);
 	}
 
-	if (sample_type & PERF_SAMPLE_ADDR) {
-		header.type |= PERF_SAMPLE_ADDR;
+	if (sample_type & PERF_SAMPLE_ADDR)
 		header.size += sizeof(u64);
-	}
 
-	if (sample_type & PERF_SAMPLE_ID) {
-		header.type |= PERF_SAMPLE_ID;
+	if (sample_type & PERF_SAMPLE_ID)
 		header.size += sizeof(u64);
-	}
 
 	if (sample_type & PERF_SAMPLE_CPU) {
-		header.type |= PERF_SAMPLE_CPU;
 		header.size += sizeof(cpu_entry);
 
 		cpu_entry.cpu = raw_smp_processor_id();
 	}
 
-	if (sample_type & PERF_SAMPLE_PERIOD) {
-		header.type |= PERF_SAMPLE_PERIOD;
+	if (sample_type & PERF_SAMPLE_PERIOD)
 		header.size += sizeof(u64);
-	}
 
 	if (sample_type & PERF_SAMPLE_GROUP) {
-		header.type |= PERF_SAMPLE_GROUP;
 		header.size += sizeof(u64) +
 			counter->nr_siblings * sizeof(group_entry);
 	}
@@ -2639,10 +2628,9 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 
 		if (callchain) {
 			callchain_size = (1 + callchain->nr) * sizeof(u64);
-
-			header.type |= PERF_SAMPLE_CALLCHAIN;
 			header.size += callchain_size;
-		}
+		} else
+			header.size += sizeof(u64);
 	}
 
 	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
@@ -2693,8 +2681,14 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		}
 	}
 
-	if (callchain)
-		perf_output_copy(&handle, callchain, callchain_size);
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
+		if (callchain)
+			perf_output_copy(&handle, callchain, callchain_size);
+		else {
+			u64 nr = 0;
+			perf_output_put(&handle, nr);
+		}
+	}
 
 	perf_output_end(&handle);
 }
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 7e58e3ad1508..722c0f54e549 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -855,7 +855,7 @@ static unsigned long total = 0,
 		     total_unknown = 0;
 
 static int
-process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
+process_sample_event(event_t *event, unsigned long offset, unsigned long head)
 {
 	char level;
 	int show = 0;
@@ -1013,10 +1013,10 @@ process_period_event(event_t *event, unsigned long offset, unsigned long head)
 static int
 process_event(event_t *event, unsigned long offset, unsigned long head)
 {
-	if (event->header.misc & PERF_EVENT_MISC_OVERFLOW)
-		return process_overflow_event(event, offset, head);
-
 	switch (event->header.type) {
+	case PERF_EVENT_SAMPLE:
+		return process_sample_event(event, offset, head);
+
 	case PERF_EVENT_MMAP:
 		return process_mmap_event(event, offset, head);
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index e575f3039766..ec5361c67bf5 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -53,6 +53,8 @@ static regex_t		parent_regex;
 
 static int		exclude_other = 1;
 
+static u64		sample_type;
+
 struct ip_event {
 	struct perf_event_header header;
 	u64 ip;
@@ -1135,7 +1137,7 @@ static int validate_chain(struct ip_callchain *chain, event_t *event)
 }
 
 static int
-process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
+process_sample_event(event_t *event, unsigned long offset, unsigned long head)
 {
 	char level;
 	int show = 0;
@@ -1147,12 +1149,12 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
 	void *more_data = event->ip.__more_data;
 	struct ip_callchain *chain = NULL;
 
-	if (event->header.type & PERF_SAMPLE_PERIOD) {
+	if (sample_type & PERF_SAMPLE_PERIOD) {
 		period = *(u64 *)more_data;
 		more_data += sizeof(u64);
 	}
 
-	dprintf("%p [%p]: PERF_EVENT (IP, %d): %d: %p period: %Ld\n",
+	dprintf("%p [%p]: PERF_EVENT_SAMPLE (IP, %d): %d: %p period: %Ld\n",
 		(void *)(offset + head),
 		(void *)(long)(event->header.size),
 		event->header.misc,
@@ -1160,7 +1162,7 @@ process_overflow_event(event_t *event, unsigned long offset, unsigned long head)
 		(void *)(long)ip,
 		(long long)period);
 
-	if (event->header.type & PERF_SAMPLE_CALLCHAIN) {
+	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
 		int i;
 
 		chain = (void *)more_data;
@@ -1352,10 +1354,10 @@ process_event(event_t *event, unsigned long offset, unsigned long head)
 {
 	trace_event(event);
 
-	if (event->header.misc & PERF_EVENT_MISC_OVERFLOW)
-		return process_overflow_event(event, offset, head);
-
 	switch (event->header.type) {
+	case PERF_EVENT_SAMPLE:
+		return process_sample_event(event, offset, head);
+
 	case PERF_EVENT_MMAP:
 		return process_mmap_event(event, offset, head);
 
@@ -1388,18 +1390,21 @@ process_event(event_t *event, unsigned long offset, unsigned long head)
 
 static struct perf_header	*header;
 
-static int perf_header__has_sample(u64 sample_mask)
+static u64 perf_header__sample_type(void)
 {
+	u64 sample_type = 0;
 	int i;
 
 	for (i = 0; i < header->attrs; i++) {
 		struct perf_header_attr *attr = header->attr[i];
 
-		if (!(attr->attr.sample_type & sample_mask))
-			return 0;
+		if (!sample_type)
+			sample_type = attr->attr.sample_type;
+		else if (sample_type != attr->attr.sample_type)
+			die("non matching sample_type");
 	}
 
-	return 1;
+	return sample_type;
 }
 
 static int __cmd_report(void)
@@ -1437,8 +1442,9 @@ static int __cmd_report(void)
 	header = perf_header__read(input);
 	head = header->data_offset;
 
-	if (sort__has_parent &&
-	    !perf_header__has_sample(PERF_SAMPLE_CALLCHAIN)) {
+	sample_type = perf_header__sample_type();
+
+	if (sort__has_parent && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		fprintf(stderr, "selected --sort parent, but no callchain data\n");
 		exit(-1);
 	}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5352b5e352ed..cf0d21f1ae10 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -392,11 +392,11 @@ static void record_ip(u64 ip, int counter)
 	samples--;
 }
 
-static void process_event(u64 ip, int counter)
+static void process_event(u64 ip, int counter, int user)
 {
 	samples++;
 
-	if (ip < min_ip || ip > max_ip) {
+	if (user) {
 		userspace_samples++;
 		return;
 	}
@@ -509,9 +509,10 @@ static void mmap_read_counter(struct mmap_data *md)
 
 		old += size;
 
-		if (event->header.misc & PERF_EVENT_MISC_OVERFLOW) {
-			if (event->header.type & PERF_SAMPLE_IP)
-				process_event(event->ip.ip, md->counter);
+		if (event->header.type == PERF_EVENT_SAMPLE) {
+			int user =
+	(event->header.misc & PERF_EVENT_MISC_CPUMODE_MASK) == PERF_EVENT_MISC_USER;
+			process_event(event->ip.ip, md->counter, user);
 		}
 	}
 
-- 
cgit v1.2.3


From 5211a242d0cbdded372aee59da18f80552b0a80a Mon Sep 17 00:00:00 2001
From: Kurt Garloff <garloff@suse.de>
Date: Wed, 24 Jun 2009 14:32:11 -0700
Subject: x86: Add sysctl to allow panic on IOCK NMI error

This patch introduces a new sysctl:

    /proc/sys/kernel/panic_on_io_nmi

which defaults to 0 (off).

When enabled, the kernel panics when the kernel receives an NMI
caused by an IO error.

The IO error triggered NMI indicates a serious system
condition, which could result in IO data corruption. Rather
than contiuing, panicing and dumping might be a better choice,
so one can figure out what's causing the IO error.

This could be especially important to companies running IO
intensive applications where corruption must be avoided, e.g. a
bank's databases.

[ SuSE has been shipping it for a while, it was done at the
  request of a large database vendor, for their users. ]

Signed-off-by: Kurt Garloff <garloff@suse.de>
Signed-off-by: Roberto Angelino <robertangelino@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
LKML-Reference: <20090624213211.GA11291@kroah.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/dumpstack.c | 1 +
 arch/x86/kernel/traps.c     | 3 +++
 include/linux/kernel.h      | 1 +
 kernel/sysctl.c             | 8 ++++++++
 4 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 95ea5fa7d444..c8405718a4c3 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -22,6 +22,7 @@
 #include "dumpstack.h"
 
 int panic_on_unrecovered_nmi;
+int panic_on_io_nmi;
 unsigned int code_bytes = 64;
 int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
 static int die_counter;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index a0f48f5671c0..5204332f475d 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -346,6 +346,9 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 	printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
 	show_registers(regs);
 
+	if (panic_on_io_nmi)
+		panic("NMI IOCK error: Not continuing");
+
 	/* Re-enable the IOCK line, wait for a few seconds */
 	reason = (reason & 0xf) | 8;
 	outb(reason, 0x61);
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index fac104e7186a..d6320a3e8def 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -303,6 +303,7 @@ extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in
 extern int panic_timeout;
 extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
+extern int panic_on_io_nmi;
 extern const char *print_tainted(void);
 extern void add_taint(unsigned flag);
 extern int test_taint(unsigned flag);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 62e4ff9968b5..fba42eda8de2 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -743,6 +743,14 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "panic_on_io_nmi",
+		.data		= &panic_on_io_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 	{
 		.ctl_name	= KERN_BOOTLOADER_TYPE,
 		.procname	= "bootloader_type",
-- 
cgit v1.2.3


From 5e955245d6cf49c5ed26c7add7392ff5a6762bf4 Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Tue, 23 Jun 2009 11:27:27 +0000
Subject: ide: always kill the whole request on error

* Use blk_rq_bytes() instead of obsolete ide_rq_bytes() in ide_kill_rq()
  and ide_floppy_do_request() for failed requests.
  [ bugfix part ]

* Use blk_rq_bytes() instead of obsolete ide_rq_bytes() in ide_do_devset()
  and ide_complete_drive_reset().  Then remove ide_rq_bytes().
  [ cleanup part ]

Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ide/ide-devsets.c |  2 +-
 drivers/ide/ide-eh.c      |  2 +-
 drivers/ide/ide-floppy.c  |  2 +-
 drivers/ide/ide-io.c      | 14 ++------------
 include/linux/ide.h       |  1 -
 5 files changed, 5 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index 5bf958e5b1d5..1099bf7cf968 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -183,6 +183,6 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq)
 	err = setfunc(drive, *(int *)&rq->cmd[1]);
 	if (err)
 		rq->errors = err;
-	ide_complete_rq(drive, err, ide_rq_bytes(rq));
+	ide_complete_rq(drive, err, blk_rq_bytes(rq));
 	return ide_stopped;
 }
diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c
index 2b9141979613..e9abf2c3c335 100644
--- a/drivers/ide/ide-eh.c
+++ b/drivers/ide/ide-eh.c
@@ -149,7 +149,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
 	if (rq && blk_special_request(rq) && rq->cmd[0] == REQ_DRIVE_RESET) {
 		if (err <= 0 && rq->errors == 0)
 			rq->errors = -EIO;
-		ide_complete_rq(drive, err ? err : 0, ide_rq_bytes(rq));
+		ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
 	}
 }
 
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 8b3f204f7d73..fefbdfc8db06 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -293,7 +293,7 @@ out_end:
 	drive->failed_pc = NULL;
 	if (blk_fs_request(rq) == 0 && rq->errors == 0)
 		rq->errors = -EIO;
-	ide_complete_rq(drive, -EIO, ide_rq_bytes(rq));
+	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
 	return ide_stopped;
 }
 
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 95db5f03f6a2..d5f3c77beadd 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -112,16 +112,6 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err)
 	}
 }
 
-/* obsolete, blk_rq_bytes() should be used instead */
-unsigned int ide_rq_bytes(struct request *rq)
-{
-	if (blk_pc_request(rq))
-		return blk_rq_bytes(rq);
-	else
-		return blk_rq_cur_sectors(rq) << 9;
-}
-EXPORT_SYMBOL_GPL(ide_rq_bytes);
-
 int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes)
 {
 	ide_hwif_t *hwif = drive->hwif;
@@ -152,14 +142,14 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 
 	if ((media == ide_floppy || media == ide_tape) && drv_req) {
 		rq->errors = 0;
-		ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
 	} else {
 		if (media == ide_tape)
 			rq->errors = IDE_DRV_ERROR_GENERAL;
 		else if (blk_fs_request(rq) == 0 && rq->errors == 0)
 			rq->errors = -EIO;
-		ide_complete_rq(drive, -EIO, ide_rq_bytes(rq));
 	}
+
+	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
 }
 
 static void ide_tf_set_specify_cmd(ide_drive_t *drive, struct ide_taskfile *tf)
diff --git a/include/linux/ide.h b/include/linux/ide.h
index cf1f3888067c..c6af7c44d46c 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1062,7 +1062,6 @@ int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned l
 extern int ide_vlb_clk;
 extern int ide_pci_clk;
 
-unsigned int ide_rq_bytes(struct request *);
 int ide_end_rq(ide_drive_t *, struct request *, int, unsigned int);
 void ide_kill_rq(ide_drive_t *, struct request *);
 
-- 
cgit v1.2.3


From 73f1d9391a6aa72efdcea2f302ee7bfcd313c631 Mon Sep 17 00:00:00 2001
From: Paul Mundt <lethal@linux-sh.org>
Date: Wed, 24 Jun 2009 01:04:36 +0900
Subject: asm-generic/vmlinux.lds.h: Fix up RW_DATA_SECTION definition.

RW_DATA_SECTION is defined to take 4 different alignment parameters,
while NOSAVE_DATA currently uses a fixed PAGE_SIZE alignment as noted
in the comments.

There are presently no in-tree users of this at present, and I just
stumbled across this while implementing the simplified script on a new
architecture port, which subsequently resulted in a syntax error.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
---
 include/asm-generic/vmlinux.lds.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 92b73b6140ff..f92e730695c8 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -704,7 +704,7 @@
  * matches the requirment of PAGE_ALIGNED_DATA.
  *
  * use 0 as page_align if page_aligned data is not used */
-#define RW_DATA_SECTION(cacheline, nosave, pagealigned, inittask)	\
+#define RW_DATA_SECTION(cacheline, pagealigned, inittask)		\
 	. = ALIGN(PAGE_SIZE);						\
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {				\
 		INIT_TASK(inittask)					\
@@ -712,7 +712,7 @@
 		READ_MOSTLY_DATA(cacheline)				\
 		DATA_DATA						\
 		CONSTRUCTORS						\
-		NOSAVE_DATA(nosave)					\
+		NOSAVE_DATA						\
 		PAGE_ALIGNED_DATA(pagealigned)				\
 	}
 
-- 
cgit v1.2.3


From d2af12aeadaedf657c9fb9c3df984d2c5ab25f4c Mon Sep 17 00:00:00 2001
From: Tim Abbott <tabbott@ksplice.com>
Date: Tue, 23 Jun 2009 19:59:35 -0400
Subject: Add new macros for page-aligned data and bss sections.

This patch is preparation for replacing most uses of
".bss.page_aligned" and ".data.page_aligned" in the kernel with
macros, so that the section name can later be changed without having
to touch a lot of the kernel.

The long-term goal here is to be able to change the kernel's magic
section names to those that are compatible with -ffunction-sections
-fdata-sections.  This requires renaming all magic sections with names
of the form ".data.foo".

Signed-off-by: Tim Abbott <tabbott@ksplice.com>
Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
---
 include/linux/linkage.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index fee9e59649c1..691f59171c6c 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -21,6 +21,15 @@
 #define __page_aligned_data	__section(.data.page_aligned) __aligned(PAGE_SIZE)
 #define __page_aligned_bss	__section(.bss.page_aligned) __aligned(PAGE_SIZE)
 
+/*
+ * For assembly routines.
+ *
+ * Note when using these that you must specify the appropriate
+ * alignment directives yourself
+ */
+#define __PAGE_ALIGNED_DATA	.section ".data.page_aligned", "aw"
+#define __PAGE_ALIGNED_BSS	.section ".bss.page_aligned", "aw"
+
 /*
  * This is used by architectures to keep arguments on the stack
  * untouched by the compiler by keeping them live until the end.
-- 
cgit v1.2.3


From 39a449d96ac3db9b6d498b6ffbf4c763746d5e8b Mon Sep 17 00:00:00 2001
From: Tim Abbott <tabbott@ksplice.com>
Date: Tue, 23 Jun 2009 18:53:15 -0400
Subject: asm-generic/vmlinux.lds.h: shuffle INIT_TASK* macro names in
 vmlinux.lds.h

We recently added a INIT_TASK(align) in include/asm-generic/vmlinux.lds.h,
but there is already a macro INIT_TASK in include/linux/init_task.h, which
is quite confusing.  We should switch the macro in the linker script to
INIT_TASK_DATA. (Sorry that I missed this in reviewing the patch).  Since
the macros are new, there is only one user of the INIT_TASK in
vmlinux.lds.h, arch/mn10300/kernel/vmlinux.lds.S.

However, we are currently using INIT_TASK_DATA for laying down an entire
.data.init_task section.  So rename that to INIT_TASK_DATA_SECTION.

I would be worried about changing the meaning of INIT_TASK_DATA, but the
old INIT_TASK_DATA implementation had no users, and in fact if anyone had
tried to use it, it would have failed to compile because it didn't pass
the alignment to the old INIT_TASK.

Signed-off-by: Tim Abbott <tabbott@ksplice.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jesper Nilsson <Jesper.Nilsson@axis.com
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
---
 arch/mn10300/kernel/vmlinux.lds.S | 2 +-
 include/asm-generic/vmlinux.lds.h | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S
index bcebcefb4ad7..c96ba3da95ac 100644
--- a/arch/mn10300/kernel/vmlinux.lds.S
+++ b/arch/mn10300/kernel/vmlinux.lds.S
@@ -61,7 +61,7 @@ SECTIONS
 	_edata = .;		/* End of data section */
   }
 
-  .data.init_task : { INIT_TASK(THREAD_SIZE); }
+  .data.init_task : { INIT_TASK_DATA(THREAD_SIZE); }
 
   /* might get freed after init */
   . = ALIGN(PAGE_SIZE);
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f92e730695c8..720af4c72206 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -191,7 +191,7 @@
 	. = ALIGN(align);						\
 	*(.data.cacheline_aligned)
 
-#define INIT_TASK(align)						\
+#define INIT_TASK_DATA(align)						\
 	. = ALIGN(align);						\
 	*(.data.init_task)
 
@@ -434,10 +434,10 @@
 /*
  * Init task
  */
-#define INIT_TASK_DATA(align)						\
+#define INIT_TASK_DATA_SECTION(align)					\
 	. = ALIGN(align);						\
 	.data.init_task : {						\
-		INIT_TASK						\
+		INIT_TASK_DATA(align)					\
 	}
 
 #ifdef CONFIG_CONSTRUCTORS
@@ -707,7 +707,7 @@
 #define RW_DATA_SECTION(cacheline, pagealigned, inittask)		\
 	. = ALIGN(PAGE_SIZE);						\
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {				\
-		INIT_TASK(inittask)					\
+		INIT_TASK_DATA(inittask)				\
 		CACHELINE_ALIGNED_DATA(cacheline)			\
 		READ_MOSTLY_DATA(cacheline)				\
 		DATA_DATA						\
-- 
cgit v1.2.3


From 857eceebd2803c9a3459f784acf45e5266921e4d Mon Sep 17 00:00:00 2001
From: Tim Abbott <tabbott@ksplice.com>
Date: Tue, 23 Jun 2009 19:59:36 -0400
Subject: Add new __init_task_data macro to be used in arch init_task.c files.

This patch is preparation for replacing most ".data.init_task" in the
kernel with macros, so that the section name can later be changed
without having to touch a lot of the kernel.

The long-term goal here is to be able to change the kernel's magic
section names to those that are compatible with -ffunction-sections
-fdata-sections.  This requires renaming all magic sections with names
of the form ".data.foo".

Signed-off-by: Tim Abbott <tabbott@ksplice.com>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
---
 include/linux/init_task.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 5368fbdc7801..7fc01b13be43 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -183,5 +183,8 @@ extern struct cred init_cred;
 	LIST_HEAD_INIT(cpu_timers[2]),					\
 }
 
+/* Attach to the init_task data structure for proper alignment */
+#define __init_task_data __attribute__((__section__(".data.init_task")))
+
 
 #endif
-- 
cgit v1.2.3


From 84261923d3dddb766736023bead6fa07b7e218d5 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Wed, 17 Jun 2009 10:53:47 -0300
Subject: KVM: protect concurrent make_all_cpus_request

make_all_cpus_request contains a race condition which can
trigger false request completed status, as follows:

CPU0                                              CPU1

if (test_and_set_bit(req,&vcpu->requests))
   ....                                        	   if (test_and_set_bit(req,&vcpu->requests))
   ..                                                  return
proceed to smp_call_function_many(wait=1)

Use a spinlock to serialize concurrent CPUs.

Cc: stable@kernel.org
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 include/linux/kvm_host.h | 1 +
 virt/kvm/kvm_main.c      | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index aacc5449f586..16713dc672e4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -125,6 +125,7 @@ struct kvm_kernel_irq_routing_entry {
 struct kvm {
 	struct mutex lock; /* protects the vcpus array and APIC accesses */
 	spinlock_t mmu_lock;
+	spinlock_t requests_lock;
 	struct rw_semaphore slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
 	int nmemslots;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 013a5b3e9f75..2884baf1d5f9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -746,6 +746,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 		cpumask_clear(cpus);
 
 	me = get_cpu();
+	spin_lock(&kvm->requests_lock);
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		vcpu = kvm->vcpus[i];
 		if (!vcpu)
@@ -762,6 +763,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 		smp_call_function_many(cpus, ack_flush, NULL, 1);
 	else
 		called = false;
+	spin_unlock(&kvm->requests_lock);
 	put_cpu();
 	free_cpumask_var(cpus);
 	return called;
@@ -982,6 +984,7 @@ static struct kvm *kvm_create_vm(void)
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
 	spin_lock_init(&kvm->mmu_lock);
+	spin_lock_init(&kvm->requests_lock);
 	kvm_io_bus_init(&kvm->pio_bus);
 	mutex_init(&kvm->lock);
 	kvm_io_bus_init(&kvm->mmio_bus);
-- 
cgit v1.2.3


From 94e5d714f604d4cb4cb13163f01ede278e69258b Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 26 Jun 2009 14:05:27 -0400
Subject: integrity: add ima_counts_put (updated)

This patch fixes an imbalance message as reported by J.R. Okajima.
The IMA file counters are incremented in ima_path_check. If the
actual open fails, such as ETXTBSY, decrement the counters to
prevent unnecessary imbalance messages.

Reported-by: J.R. Okajima <hooanon05@yahoo.co.jp>
Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
---
 fs/namei.c                        |  7 +++++++
 include/linux/ima.h               |  6 ++++++
 security/integrity/ima/ima_main.c | 29 ++++++++++++++++++++++++++++-
 3 files changed, 41 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 5b961eb71cbf..f3c5b278895a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1761,6 +1761,10 @@ do_last:
 			goto exit;
 		}
 		filp = nameidata_to_filp(&nd, open_flag);
+		if (IS_ERR(filp))
+			ima_counts_put(&nd.path,
+				       acc_mode & (MAY_READ | MAY_WRITE |
+						   MAY_EXEC));
 		mnt_drop_write(nd.path.mnt);
 		if (nd.root.mnt)
 			path_put(&nd.root);
@@ -1817,6 +1821,9 @@ ok:
 		goto exit;
 	}
 	filp = nameidata_to_filp(&nd, open_flag);
+	if (IS_ERR(filp))
+		ima_counts_put(&nd.path,
+			       acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
 	/*
 	 * It is now safe to drop the mnt write
 	 * because the filp has had a write taken
diff --git a/include/linux/ima.h b/include/linux/ima.h
index b1b827d091a9..0e3f2a4c25f6 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -24,6 +24,7 @@ extern int ima_path_check(struct path *path, int mask, int update_counts);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern void ima_counts_get(struct file *file);
+extern void ima_counts_put(struct path *path, int mask);
 
 #else
 static inline int ima_bprm_check(struct linux_binprm *bprm)
@@ -60,5 +61,10 @@ static inline void ima_counts_get(struct file *file)
 {
 	return;
 }
+
+static inline void ima_counts_put(struct path *path, int mask)
+{
+	return;
+}
 #endif /* CONFIG_IMA_H */
 #endif /* _LINUX_IMA_H */
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 6f611874d10e..101c512564ec 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -238,7 +238,34 @@ out:
 }
 
 /*
- * ima_opens_get - increment file counts
+ * ima_counts_put - decrement file counts
+ *
+ * File counts are incremented in ima_path_check. On file open
+ * error, such as ETXTBSY, decrement the counts to prevent
+ * unnecessary imbalance messages.
+ */
+void ima_counts_put(struct path *path, int mask)
+{
+	struct inode *inode = path->dentry->d_inode;
+	struct ima_iint_cache *iint;
+
+	if (!ima_initialized || !S_ISREG(inode->i_mode))
+		return;
+	iint = ima_iint_find_insert_get(inode);
+	if (!iint)
+		return;
+
+	mutex_lock(&iint->mutex);
+	iint->opencount--;
+	if ((mask & MAY_WRITE) || (mask == 0))
+		iint->writecount--;
+	else if (mask & (MAY_READ | MAY_EXEC))
+		iint->readcount--;
+	mutex_unlock(&iint->mutex);
+}
+
+/*
+ * ima_counts_get - increment file counts
  *
  * - for IPC shm and shmat file.
  * - for nfsd exported files.
-- 
cgit v1.2.3


From bab7614d6d1b1fc96ec6c5a7ca34c8641060e659 Mon Sep 17 00:00:00 2001
From: Eric Miao <eric.y.miao@gmail.com>
Date: Mon, 29 Jun 2009 00:20:52 -0700
Subject: Input: add support for generic GPIO-based matrix keypad

Original patch by Marek Vasut, modified by Eric in:

1. use delayed work to simplify the debouncing
2. combine col_polarity/row_polarity into a single active_low field
3. use a generic bit array based XOR algorithm to detect key
   press/release, which should make the column assertion time
   shorter and code a bit cleaner
4. remove the ALT_FN handling, which is no way generic, the ALT_FN
   key should be treated as no different from other keys, and
   translation will be done by user space by commands like 'loadkeys'.
5. explicitly disable row IRQs and flush potential pending work,
   and schedule an immediate scan after resuming as suggested
   by Uli Luckas
6. incorporate review comments from many others

Patch tested on Littleton/PXA310 (though PXA310 has a dedicate keypad
controller, I have to configure those pins as generic GPIO to use this
driver, works quite well, though), and Sharp Zaurus model SL-C7x0
and SL-C1000.

[dtor@mail.ru: fix error unwinding path, support changing keymap
 from userspace]
Signed-off-by: Marek Vasut <marek.vasut@gmail.com>
Reviewed-by: Trilok Soni <soni.trilok@gmail.com>
Reviewed-by: Uli Luckas <u.luckas@road.de>
Reviewed-by: Russell King <linux@arm.linux.org.uk>
Reviewed-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Eric Miao <eric.miao@marvell.com>
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
---
 drivers/input/keyboard/Kconfig         |  13 +-
 drivers/input/keyboard/Makefile        |   1 +
 drivers/input/keyboard/matrix_keypad.c | 453 +++++++++++++++++++++++++++++++++
 include/linux/input/matrix_keypad.h    |  65 +++++
 4 files changed, 530 insertions(+), 2 deletions(-)
 create mode 100644 drivers/input/keyboard/matrix_keypad.c
 create mode 100644 include/linux/input/matrix_keypad.h

(limited to 'include')

diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index d2df1030675a..a6b989a9dc07 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -158,7 +158,16 @@ config KEYBOARD_GPIO
 	  with configuration data saying which GPIOs are used.
 
 	  To compile this driver as a module, choose M here: the
-	  module will be called gpio-keys.
+	  module will be called gpio_keys.
+
+config KEYBOARD_MATRIX
+	tristate "GPIO driven matrix keypad support"
+	depends on GENERIC_GPIO
+	help
+	  Enable support for GPIO driven matrix keypad.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called matrix_keypad.
 
 config KEYBOARD_HIL_OLD
 	tristate "HP HIL keyboard support (simple driver)"
@@ -254,7 +263,7 @@ config KEYBOARD_PXA27x
 	tristate "PXA27x/PXA3xx keypad support"
 	depends on PXA27x || PXA3xx
 	help
-	  Enable support for PXA27x/PXA3xx keypad controller
+	  Enable support for PXA27x/PXA3xx keypad controller.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called pxa27x_keypad.
diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile
index 632efbc18c44..b5b5eae9724f 100644
--- a/drivers/input/keyboard/Makefile
+++ b/drivers/input/keyboard/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_KEYBOARD_LKKBD)		+= lkkbd.o
 obj-$(CONFIG_KEYBOARD_LM8323)		+= lm8323.o
 obj-$(CONFIG_KEYBOARD_LOCOMO)		+= locomokbd.o
 obj-$(CONFIG_KEYBOARD_MAPLE)		+= maple_keyb.o
+obj-$(CONFIG_KEYBOARD_MATRIX)		+= matrix_keypad.o
 obj-$(CONFIG_KEYBOARD_NEWTON)		+= newtonkbd.o
 obj-$(CONFIG_KEYBOARD_OMAP)		+= omap-keypad.o
 obj-$(CONFIG_KEYBOARD_PXA27x)		+= pxa27x_keypad.o
diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c
new file mode 100644
index 000000000000..e9b2e7cb05be
--- /dev/null
+++ b/drivers/input/keyboard/matrix_keypad.c
@@ -0,0 +1,453 @@
+/*
+ *  GPIO driven matrix keyboard driver
+ *
+ *  Copyright (c) 2008 Marek Vasut <marek.vasut@gmail.com>
+ *
+ *  Based on corgikbd.c
+ *
+ *  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/types.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/input.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/gpio.h>
+#include <linux/input/matrix_keypad.h>
+
+struct matrix_keypad {
+	const struct matrix_keypad_platform_data *pdata;
+	struct input_dev *input_dev;
+	unsigned short *keycodes;
+
+	uint32_t last_key_state[MATRIX_MAX_COLS];
+	struct delayed_work work;
+	bool scan_pending;
+	bool stopped;
+	spinlock_t lock;
+};
+
+/*
+ * NOTE: normally the GPIO has to be put into HiZ when de-activated to cause
+ * minmal side effect when scanning other columns, here it is configured to
+ * be input, and it should work on most platforms.
+ */
+static void __activate_col(const struct matrix_keypad_platform_data *pdata,
+			   int col, bool on)
+{
+	bool level_on = !pdata->active_low;
+
+	if (on) {
+		gpio_direction_output(pdata->col_gpios[col], level_on);
+	} else {
+		gpio_set_value_cansleep(pdata->col_gpios[col], !level_on);
+		gpio_direction_input(pdata->col_gpios[col]);
+	}
+}
+
+static void activate_col(const struct matrix_keypad_platform_data *pdata,
+			 int col, bool on)
+{
+	__activate_col(pdata, col, on);
+
+	if (on && pdata->col_scan_delay_us)
+		udelay(pdata->col_scan_delay_us);
+}
+
+static void activate_all_cols(const struct matrix_keypad_platform_data *pdata,
+			      bool on)
+{
+	int col;
+
+	for (col = 0; col < pdata->num_col_gpios; col++)
+		__activate_col(pdata, col, on);
+}
+
+static bool row_asserted(const struct matrix_keypad_platform_data *pdata,
+			 int row)
+{
+	return gpio_get_value_cansleep(pdata->row_gpios[row]) ?
+			!pdata->active_low : pdata->active_low;
+}
+
+static void enable_row_irqs(struct matrix_keypad *keypad)
+{
+	const struct matrix_keypad_platform_data *pdata = keypad->pdata;
+	int i;
+
+	for (i = 0; i < pdata->num_row_gpios; i++)
+		enable_irq(gpio_to_irq(pdata->row_gpios[i]));
+}
+
+static void disable_row_irqs(struct matrix_keypad *keypad)
+{
+	const struct matrix_keypad_platform_data *pdata = keypad->pdata;
+	int i;
+
+	for (i = 0; i < pdata->num_row_gpios; i++)
+		disable_irq_nosync(gpio_to_irq(pdata->row_gpios[i]));
+}
+
+/*
+ * This gets the keys from keyboard and reports it to input subsystem
+ */
+static void matrix_keypad_scan(struct work_struct *work)
+{
+	struct matrix_keypad *keypad =
+		container_of(work, struct matrix_keypad, work.work);
+	struct input_dev *input_dev = keypad->input_dev;
+	const struct matrix_keypad_platform_data *pdata = keypad->pdata;
+	uint32_t new_state[MATRIX_MAX_COLS];
+	int row, col, code;
+
+	/* de-activate all columns for scanning */
+	activate_all_cols(pdata, false);
+
+	memset(new_state, 0, sizeof(new_state));
+
+	/* assert each column and read the row status out */
+	for (col = 0; col < pdata->num_col_gpios; col++) {
+
+		activate_col(pdata, col, true);
+
+		for (row = 0; row < pdata->num_row_gpios; row++)
+			new_state[col] |=
+				row_asserted(pdata, row) ? (1 << row) : 0;
+
+		activate_col(pdata, col, false);
+	}
+
+	for (col = 0; col < pdata->num_col_gpios; col++) {
+		uint32_t bits_changed;
+
+		bits_changed = keypad->last_key_state[col] ^ new_state[col];
+		if (bits_changed == 0)
+			continue;
+
+		for (row = 0; row < pdata->num_row_gpios; row++) {
+			if ((bits_changed & (1 << row)) == 0)
+				continue;
+
+			code = (row << 4) + col;
+			input_event(input_dev, EV_MSC, MSC_SCAN, code);
+			input_report_key(input_dev,
+					 keypad->keycodes[code],
+					 new_state[col] & (1 << row));
+		}
+	}
+	input_sync(input_dev);
+
+	memcpy(keypad->last_key_state, new_state, sizeof(new_state));
+
+	activate_all_cols(pdata, true);
+
+	/* Enable IRQs again */
+	spin_lock_irq(&keypad->lock);
+	keypad->scan_pending = false;
+	enable_row_irqs(keypad);
+	spin_unlock_irq(&keypad->lock);
+}
+
+static irqreturn_t matrix_keypad_interrupt(int irq, void *id)
+{
+	struct matrix_keypad *keypad = id;
+	unsigned long flags;
+
+	spin_lock_irqsave(&keypad->lock, flags);
+
+	/*
+	 * See if another IRQ beaten us to it and scheduled the
+	 * scan already. In that case we should not try to
+	 * disable IRQs again.
+	 */
+	if (unlikely(keypad->scan_pending || keypad->stopped))
+		goto out;
+
+	disable_row_irqs(keypad);
+	keypad->scan_pending = true;
+	schedule_delayed_work(&keypad->work,
+		msecs_to_jiffies(keypad->pdata->debounce_ms));
+
+out:
+	spin_unlock_irqrestore(&keypad->lock, flags);
+	return IRQ_HANDLED;
+}
+
+static int matrix_keypad_start(struct input_dev *dev)
+{
+	struct matrix_keypad *keypad = input_get_drvdata(dev);
+
+	keypad->stopped = false;
+	mb();
+
+	/*
+	 * Schedule an immediate key scan to capture current key state;
+	 * columns will be activated and IRQs be enabled after the scan.
+	 */
+	schedule_delayed_work(&keypad->work, 0);
+
+	return 0;
+}
+
+static void matrix_keypad_stop(struct input_dev *dev)
+{
+	struct matrix_keypad *keypad = input_get_drvdata(dev);
+
+	keypad->stopped = true;
+	mb();
+	flush_work(&keypad->work.work);
+	/*
+	 * matrix_keypad_scan() will leave IRQs enabled;
+	 * we should disable them now.
+	 */
+	disable_row_irqs(keypad);
+}
+
+#ifdef CONFIG_PM
+static int matrix_keypad_suspend(struct platform_device *pdev, pm_message_t state)
+{
+	struct matrix_keypad *keypad = platform_get_drvdata(pdev);
+	const struct matrix_keypad_platform_data *pdata = keypad->pdata;
+	int i;
+
+	matrix_keypad_stop(keypad->input_dev);
+
+	if (device_may_wakeup(&pdev->dev))
+		for (i = 0; i < pdata->num_row_gpios; i++)
+			enable_irq_wake(gpio_to_irq(pdata->row_gpios[i]));
+
+	return 0;
+}
+
+static int matrix_keypad_resume(struct platform_device *pdev)
+{
+	struct matrix_keypad *keypad = platform_get_drvdata(pdev);
+	const struct matrix_keypad_platform_data *pdata = keypad->pdata;
+	int i;
+
+	if (device_may_wakeup(&pdev->dev))
+		for (i = 0; i < pdata->num_row_gpios; i++)
+			disable_irq_wake(gpio_to_irq(pdata->row_gpios[i]));
+
+	matrix_keypad_start(keypad->input_dev);
+
+	return 0;
+}
+#else
+#define matrix_keypad_suspend	NULL
+#define matrix_keypad_resume	NULL
+#endif
+
+static int __devinit init_matrix_gpio(struct platform_device *pdev,
+					struct matrix_keypad *keypad)
+{
+	const struct matrix_keypad_platform_data *pdata = keypad->pdata;
+	int i, err = -EINVAL;
+
+	/* initialized strobe lines as outputs, activated */
+	for (i = 0; i < pdata->num_col_gpios; i++) {
+		err = gpio_request(pdata->col_gpios[i], "matrix_kbd_col");
+		if (err) {
+			dev_err(&pdev->dev,
+				"failed to request GPIO%d for COL%d\n",
+				pdata->col_gpios[i], i);
+			goto err_free_cols;
+		}
+
+		gpio_direction_output(pdata->col_gpios[i], !pdata->active_low);
+	}
+
+	for (i = 0; i < pdata->num_row_gpios; i++) {
+		err = gpio_request(pdata->row_gpios[i], "matrix_kbd_row");
+		if (err) {
+			dev_err(&pdev->dev,
+				"failed to request GPIO%d for ROW%d\n",
+				pdata->row_gpios[i], i);
+			goto err_free_rows;
+		}
+
+		gpio_direction_input(pdata->row_gpios[i]);
+	}
+
+	for (i = 0; i < pdata->num_row_gpios; i++) {
+		err = request_irq(gpio_to_irq(pdata->row_gpios[i]),
+				matrix_keypad_interrupt,
+				IRQF_DISABLED |
+				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
+				"matrix-keypad", keypad);
+		if (err) {
+			dev_err(&pdev->dev,
+				"Unable to acquire interrupt for GPIO line %i\n",
+				pdata->row_gpios[i]);
+			goto err_free_irqs;
+		}
+	}
+
+	/* initialized as disabled - enabled by input->open */
+	disable_row_irqs(keypad);
+	return 0;
+
+err_free_irqs:
+	while (--i >= 0)
+		free_irq(gpio_to_irq(pdata->row_gpios[i]), keypad);
+	i = pdata->num_row_gpios;
+err_free_rows:
+	while (--i >= 0)
+		gpio_free(pdata->row_gpios[i]);
+	i = pdata->num_col_gpios;
+err_free_cols:
+	while (--i >= 0)
+		gpio_free(pdata->col_gpios[i]);
+
+	return err;
+}
+
+static int __devinit matrix_keypad_probe(struct platform_device *pdev)
+{
+	const struct matrix_keypad_platform_data *pdata;
+	const struct matrix_keymap_data *keymap_data;
+	struct matrix_keypad *keypad;
+	struct input_dev *input_dev;
+	unsigned short *keycodes;
+	int i;
+	int err;
+
+	pdata = pdev->dev.platform_data;
+	if (!pdata) {
+		dev_err(&pdev->dev, "no platform data defined\n");
+		return -EINVAL;
+	}
+
+	keymap_data = pdata->keymap_data;
+	if (!keymap_data) {
+		dev_err(&pdev->dev, "no keymap data defined\n");
+		return -EINVAL;
+	}
+
+	if (!keymap_data->max_keymap_size) {
+		dev_err(&pdev->dev, "invalid keymap data supplied\n");
+		return -EINVAL;
+	}
+
+	keypad = kzalloc(sizeof(struct matrix_keypad), GFP_KERNEL);
+	keycodes = kzalloc(keymap_data->max_keymap_size *
+				sizeof(keypad->keycodes),
+			   GFP_KERNEL);
+	input_dev = input_allocate_device();
+	if (!keypad || !keycodes || !input_dev) {
+		err = -ENOMEM;
+		goto err_free_mem;
+	}
+
+	keypad->input_dev = input_dev;
+	keypad->pdata = pdata;
+	keypad->keycodes = keycodes;
+	keypad->stopped = true;
+	INIT_DELAYED_WORK(&keypad->work, matrix_keypad_scan);
+	spin_lock_init(&keypad->lock);
+
+	input_dev->name		= pdev->name;
+	input_dev->id.bustype	= BUS_HOST;
+	input_dev->dev.parent	= &pdev->dev;
+	input_dev->evbit[0]	= BIT_MASK(EV_KEY) | BIT_MASK(EV_REP);
+	input_dev->open		= matrix_keypad_start;
+	input_dev->close	= matrix_keypad_stop;
+
+	input_dev->keycode	= keycodes;
+	input_dev->keycodesize	= sizeof(*keycodes);
+	input_dev->keycodemax	= keymap_data->max_keymap_size;
+
+	for (i = 0; i < keymap_data->keymap_size; i++) {
+		unsigned int key = keymap_data->keymap[i];
+		unsigned int row = KEY_ROW(key);
+		unsigned int col = KEY_COL(key);
+		unsigned short code = KEY_VAL(key);
+
+		keycodes[(row << 4) + col] = code;
+		__set_bit(code, input_dev->keybit);
+	}
+	__clear_bit(KEY_RESERVED, input_dev->keybit);
+
+	input_set_capability(input_dev, EV_MSC, MSC_SCAN);
+	input_set_drvdata(input_dev, keypad);
+
+	err = init_matrix_gpio(pdev, keypad);
+	if (err)
+		goto err_free_mem;
+
+	err = input_register_device(keypad->input_dev);
+	if (err)
+		goto err_free_mem;
+
+	device_init_wakeup(&pdev->dev, pdata->wakeup);
+	platform_set_drvdata(pdev, keypad);
+
+	return 0;
+
+err_free_mem:
+	input_free_device(input_dev);
+	kfree(keycodes);
+	kfree(keypad);
+	return err;
+}
+
+static int __devexit matrix_keypad_remove(struct platform_device *pdev)
+{
+	struct matrix_keypad *keypad = platform_get_drvdata(pdev);
+	const struct matrix_keypad_platform_data *pdata = keypad->pdata;
+	int i;
+
+	device_init_wakeup(&pdev->dev, 0);
+
+	for (i = 0; i < pdata->num_row_gpios; i++) {
+		free_irq(gpio_to_irq(pdata->row_gpios[i]), keypad);
+		gpio_free(pdata->row_gpios[i]);
+	}
+
+	for (i = 0; i < pdata->num_col_gpios; i++)
+		gpio_free(pdata->col_gpios[i]);
+
+	input_unregister_device(keypad->input_dev);
+	platform_set_drvdata(pdev, NULL);
+	kfree(keypad->keycodes);
+	kfree(keypad);
+
+	return 0;
+}
+
+static struct platform_driver matrix_keypad_driver = {
+	.probe		= matrix_keypad_probe,
+	.remove		= __devexit_p(matrix_keypad_remove),
+	.suspend	= matrix_keypad_suspend,
+	.resume		= matrix_keypad_resume,
+	.driver		= {
+		.name	= "matrix-keypad",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init matrix_keypad_init(void)
+{
+	return platform_driver_register(&matrix_keypad_driver);
+}
+
+static void __exit matrix_keypad_exit(void)
+{
+	platform_driver_unregister(&matrix_keypad_driver);
+}
+
+module_init(matrix_keypad_init);
+module_exit(matrix_keypad_exit);
+
+MODULE_AUTHOR("Marek Vasut <marek.vasut@gmail.com>");
+MODULE_DESCRIPTION("GPIO Driven Matrix Keypad Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:matrix-keypad");
diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h
new file mode 100644
index 000000000000..7964516c6954
--- /dev/null
+++ b/include/linux/input/matrix_keypad.h
@@ -0,0 +1,65 @@
+#ifndef _MATRIX_KEYPAD_H
+#define _MATRIX_KEYPAD_H
+
+#include <linux/types.h>
+#include <linux/input.h>
+
+#define MATRIX_MAX_ROWS		16
+#define MATRIX_MAX_COLS		16
+
+#define KEY(row, col, val)	((((row) & (MATRIX_MAX_ROWS - 1)) << 24) |\
+				 (((col) & (MATRIX_MAX_COLS - 1)) << 16) |\
+				 (val & 0xffff))
+
+#define KEY_ROW(k)		(((k) >> 24) & 0xff)
+#define KEY_COL(k)		(((k) >> 16) & 0xff)
+#define KEY_VAL(k)		((k) & 0xffff)
+
+/**
+ * struct matrix_keymap_data - keymap for matrix keyboards
+ * @keymap: pointer to array of uint32 values encoded with KEY() macro
+ *	representing keymap
+ * @keymap_size: number of entries (initialized) in this keymap
+ * @max_keymap_size: maximum size of keymap supported by the device
+ *
+ * This structure is supposed to be used by platform code to supply
+ * keymaps to drivers that implement matrix-like keypads/keyboards.
+ */
+struct matrix_keymap_data {
+	const uint32_t *keymap;
+	unsigned int	keymap_size;
+	unsigned int	max_keymap_size;
+};
+
+/**
+ * struct matrix_keypad_platform_data - platform-dependent keypad data
+ * @keymap_data: pointer to &matrix_keymap_data
+ * @row_gpios: array of gpio numbers reporesenting rows
+ * @col_gpios: array of gpio numbers reporesenting colums
+ * @num_row_gpios: actual number of row gpios used by device
+ * @num_col_gpios: actual number of col gpios used by device
+ * @col_scan_delay_us: delay, measured in microseconds, that is
+ *	needed before we can keypad after activating column gpio
+ * @debounce_ms: debounce interval in milliseconds
+ *
+ * This structure represents platform-specific data that use used by
+ * matrix_keypad driver to perform proper initialization.
+ */
+struct matrix_keypad_platform_data {
+	const struct matrix_keymap_data *keymap_data;
+
+	unsigned int	row_gpios[MATRIX_MAX_ROWS];
+	unsigned int	col_gpios[MATRIX_MAX_COLS];
+	unsigned int	num_row_gpios;
+	unsigned int	num_col_gpios;
+
+	unsigned int	col_scan_delay_us;
+
+	/* key debounce interval in milli-second */
+	unsigned int	debounce_ms;
+
+	bool		active_low;
+	bool		wakeup;
+};
+
+#endif /* _MATRIX_KEYPAD_H */
-- 
cgit v1.2.3


From a3a9f79e361e864f0e9d75ebe2a0cb43d17c4272 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Mon, 29 Jun 2009 14:07:56 +0200
Subject: netfilter: tcp conntrack: fix unacknowledged data detection with NAT

When NAT helpers change the TCP packet size, the highest seen sequence
number needs to be corrected. This is currently only done upwards, when
the packet size is reduced the sequence number is unchanged. This causes
TCP conntrack to falsely detect unacknowledged data and decrease the
timeout.

Fix by updating the highest seen sequence number in both directions after
packet mangling.

Tested-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/net/netfilter/nf_conntrack.h   |  4 ++--
 net/ipv4/netfilter/nf_nat_helper.c     | 17 +++++++++++------
 net/netfilter/nf_conntrack_proto_tcp.c |  6 +++---
 3 files changed, 16 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index a632689b61b4..cbdd6284996d 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -258,8 +258,8 @@ static inline bool nf_ct_kill(struct nf_conn *ct)
 /* Update TCP window tracking data when NAT mangles the packet */
 extern void nf_conntrack_tcp_update(const struct sk_buff *skb,
 				    unsigned int dataoff,
-				    struct nf_conn *ct,
-				    int dir);
+				    struct nf_conn *ct, int dir,
+				    s16 offset);
 
 /* Fake conntrack entry for untracked connections */
 extern struct nf_conn nf_conntrack_untracked;
diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c
index 155c008626c8..09172a65d9b6 100644
--- a/net/ipv4/netfilter/nf_nat_helper.c
+++ b/net/ipv4/netfilter/nf_nat_helper.c
@@ -191,7 +191,8 @@ nf_nat_mangle_tcp_packet(struct sk_buff *skb,
 				    ct, ctinfo);
 		/* Tell TCP window tracking about seq change */
 		nf_conntrack_tcp_update(skb, ip_hdrlen(skb),
-					ct, CTINFO2DIR(ctinfo));
+					ct, CTINFO2DIR(ctinfo),
+					(int)rep_len - (int)match_len);
 
 		nf_conntrack_event_cache(IPCT_NATSEQADJ, ct);
 	}
@@ -377,6 +378,7 @@ nf_nat_seq_adjust(struct sk_buff *skb,
 	struct tcphdr *tcph;
 	int dir;
 	__be32 newseq, newack;
+	s16 seqoff, ackoff;
 	struct nf_conn_nat *nat = nfct_nat(ct);
 	struct nf_nat_seq *this_way, *other_way;
 
@@ -390,15 +392,18 @@ nf_nat_seq_adjust(struct sk_buff *skb,
 
 	tcph = (void *)skb->data + ip_hdrlen(skb);
 	if (after(ntohl(tcph->seq), this_way->correction_pos))
-		newseq = htonl(ntohl(tcph->seq) + this_way->offset_after);
+		seqoff = this_way->offset_after;
 	else
-		newseq = htonl(ntohl(tcph->seq) + this_way->offset_before);
+		seqoff = this_way->offset_before;
 
 	if (after(ntohl(tcph->ack_seq) - other_way->offset_before,
 		  other_way->correction_pos))
-		newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_after);
+		ackoff = other_way->offset_after;
 	else
-		newack = htonl(ntohl(tcph->ack_seq) - other_way->offset_before);
+		ackoff = other_way->offset_before;
+
+	newseq = htonl(ntohl(tcph->seq) + seqoff);
+	newack = htonl(ntohl(tcph->ack_seq) - ackoff);
 
 	inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0);
 	inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0);
@@ -413,7 +418,7 @@ nf_nat_seq_adjust(struct sk_buff *skb,
 	if (!nf_nat_sack_adjust(skb, tcph, ct, ctinfo))
 		return 0;
 
-	nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir);
+	nf_conntrack_tcp_update(skb, ip_hdrlen(skb), ct, dir, seqoff);
 
 	return 1;
 }
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 33fc0a443f3d..97a82ba75376 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -720,8 +720,8 @@ static bool tcp_in_window(const struct nf_conn *ct,
 /* Caller must linearize skb at tcp header. */
 void nf_conntrack_tcp_update(const struct sk_buff *skb,
 			     unsigned int dataoff,
-			     struct nf_conn *ct,
-			     int dir)
+			     struct nf_conn *ct, int dir,
+			     s16 offset)
 {
 	const struct tcphdr *tcph = (const void *)skb->data + dataoff;
 	const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[dir];
@@ -734,7 +734,7 @@ void nf_conntrack_tcp_update(const struct sk_buff *skb,
 	/*
 	 * We have to worry for the ack in the reply packet only...
 	 */
-	if (after(end, ct->proto.tcp.seen[dir].td_end))
+	if (ct->proto.tcp.seen[dir].td_end + offset == end)
 		ct->proto.tcp.seen[dir].td_end = end;
 	ct->proto.tcp.last_end = end;
 	spin_unlock_bh(&ct->lock);
-- 
cgit v1.2.3


From 8a3af79361e85db6fec4173ef1916322471c19e3 Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Date: Mon, 29 Jun 2009 14:28:27 +0200
Subject: netfilter: headers_check fix: linux/netfilter/xt_osf.h

fix the following 'make headers_check' warnings:

  usr/include/linux/netfilter/xt_osf.h:40: found __[us]{8,16,32,64} type without #include <linux/types.h>

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/xt_osf.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/netfilter/xt_osf.h b/include/linux/netfilter/xt_osf.h
index fd2272e0959a..18afa495f973 100644
--- a/include/linux/netfilter/xt_osf.h
+++ b/include/linux/netfilter/xt_osf.h
@@ -20,6 +20,8 @@
 #ifndef _XT_OSF_H
 #define _XT_OSF_H
 
+#include <linux/types.h>
+
 #define MAXGENRELEN		32
 
 #define XT_OSF_GENRE		(1<<0)
-- 
cgit v1.2.3


From d6d3f08b0fd998b647a05540cedd11a067b72867 Mon Sep 17 00:00:00 2001
From: Jan Engelhardt <jengelh@medozas.de>
Date: Mon, 29 Jun 2009 14:31:46 +0200
Subject: netfilter: xtables: conntrack match revision 2

As reported by Philip, the UNTRACKED state bit does not fit within
the 8-bit state_mask member. Enlarge state_mask and give status_mask
a few more bits too.

Reported-by: Philip Craig <philipc@snapgear.com>
References: http://markmail.org/thread/b7eg6aovfh4agyz7
Signed-off-by: Jan Engelhardt <jengelh@medozas.de>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
 include/linux/netfilter/xt_conntrack.h | 13 +++++++
 net/netfilter/xt_conntrack.c           | 66 ++++++++++++++++++++++++++++++----
 2 files changed, 73 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h
index 3430c7751948..7ae05338e94c 100644
--- a/include/linux/netfilter/xt_conntrack.h
+++ b/include/linux/netfilter/xt_conntrack.h
@@ -81,4 +81,17 @@ struct xt_conntrack_mtinfo1 {
 	__u8 state_mask, status_mask;
 };
 
+struct xt_conntrack_mtinfo2 {
+	union nf_inet_addr origsrc_addr, origsrc_mask;
+	union nf_inet_addr origdst_addr, origdst_mask;
+	union nf_inet_addr replsrc_addr, replsrc_mask;
+	union nf_inet_addr repldst_addr, repldst_mask;
+	__u32 expires_min, expires_max;
+	__u16 l4proto;
+	__be16 origsrc_port, origdst_port;
+	__be16 replsrc_port, repldst_port;
+	__u16 match_flags, invert_flags;
+	__u16 state_mask, status_mask;
+};
+
 #endif /*_XT_CONNTRACK_H*/
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index 0b7139f3dd78..fc581800698e 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -129,7 +129,7 @@ conntrack_addrcmp(const union nf_inet_addr *kaddr,
 
 static inline bool
 conntrack_mt_origsrc(const struct nf_conn *ct,
-                     const struct xt_conntrack_mtinfo1 *info,
+                     const struct xt_conntrack_mtinfo2 *info,
 		     u_int8_t family)
 {
 	return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3,
@@ -138,7 +138,7 @@ conntrack_mt_origsrc(const struct nf_conn *ct,
 
 static inline bool
 conntrack_mt_origdst(const struct nf_conn *ct,
-                     const struct xt_conntrack_mtinfo1 *info,
+                     const struct xt_conntrack_mtinfo2 *info,
 		     u_int8_t family)
 {
 	return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3,
@@ -147,7 +147,7 @@ conntrack_mt_origdst(const struct nf_conn *ct,
 
 static inline bool
 conntrack_mt_replsrc(const struct nf_conn *ct,
-                     const struct xt_conntrack_mtinfo1 *info,
+                     const struct xt_conntrack_mtinfo2 *info,
 		     u_int8_t family)
 {
 	return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3,
@@ -156,7 +156,7 @@ conntrack_mt_replsrc(const struct nf_conn *ct,
 
 static inline bool
 conntrack_mt_repldst(const struct nf_conn *ct,
-                     const struct xt_conntrack_mtinfo1 *info,
+                     const struct xt_conntrack_mtinfo2 *info,
 		     u_int8_t family)
 {
 	return conntrack_addrcmp(&ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3,
@@ -164,7 +164,7 @@ conntrack_mt_repldst(const struct nf_conn *ct,
 }
 
 static inline bool
-ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info,
+ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info,
                     const struct nf_conn *ct)
 {
 	const struct nf_conntrack_tuple *tuple;
@@ -204,7 +204,7 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo1 *info,
 static bool
 conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par)
 {
-	const struct xt_conntrack_mtinfo1 *info = par->matchinfo;
+	const struct xt_conntrack_mtinfo2 *info = par->matchinfo;
 	enum ip_conntrack_info ctinfo;
 	const struct nf_conn *ct;
 	unsigned int statebit;
@@ -278,6 +278,16 @@ conntrack_mt(const struct sk_buff *skb, const struct xt_match_param *par)
 	return true;
 }
 
+static bool
+conntrack_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par)
+{
+	const struct xt_conntrack_mtinfo2 *const *info = par->matchinfo;
+	struct xt_match_param newpar = *par;
+
+	newpar.matchinfo = *info;
+	return conntrack_mt(skb, &newpar);
+}
+
 static bool conntrack_mt_check(const struct xt_mtchk_param *par)
 {
 	if (nf_ct_l3proto_try_module_get(par->family) < 0) {
@@ -288,11 +298,45 @@ static bool conntrack_mt_check(const struct xt_mtchk_param *par)
 	return true;
 }
 
+static bool conntrack_mt_check_v1(const struct xt_mtchk_param *par)
+{
+	struct xt_conntrack_mtinfo1 *info = par->matchinfo;
+	struct xt_conntrack_mtinfo2 *up;
+	int ret = conntrack_mt_check(par);
+
+	if (ret < 0)
+		return ret;
+
+	up = kmalloc(sizeof(*up), GFP_KERNEL);
+	if (up == NULL) {
+		nf_ct_l3proto_module_put(par->family);
+		return -ENOMEM;
+	}
+
+	/*
+	 * The strategy here is to minimize the overhead of v1 matching,
+	 * by prebuilding a v2 struct and putting the pointer into the
+	 * v1 dataspace.
+	 */
+	memcpy(up, info, offsetof(typeof(*info), state_mask));
+	up->state_mask  = info->state_mask;
+	up->status_mask = info->status_mask;
+	*(void **)info  = up;
+	return true;
+}
+
 static void conntrack_mt_destroy(const struct xt_mtdtor_param *par)
 {
 	nf_ct_l3proto_module_put(par->family);
 }
 
+static void conntrack_mt_destroy_v1(const struct xt_mtdtor_param *par)
+{
+	struct xt_conntrack_mtinfo2 **info = par->matchinfo;
+	kfree(*info);
+	conntrack_mt_destroy(par);
+}
+
 #ifdef CONFIG_COMPAT
 struct compat_xt_conntrack_info
 {
@@ -363,6 +407,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = {
 		.revision   = 1,
 		.family     = NFPROTO_UNSPEC,
 		.matchsize  = sizeof(struct xt_conntrack_mtinfo1),
+		.match      = conntrack_mt_v1,
+		.checkentry = conntrack_mt_check_v1,
+		.destroy    = conntrack_mt_destroy_v1,
+		.me         = THIS_MODULE,
+	},
+	{
+		.name       = "conntrack",
+		.revision   = 2,
+		.family     = NFPROTO_UNSPEC,
+		.matchsize  = sizeof(struct xt_conntrack_mtinfo2),
 		.match      = conntrack_mt,
 		.checkentry = conntrack_mt_check,
 		.destroy    = conntrack_mt_destroy,
-- 
cgit v1.2.3


From e6ce3066010a21bde961d8f8cefe0b69cae78a0f Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@ozlabs.org>
Date: Mon, 29 Jun 2009 14:31:58 +0800
Subject: fs: allow d_instantiate to be called with negative parent dentry

The new fsnotify infrastructure (starting at 90586523) causes an oops in
spufs, where we populate a directory with files before instantiating the
directory itself. The new changes seem to have introduced an assumption
that a dentry's parent will be positive when instantiating.

This change makes it once again possible to d_instantiate a dentry
with a negative parent, and brings __fsnotify_d_instantiate() into
line with inotify_d_instantiate(), which already has this NULL check.

Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/fsnotify_backend.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 44848aa830dc..6c3de999fb34 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -280,7 +280,7 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
 	assert_spin_locked(&dentry->d_lock);
 
 	parent = dentry->d_parent;
-	if (fsnotify_inode_watches_children(parent->d_inode))
+	if (parent->d_inode && fsnotify_inode_watches_children(parent->d_inode))
 		dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
 	else
 		dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
-- 
cgit v1.2.3


From 2fc90f6133a87da8177636866557d4cc5f56e661 Mon Sep 17 00:00:00 2001
From: Alexey Zaytsev <zaytsev@altell.ru>
Date: Wed, 24 Jun 2009 16:22:30 +0400
Subject: PCI: make pci_name() take const argument

Since this function should never modify it (saves warnings when called with
const args too).

Signed-off-by: Alexey Zaytsev <zaytsev@altell.ru>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 include/linux/pci.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index d304ddf412d0..115fb7ba5089 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1145,7 +1145,7 @@ static inline void pci_set_drvdata(struct pci_dev *pdev, void *data)
 /* If you want to know what to call your pci_dev, ask this function.
  * Again, it's a wrapper around the generic device.
  */
-static inline const char *pci_name(struct pci_dev *pdev)
+static inline const char *pci_name(const struct pci_dev *pdev)
 {
 	return dev_name(&pdev->dev);
 }
-- 
cgit v1.2.3


From 2bf427b25b79eb7cea27963a66c3d4684cae0e0c Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Mon, 29 Jun 2009 19:20:42 -0700
Subject: ide: fix resume for CONFIG_BLK_DEV_IDEACPI=y

commit 2f0d0fd2a605666d38e290c5c0d2907484352dc4 ("ide-acpi: cleanup
do_drive_get_GTF()") didn't account for the lack of hwif->acpidata
check in generic_ide_suspend() [ indirect user of do_drive_get_GTF()
through ide_acpi_exec_tfs() ] resulting in broken resume when ACPI
support is enabled but ACPI data is unavailable.

Fix it by adding ide_port_acpi() helper for checking if port needs
ACPI handling and cleaning generic_ide_{suspend,resume}() to use it
instead of hiding hwif->acpidata and ide_noacpi checks in IDE ACPI
helpers (this should help in preventing similar bugs in the future).

While at it:
- kill superfluous debugging printks in ide_acpi_{get,push}_timing()

Reported-and-tested-by: Etienne Basset <etienne.basset@numericable.fr>
Also-reported-and-tested-by: Jeff Chua <jeff.chua.linux@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ide/ide-acpi.c | 37 +++++++------------------------------
 drivers/ide/ide-pm.c   | 30 ++++++++++++++++++------------
 include/linux/ide.h    |  2 ++
 3 files changed, 27 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-acpi.c b/drivers/ide/ide-acpi.c
index 77f79d26b264..c509c9916464 100644
--- a/drivers/ide/ide-acpi.c
+++ b/drivers/ide/ide-acpi.c
@@ -92,6 +92,11 @@ int ide_acpi_init(void)
 	return 0;
 }
 
+bool ide_port_acpi(ide_hwif_t *hwif)
+{
+	return ide_noacpi == 0 && hwif->acpidata;
+}
+
 /**
  * ide_get_dev_handle - finds acpi_handle and PCI device.function
  * @dev: device to locate
@@ -352,9 +357,6 @@ int ide_acpi_exec_tfs(ide_drive_t *drive)
 	unsigned long	gtf_address;
 	unsigned long	obj_loc;
 
-	if (ide_noacpi)
-		return 0;
-
 	DEBPRINT("call get_GTF, drive=%s port=%d\n", drive->name, drive->dn);
 
 	ret = do_drive_get_GTF(drive, &gtf_length, &gtf_address, &obj_loc);
@@ -389,16 +391,6 @@ void ide_acpi_get_timing(ide_hwif_t *hwif)
 	struct acpi_buffer	output;
 	union acpi_object 	*out_obj;
 
-	if (ide_noacpi)
-		return;
-
-	DEBPRINT("ENTER:\n");
-
-	if (!hwif->acpidata) {
-		DEBPRINT("no ACPI data for %s\n", hwif->name);
-		return;
-	}
-
 	/* Setting up output buffer for _GTM */
 	output.length = ACPI_ALLOCATE_BUFFER;
 	output.pointer = NULL;	/* ACPI-CA sets this; save/free it later */
@@ -479,16 +471,6 @@ void ide_acpi_push_timing(ide_hwif_t *hwif)
 	struct ide_acpi_drive_link	*master = &hwif->acpidata->master;
 	struct ide_acpi_drive_link	*slave = &hwif->acpidata->slave;
 
-	if (ide_noacpi)
-		return;
-
-	DEBPRINT("ENTER:\n");
-
-	if (!hwif->acpidata) {
-		DEBPRINT("no ACPI data for %s\n", hwif->name);
-		return;
-	}
-
 	/* Give the GTM buffer + drive Identify data to the channel via the
 	 * _STM method: */
 	/* setup input parameters buffer for _STM */
@@ -527,16 +509,11 @@ void ide_acpi_set_state(ide_hwif_t *hwif, int on)
 	ide_drive_t *drive;
 	int i;
 
-	if (ide_noacpi || ide_noacpi_psx)
+	if (ide_noacpi_psx)
 		return;
 
 	DEBPRINT("ENTER:\n");
 
-	if (!hwif->acpidata) {
-		DEBPRINT("no ACPI data for %s\n", hwif->name);
-		return;
-	}
-
 	/* channel first and then drives for power on and verse versa for power off */
 	if (on)
 		acpi_bus_set_power(hwif->acpidata->obj_handle, ACPI_STATE_D0);
@@ -616,7 +593,7 @@ void ide_acpi_port_init_devices(ide_hwif_t *hwif)
 				 drive->name, err);
 	}
 
-	if (!ide_acpionboot) {
+	if (ide_noacpi || ide_acpionboot == 0) {
 		DEBPRINT("ACPI methods disabled on boot\n");
 		return;
 	}
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index c14ca144cffe..ad7be2669dcb 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -10,9 +10,11 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	struct request_pm_state rqpm;
 	int ret;
 
-	/* call ACPI _GTM only once */
-	if ((drive->dn & 1) == 0 || pair == NULL)
-		ide_acpi_get_timing(hwif);
+	if (ide_port_acpi(hwif)) {
+		/* call ACPI _GTM only once */
+		if ((drive->dn & 1) == 0 || pair == NULL)
+			ide_acpi_get_timing(hwif);
+	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
@@ -26,9 +28,11 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	ret = blk_execute_rq(drive->queue, NULL, rq, 0);
 	blk_put_request(rq);
 
-	/* call ACPI _PS3 only after both devices are suspended */
-	if (ret == 0 && ((drive->dn & 1) || pair == NULL))
-		ide_acpi_set_state(hwif, 0);
+	if (ret == 0 && ide_port_acpi(hwif)) {
+		/* call ACPI _PS3 only after both devices are suspended */
+		if ((drive->dn & 1) || pair == NULL)
+			ide_acpi_set_state(hwif, 0);
+	}
 
 	return ret;
 }
@@ -42,13 +46,15 @@ int generic_ide_resume(struct device *dev)
 	struct request_pm_state rqpm;
 	int err;
 
-	/* call ACPI _PS0 / _STM only once */
-	if ((drive->dn & 1) == 0 || pair == NULL) {
-		ide_acpi_set_state(hwif, 1);
-		ide_acpi_push_timing(hwif);
-	}
+	if (ide_port_acpi(hwif)) {
+		/* call ACPI _PS0 / _STM only once */
+		if ((drive->dn & 1) == 0 || pair == NULL) {
+			ide_acpi_set_state(hwif, 1);
+			ide_acpi_push_timing(hwif);
+		}
 
-	ide_acpi_exec_tfs(drive);
+		ide_acpi_exec_tfs(drive);
+	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, READ, __GFP_WAIT);
diff --git a/include/linux/ide.h b/include/linux/ide.h
index c6af7c44d46c..edc93a6d931d 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1419,6 +1419,7 @@ static inline void ide_dma_unmap_sg(ide_drive_t *drive,
 
 #ifdef CONFIG_BLK_DEV_IDEACPI
 int ide_acpi_init(void);
+bool ide_port_acpi(ide_hwif_t *hwif);
 extern int ide_acpi_exec_tfs(ide_drive_t *drive);
 extern void ide_acpi_get_timing(ide_hwif_t *hwif);
 extern void ide_acpi_push_timing(ide_hwif_t *hwif);
@@ -1427,6 +1428,7 @@ void ide_acpi_port_init_devices(ide_hwif_t *);
 extern void ide_acpi_set_state(ide_hwif_t *hwif, int on);
 #else
 static inline int ide_acpi_init(void) { return 0; }
+static inline bool ide_port_acpi(ide_hwif_t *hwif) { return 0; }
 static inline int ide_acpi_exec_tfs(ide_drive_t *drive) { return 0; }
 static inline void ide_acpi_get_timing(ide_hwif_t *hwif) { ; }
 static inline void ide_acpi_push_timing(ide_hwif_t *hwif) { ; }
-- 
cgit v1.2.3


From 57e7986ed142417498155ebcd5eaf617ac37136d Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Tue, 30 Jun 2009 16:07:19 +1000
Subject: perf_counter: Provide a way to enable counters on exec

This provides a way to mark a counter to be enabled on the next
exec. This is useful for measuring the total activity of a
program without including overhead from the process that
launches it.

This also changes the perf stat command to use this new
facility.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <19017.43927.838745.689203@cargo.ozlabs.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/perf_counter.h |  3 ++-
 kernel/perf_counter.c        | 50 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/builtin-stat.c    |  6 +++---
 3 files changed, 55 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 3078e23c91eb..5e970c7d3fd5 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -179,8 +179,9 @@ struct perf_counter_attr {
 				comm	       :  1, /* include comm data     */
 				freq           :  1, /* use freq, not period  */
 				inherit_stat   :  1, /* per task counts       */
+				enable_on_exec :  1, /* next exec enables     */
 
-				__reserved_1   : 52;
+				__reserved_1   : 51;
 
 	__u32			wakeup_events;	/* wakeup every n events */
 	__u32			__reserved_2;
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 66ab1e9d1294..d55a50da2347 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -1428,6 +1428,53 @@ void perf_counter_task_tick(struct task_struct *curr, int cpu)
 		perf_counter_task_sched_in(curr, cpu);
 }
 
+/*
+ * Enable all of a task's counters that have been marked enable-on-exec.
+ * This expects task == current.
+ */
+static void perf_counter_enable_on_exec(struct task_struct *task)
+{
+	struct perf_counter_context *ctx;
+	struct perf_counter *counter;
+	unsigned long flags;
+	int enabled = 0;
+
+	local_irq_save(flags);
+	ctx = task->perf_counter_ctxp;
+	if (!ctx || !ctx->nr_counters)
+		goto out;
+
+	__perf_counter_task_sched_out(ctx);
+
+	spin_lock(&ctx->lock);
+
+	list_for_each_entry(counter, &ctx->counter_list, list_entry) {
+		if (!counter->attr.enable_on_exec)
+			continue;
+		counter->attr.enable_on_exec = 0;
+		if (counter->state >= PERF_COUNTER_STATE_INACTIVE)
+			continue;
+		counter->state = PERF_COUNTER_STATE_INACTIVE;
+		counter->tstamp_enabled =
+			ctx->time - counter->total_time_enabled;
+		enabled = 1;
+	}
+
+	/*
+	 * Unclone this context if we enabled any counter.
+	 */
+	if (enabled && ctx->parent_ctx) {
+		put_ctx(ctx->parent_ctx);
+		ctx->parent_ctx = NULL;
+	}
+
+	spin_unlock(&ctx->lock);
+
+	perf_counter_task_sched_in(task, smp_processor_id());
+ out:
+	local_irq_restore(flags);
+}
+
 /*
  * Cross CPU call to read the hardware counter
  */
@@ -2949,6 +2996,9 @@ void perf_counter_comm(struct task_struct *task)
 {
 	struct perf_comm_event comm_event;
 
+	if (task->perf_counter_ctxp)
+		perf_counter_enable_on_exec(task);
+
 	if (!atomic_read(&nr_comm_counters))
 		return;
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 201ef2367dcb..2e03524a1de0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -116,8 +116,9 @@ static void create_perf_stat_counter(int counter, int pid)
 					fd[cpu][counter], strerror(errno));
 		}
 	} else {
-		attr->inherit	= inherit;
-		attr->disabled	= 1;
+		attr->inherit	     = inherit;
+		attr->disabled	     = 1;
+		attr->enable_on_exec = 1;
 
 		fd[0][counter] = sys_perf_counter_open(attr, pid, -1, -1, 0);
 		if (fd[0][counter] < 0 && verbose)
@@ -262,7 +263,6 @@ static int run_perf_stat(int argc, const char **argv)
 	 * Enable counters and exec the command:
 	 */
 	t0 = rdclock();
-	prctl(PR_TASK_PERF_COUNTERS_ENABLE);
 
 	close(go_pipe[1]);
 	wait(&status);
-- 
cgit v1.2.3


From e0a43ddcc08c34dbd666d93600fd23914505f4aa Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Tue, 30 Jun 2009 20:12:23 +0200
Subject: fuse: allow umask processing in userspace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch lets filesystems handle masking the file mode on creation.
This is needed if filesystem is using ACLs.

 - The CREATE, MKDIR and MKNOD requests are extended with a "umask"
   parameter.

 - A new FUSE_DONT_MASK flag is added to the INIT request/reply.  With
   this the filesystem may request that the create mode is not masked.

CC: Jean-Pierre André <jean-pierre.andre@wanadoo.fr>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
---
 fs/fuse/dir.c        | 20 +++++++++++++++++---
 fs/fuse/fuse_i.h     |  3 +++
 fs/fuse/inode.c      |  9 ++++++++-
 include/linux/fuse.h | 20 ++++++++++++++++++--
 4 files changed, 46 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b3089a083d30..6b700734e519 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -375,7 +375,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
 	struct fuse_conn *fc = get_fuse_conn(dir);
 	struct fuse_req *req;
 	struct fuse_req *forget_req;
-	struct fuse_open_in inarg;
+	struct fuse_create_in inarg;
 	struct fuse_open_out outopen;
 	struct fuse_entry_out outentry;
 	struct fuse_file *ff;
@@ -399,15 +399,20 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode,
 	if (!ff)
 		goto out_put_request;
 
+	if (!fc->dont_mask)
+		mode &= ~current_umask();
+
 	flags &= ~O_NOCTTY;
 	memset(&inarg, 0, sizeof(inarg));
 	memset(&outentry, 0, sizeof(outentry));
 	inarg.flags = flags;
 	inarg.mode = mode;
+	inarg.umask = current_umask();
 	req->in.h.opcode = FUSE_CREATE;
 	req->in.h.nodeid = get_node_id(dir);
 	req->in.numargs = 2;
-	req->in.args[0].size = sizeof(inarg);
+	req->in.args[0].size = fc->minor < 12 ? sizeof(struct fuse_open_in) :
+						sizeof(inarg);
 	req->in.args[0].value = &inarg;
 	req->in.args[1].size = entry->d_name.len + 1;
 	req->in.args[1].value = entry->d_name.name;
@@ -546,12 +551,17 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, int mode,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	if (!fc->dont_mask)
+		mode &= ~current_umask();
+
 	memset(&inarg, 0, sizeof(inarg));
 	inarg.mode = mode;
 	inarg.rdev = new_encode_dev(rdev);
+	inarg.umask = current_umask();
 	req->in.h.opcode = FUSE_MKNOD;
 	req->in.numargs = 2;
-	req->in.args[0].size = sizeof(inarg);
+	req->in.args[0].size = fc->minor < 12 ? FUSE_COMPAT_MKNOD_IN_SIZE :
+						sizeof(inarg);
 	req->in.args[0].value = &inarg;
 	req->in.args[1].size = entry->d_name.len + 1;
 	req->in.args[1].value = entry->d_name.name;
@@ -578,8 +588,12 @@ static int fuse_mkdir(struct inode *dir, struct dentry *entry, int mode)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	if (!fc->dont_mask)
+		mode &= ~current_umask();
+
 	memset(&inarg, 0, sizeof(inarg));
 	inarg.mode = mode;
+	inarg.umask = current_umask();
 	req->in.h.opcode = FUSE_MKDIR;
 	req->in.numargs = 2;
 	req->in.args[0].size = sizeof(inarg);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index aaf2f9ff970e..ede4f77b2d6c 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -446,6 +446,9 @@ struct fuse_conn {
 	/** Do multi-page cached writes */
 	unsigned big_writes:1;
 
+	/** Don't apply umask to creation modes */
+	unsigned dont_mask:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d8673ccf90b7..6cc501bd0187 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -725,6 +725,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 			}
 			if (arg->flags & FUSE_BIG_WRITES)
 				fc->big_writes = 1;
+			if (arg->flags & FUSE_DONT_MASK)
+				fc->dont_mask = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_CACHE_SIZE;
 			fc->no_lock = 1;
@@ -748,7 +750,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 	arg->minor = FUSE_KERNEL_MINOR_VERSION;
 	arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE;
 	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
-		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES;
+		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
@@ -864,6 +866,11 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto err_put_conn;
 
+	/* Handle umasking inside the fuse code */
+	if (sb->s_flags & MS_POSIXACL)
+		fc->dont_mask = 1;
+	sb->s_flags |= MS_POSIXACL;
+
 	fc->release = fuse_free_conn;
 	fc->flags = d.flags;
 	fc->user_id = d.user_id;
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index d41ed593f79f..e2b816a62488 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -25,6 +25,9 @@
  *  - add IOCTL message
  *  - add unsolicited notification support
  *  - add POLL message and NOTIFY_POLL notification
+ *
+ * 7.12
+ *  - add umask flag to input argument of open, mknod and mkdir
  */
 
 #ifndef _LINUX_FUSE_H
@@ -36,7 +39,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 11
+#define FUSE_KERNEL_MINOR_VERSION 12
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -112,6 +115,7 @@ struct fuse_file_lock {
  * INIT request/reply flags
  *
  * FUSE_EXPORT_SUPPORT: filesystem handles lookups of "." and ".."
+ * FUSE_DONT_MASK: don't apply umask to file mode on create operations
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -119,6 +123,7 @@ struct fuse_file_lock {
 #define FUSE_ATOMIC_O_TRUNC	(1 << 3)
 #define FUSE_EXPORT_SUPPORT	(1 << 4)
 #define FUSE_BIG_WRITES		(1 << 5)
+#define FUSE_DONT_MASK		(1 << 6)
 
 /**
  * CUSE INIT request/reply flags
@@ -262,14 +267,18 @@ struct fuse_attr_out {
 	struct fuse_attr attr;
 };
 
+#define FUSE_COMPAT_MKNOD_IN_SIZE 8
+
 struct fuse_mknod_in {
 	__u32	mode;
 	__u32	rdev;
+	__u32	umask;
+	__u32	padding;
 };
 
 struct fuse_mkdir_in {
 	__u32	mode;
-	__u32	padding;
+	__u32	umask;
 };
 
 struct fuse_rename_in {
@@ -300,8 +309,15 @@ struct fuse_setattr_in {
 };
 
 struct fuse_open_in {
+	__u32	flags;
+	__u32	unused;
+};
+
+struct fuse_create_in {
 	__u32	flags;
 	__u32	mode;
+	__u32	umask;
+	__u32	padding;
 };
 
 struct fuse_open_out {
-- 
cgit v1.2.3


From 3b463ae0c6264f70e5d4c0a9c46af20fed43c96e Mon Sep 17 00:00:00 2001
From: John Muir <muirj@nortel.com>
Date: Sun, 31 May 2009 11:13:57 -0400
Subject: fuse: invalidation reverse calls

Add notification messages that allow the filesystem to invalidate VFS
caches.

Two notifications are added:

 1) inode invalidation

   - invalidate cached attributes
   - invalidate a range of pages in the page cache (this is optional)

 2) dentry invalidation

   - try to invalidate a subtree in the dentry cache

Care must be taken while accessing the 'struct super_block' for the
mount, as it can go away while an invalidation is in progress.  To
prevent this, introduce a rw-semaphore, that is taken for read during
the invalidation and taken for write in the ->kill_sb callback.

Cc: Csaba Henk <csaba@gluster.com>
Cc: Anand Avati <avati@zresearch.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
---
 fs/fuse/dev.c        | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/fuse/dir.c        | 37 ++++++++++++++++++++++++
 fs/fuse/fuse_i.h     | 24 ++++++++++++++++
 fs/fuse/inode.c      | 59 ++++++++++++++++++++++++++++++++++++--
 include/linux/fuse.h | 16 +++++++++++
 5 files changed, 214 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 8a11a8c67c42..f58ecbc416c8 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -849,6 +849,81 @@ err:
 	return err;
 }
 
+static int fuse_notify_inval_inode(struct fuse_conn *fc, unsigned int size,
+				   struct fuse_copy_state *cs)
+{
+	struct fuse_notify_inval_inode_out outarg;
+	int err = -EINVAL;
+
+	if (size != sizeof(outarg))
+		goto err;
+
+	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
+	if (err)
+		goto err;
+	fuse_copy_finish(cs);
+
+	down_read(&fc->killsb);
+	err = -ENOENT;
+	if (!fc->sb)
+		goto err_unlock;
+
+	err = fuse_reverse_inval_inode(fc->sb, outarg.ino,
+				       outarg.off, outarg.len);
+
+err_unlock:
+	up_read(&fc->killsb);
+	return err;
+
+err:
+	fuse_copy_finish(cs);
+	return err;
+}
+
+static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size,
+				   struct fuse_copy_state *cs)
+{
+	struct fuse_notify_inval_entry_out outarg;
+	int err = -EINVAL;
+	char buf[FUSE_NAME_MAX+1];
+	struct qstr name;
+
+	if (size < sizeof(outarg))
+		goto err;
+
+	err = fuse_copy_one(cs, &outarg, sizeof(outarg));
+	if (err)
+		goto err;
+
+	err = -ENAMETOOLONG;
+	if (outarg.namelen > FUSE_NAME_MAX)
+		goto err;
+
+	name.name = buf;
+	name.len = outarg.namelen;
+	err = fuse_copy_one(cs, buf, outarg.namelen + 1);
+	if (err)
+		goto err;
+	fuse_copy_finish(cs);
+	buf[outarg.namelen] = 0;
+	name.hash = full_name_hash(name.name, name.len);
+
+	down_read(&fc->killsb);
+	err = -ENOENT;
+	if (!fc->sb)
+		goto err_unlock;
+
+	err = fuse_reverse_inval_entry(fc->sb, outarg.parent, &name);
+
+err_unlock:
+	up_read(&fc->killsb);
+	return err;
+
+err:
+	fuse_copy_finish(cs);
+	return err;
+}
+
 static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 		       unsigned int size, struct fuse_copy_state *cs)
 {
@@ -856,6 +931,12 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
 	case FUSE_NOTIFY_POLL:
 		return fuse_notify_poll(fc, size, cs);
 
+	case FUSE_NOTIFY_INVAL_INODE:
+		return fuse_notify_inval_inode(fc, size, cs);
+
+	case FUSE_NOTIFY_INVAL_ENTRY:
+		return fuse_notify_inval_entry(fc, size, cs);
+
 	default:
 		fuse_copy_finish(cs);
 		return -EINVAL;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 6b700734e519..e703654e7f40 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -859,6 +859,43 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat,
 	return err;
 }
 
+int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
+			     struct qstr *name)
+{
+	int err = -ENOTDIR;
+	struct inode *parent;
+	struct dentry *dir;
+	struct dentry *entry;
+
+	parent = ilookup5(sb, parent_nodeid, fuse_inode_eq, &parent_nodeid);
+	if (!parent)
+		return -ENOENT;
+
+	mutex_lock(&parent->i_mutex);
+	if (!S_ISDIR(parent->i_mode))
+		goto unlock;
+
+	err = -ENOENT;
+	dir = d_find_alias(parent);
+	if (!dir)
+		goto unlock;
+
+	entry = d_lookup(dir, name);
+	dput(dir);
+	if (!entry)
+		goto unlock;
+
+	fuse_invalidate_attr(parent);
+	fuse_invalidate_entry(entry);
+	dput(entry);
+	err = 0;
+
+ unlock:
+	mutex_unlock(&parent->i_mutex);
+	iput(parent);
+	return err;
+}
+
 /*
  * Calling into a user-controlled filesystem gives the filesystem
  * daemon ptrace-like capabilities over the requester process.  This
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ede4f77b2d6c..52b641fc0faf 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -484,6 +484,12 @@ struct fuse_conn {
 
 	/** Called on final put */
 	void (*release)(struct fuse_conn *);
+
+	/** Super block for this connection. */
+	struct super_block *sb;
+
+	/** Read/write semaphore to hold when accessing sb. */
+	struct rw_semaphore killsb;
 };
 
 static inline struct fuse_conn *get_fuse_conn_super(struct super_block *sb)
@@ -511,6 +517,11 @@ extern const struct file_operations fuse_dev_operations;
 
 extern const struct dentry_operations fuse_dentry_operations;
 
+/**
+ * Inode to nodeid comparison.
+ */
+int fuse_inode_eq(struct inode *inode, void *_nodeidp);
+
 /**
  * Get a filled in inode
  */
@@ -711,6 +722,19 @@ void fuse_release_nowrite(struct inode *inode);
 
 u64 fuse_get_attr_version(struct fuse_conn *fc);
 
+/**
+ * File-system tells the kernel to invalidate cache for the given node id.
+ */
+int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
+			     loff_t offset, loff_t len);
+
+/**
+ * File-system tells the kernel to invalidate parent attributes and
+ * the dentry matching parent/name.
+ */
+int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid,
+			     struct qstr *name);
+
 int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 		 bool isdir);
 ssize_t fuse_direct_io(struct file *file, const char __user *buf,
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 6cc501bd0187..f91ccc4a189d 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -206,7 +206,7 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
 		BUG();
 }
 
-static int fuse_inode_eq(struct inode *inode, void *_nodeidp)
+int fuse_inode_eq(struct inode *inode, void *_nodeidp)
 {
 	u64 nodeid = *(u64 *) _nodeidp;
 	if (get_node_id(inode) == nodeid)
@@ -257,6 +257,31 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 	return inode;
 }
 
+int fuse_reverse_inval_inode(struct super_block *sb, u64 nodeid,
+			     loff_t offset, loff_t len)
+{
+	struct inode *inode;
+	pgoff_t pg_start;
+	pgoff_t pg_end;
+
+	inode = ilookup5(sb, nodeid, fuse_inode_eq, &nodeid);
+	if (!inode)
+		return -ENOENT;
+
+	fuse_invalidate_attr(inode);
+	if (offset >= 0) {
+		pg_start = offset >> PAGE_CACHE_SHIFT;
+		if (len <= 0)
+			pg_end = -1;
+		else
+			pg_end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+		invalidate_inode_pages2_range(inode->i_mapping,
+					      pg_start, pg_end);
+	}
+	iput(inode);
+	return 0;
+}
+
 static void fuse_umount_begin(struct super_block *sb)
 {
 	fuse_abort_conn(get_fuse_conn_super(sb));
@@ -480,6 +505,7 @@ void fuse_conn_init(struct fuse_conn *fc)
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);
 	mutex_init(&fc->inst_mutex);
+	init_rwsem(&fc->killsb);
 	atomic_set(&fc->count, 1);
 	init_waitqueue_head(&fc->waitq);
 	init_waitqueue_head(&fc->blocked_waitq);
@@ -862,6 +888,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	fuse_conn_init(fc);
 
 	fc->dev = sb->s_dev;
+	fc->sb = sb;
 	err = fuse_bdi_init(fc, sb);
 	if (err)
 		goto err_put_conn;
@@ -948,12 +975,25 @@ static int fuse_get_sb(struct file_system_type *fs_type,
 	return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super, mnt);
 }
 
+static void fuse_kill_sb_anon(struct super_block *sb)
+{
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+	if (fc) {
+		down_write(&fc->killsb);
+		fc->sb = NULL;
+		up_write(&fc->killsb);
+	}
+
+	kill_anon_super(sb);
+}
+
 static struct file_system_type fuse_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "fuse",
 	.fs_flags	= FS_HAS_SUBTYPE,
 	.get_sb		= fuse_get_sb,
-	.kill_sb	= kill_anon_super,
+	.kill_sb	= fuse_kill_sb_anon,
 };
 
 #ifdef CONFIG_BLOCK
@@ -965,11 +1005,24 @@ static int fuse_get_sb_blk(struct file_system_type *fs_type,
 			   mnt);
 }
 
+static void fuse_kill_sb_blk(struct super_block *sb)
+{
+	struct fuse_conn *fc = get_fuse_conn_super(sb);
+
+	if (fc) {
+		down_write(&fc->killsb);
+		fc->sb = NULL;
+		up_write(&fc->killsb);
+	}
+
+	kill_block_super(sb);
+}
+
 static struct file_system_type fuseblk_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "fuseblk",
 	.get_sb		= fuse_get_sb_blk,
-	.kill_sb	= kill_block_super,
+	.kill_sb	= fuse_kill_sb_blk,
 	.fs_flags	= FS_REQUIRES_DEV | FS_HAS_SUBTYPE,
 };
 
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index e2b816a62488..cf593bf9fd32 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -28,6 +28,8 @@
  *
  * 7.12
  *  - add umask flag to input argument of open, mknod and mkdir
+ *  - add notification messages for invalidation of inodes and
+ *    directory entries
  */
 
 #ifndef _LINUX_FUSE_H
@@ -229,6 +231,8 @@ enum fuse_opcode {
 
 enum fuse_notify_code {
 	FUSE_NOTIFY_POLL   = 1,
+	FUSE_NOTIFY_INVAL_INODE = 2,
+	FUSE_NOTIFY_INVAL_ENTRY = 3,
 	FUSE_NOTIFY_CODE_MAX,
 };
 
@@ -524,4 +528,16 @@ struct fuse_dirent {
 #define FUSE_DIRENT_SIZE(d) \
 	FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen)
 
+struct fuse_notify_inval_inode_out {
+	__u64	ino;
+	__s64	off;
+	__s64	len;
+};
+
+struct fuse_notify_inval_entry_out {
+	__u64	parent;
+	__u32	namelen;
+	__u32	padding;
+};
+
 #endif /* _LINUX_FUSE_H */
-- 
cgit v1.2.3


From 133890103b9de08904f909995973e4b5c08a780e Mon Sep 17 00:00:00 2001
From: Davide Libenzi <davidel@xmailserver.org>
Date: Tue, 30 Jun 2009 11:41:11 -0700
Subject: eventfd: revised interface and cleanups

Change the eventfd interface to de-couple the eventfd memory context, from
the file pointer instance.

Without such change, there is no clean way to racely free handle the
POLLHUP event sent when the last instance of the file* goes away.  Also,
now the internal eventfd APIs are using the eventfd context instead of the
file*.

This patch is required by KVM's IRQfd code, which is still under
development.

Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Gregory Haskins <ghaskins@novell.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Cc: Avi Kivity <avi@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/lguest/lg.h          |   2 +-
 drivers/lguest/lguest_user.c |   4 +-
 fs/aio.c                     |  24 +++------
 fs/eventfd.c                 | 122 ++++++++++++++++++++++++++++++++++++++-----
 include/linux/aio.h          |   4 +-
 include/linux/eventfd.h      |  35 ++++++++++---
 6 files changed, 149 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h
index d4e8979735cb..9c3138265f8e 100644
--- a/drivers/lguest/lg.h
+++ b/drivers/lguest/lg.h
@@ -82,7 +82,7 @@ struct lg_cpu {
 
 struct lg_eventfd {
 	unsigned long addr;
-	struct file *event;
+	struct eventfd_ctx *event;
 };
 
 struct lg_eventfd_map {
diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c
index 32e297121058..9f9a2953b383 100644
--- a/drivers/lguest/lguest_user.c
+++ b/drivers/lguest/lguest_user.c
@@ -50,7 +50,7 @@ static int add_eventfd(struct lguest *lg, unsigned long addr, int fd)
 
 	/* Now append new entry. */
 	new->map[new->num].addr = addr;
-	new->map[new->num].event = eventfd_fget(fd);
+	new->map[new->num].event = eventfd_ctx_fdget(fd);
 	if (IS_ERR(new->map[new->num].event)) {
 		kfree(new);
 		return PTR_ERR(new->map[new->num].event);
@@ -357,7 +357,7 @@ static int close(struct inode *inode, struct file *file)
 
 	/* Release any eventfds they registered. */
 	for (i = 0; i < lg->eventfds->num; i++)
-		fput(lg->eventfds->map[i].event);
+		eventfd_ctx_put(lg->eventfds->map[i].event);
 	kfree(lg->eventfds);
 
 	/* If lg->dead doesn't contain an error code it will be NULL or a
diff --git a/fs/aio.c b/fs/aio.c
index 76da12537956..d065b2c3273e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -485,6 +485,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
 {
 	assert_spin_locked(&ctx->ctx_lock);
 
+	if (req->ki_eventfd != NULL)
+		eventfd_ctx_put(req->ki_eventfd);
 	if (req->ki_dtor)
 		req->ki_dtor(req);
 	if (req->ki_iovec != &req->ki_inline_vec)
@@ -509,8 +511,6 @@ static void aio_fput_routine(struct work_struct *data)
 		/* Complete the fput(s) */
 		if (req->ki_filp != NULL)
 			__fput(req->ki_filp);
-		if (req->ki_eventfd != NULL)
-			__fput(req->ki_eventfd);
 
 		/* Link the iocb into the context's free list */
 		spin_lock_irq(&ctx->ctx_lock);
@@ -528,8 +528,6 @@ static void aio_fput_routine(struct work_struct *data)
  */
 static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 {
-	int schedule_putreq = 0;
-
 	dprintk(KERN_DEBUG "aio_put(%p): f_count=%ld\n",
 		req, atomic_long_read(&req->ki_filp->f_count));
 
@@ -549,24 +547,16 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 	 * we would not be holding the last reference to the file*, so
 	 * this function will be executed w/out any aio kthread wakeup.
 	 */
-	if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count)))
-		schedule_putreq++;
-	else
-		req->ki_filp = NULL;
-	if (req->ki_eventfd != NULL) {
-		if (unlikely(atomic_long_dec_and_test(&req->ki_eventfd->f_count)))
-			schedule_putreq++;
-		else
-			req->ki_eventfd = NULL;
-	}
-	if (unlikely(schedule_putreq)) {
+	if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) {
 		get_ioctx(ctx);
 		spin_lock(&fput_lock);
 		list_add(&req->ki_list, &fput_head);
 		spin_unlock(&fput_lock);
 		queue_work(aio_wq, &fput_work);
-	} else
+	} else {
+		req->ki_filp = NULL;
 		really_put_req(ctx, req);
+	}
 	return 1;
 }
 
@@ -1622,7 +1612,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		 * an eventfd() fd, and will be signaled for each completed
 		 * event using the eventfd_signal() function.
 		 */
-		req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
+		req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
 		if (IS_ERR(req->ki_eventfd)) {
 			ret = PTR_ERR(req->ki_eventfd);
 			req->ki_eventfd = NULL;
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 3f0e1974abdc..31d12de83a2a 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -14,35 +14,44 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/anon_inodes.h>
-#include <linux/eventfd.h>
 #include <linux/syscalls.h>
 #include <linux/module.h>
+#include <linux/kref.h>
+#include <linux/eventfd.h>
 
 struct eventfd_ctx {
+	struct kref kref;
 	wait_queue_head_t wqh;
 	/*
 	 * Every time that a write(2) is performed on an eventfd, the
 	 * value of the __u64 being written is added to "count" and a
 	 * wakeup is performed on "wqh". A read(2) will return the "count"
 	 * value to userspace, and will reset "count" to zero. The kernel
-	 * size eventfd_signal() also, adds to the "count" counter and
+	 * side eventfd_signal() also, adds to the "count" counter and
 	 * issue a wakeup.
 	 */
 	__u64 count;
 	unsigned int flags;
 };
 
-/*
- * Adds "n" to the eventfd counter "count". Returns "n" in case of
- * success, or a value lower then "n" in case of coutner overflow.
- * This function is supposed to be called by the kernel in paths
- * that do not allow sleeping. In this function we allow the counter
- * to reach the ULLONG_MAX value, and we signal this as overflow
- * condition by returining a POLLERR to poll(2).
+/**
+ * eventfd_signal - Adds @n to the eventfd counter.
+ * @ctx: [in] Pointer to the eventfd context.
+ * @n: [in] Value of the counter to be added to the eventfd internal counter.
+ *          The value cannot be negative.
+ *
+ * This function is supposed to be called by the kernel in paths that do not
+ * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX
+ * value, and we signal this as overflow condition by returining a POLLERR
+ * to poll(2).
+ *
+ * Returns @n in case of success, a non-negative number lower than @n in case
+ * of overflow, or the following error codes:
+ *
+ * -EINVAL    : The value of @n is negative.
  */
-int eventfd_signal(struct file *file, int n)
+int eventfd_signal(struct eventfd_ctx *ctx, int n)
 {
-	struct eventfd_ctx *ctx = file->private_data;
 	unsigned long flags;
 
 	if (n < 0)
@@ -59,9 +68,45 @@ int eventfd_signal(struct file *file, int n)
 }
 EXPORT_SYMBOL_GPL(eventfd_signal);
 
+static void eventfd_free(struct kref *kref)
+{
+	struct eventfd_ctx *ctx = container_of(kref, struct eventfd_ctx, kref);
+
+	kfree(ctx);
+}
+
+/**
+ * eventfd_ctx_get - Acquires a reference to the internal eventfd context.
+ * @ctx: [in] Pointer to the eventfd context.
+ *
+ * Returns: In case of success, returns a pointer to the eventfd context.
+ */
+struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx)
+{
+	kref_get(&ctx->kref);
+	return ctx;
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_get);
+
+/**
+ * eventfd_ctx_put - Releases a reference to the internal eventfd context.
+ * @ctx: [in] Pointer to eventfd context.
+ *
+ * The eventfd context reference must have been previously acquired either
+ * with eventfd_ctx_get() or eventfd_ctx_fdget()).
+ */
+void eventfd_ctx_put(struct eventfd_ctx *ctx)
+{
+	kref_put(&ctx->kref, eventfd_free);
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_put);
+
 static int eventfd_release(struct inode *inode, struct file *file)
 {
-	kfree(file->private_data);
+	struct eventfd_ctx *ctx = file->private_data;
+
+	wake_up_poll(&ctx->wqh, POLLHUP);
+	eventfd_ctx_put(ctx);
 	return 0;
 }
 
@@ -185,6 +230,16 @@ static const struct file_operations eventfd_fops = {
 	.write		= eventfd_write,
 };
 
+/**
+ * eventfd_fget - Acquire a reference of an eventfd file descriptor.
+ * @fd: [in] Eventfd file descriptor.
+ *
+ * Returns a pointer to the eventfd file structure in case of success, or the
+ * following error pointer:
+ *
+ * -EBADF    : Invalid @fd file descriptor.
+ * -EINVAL   : The @fd file descriptor is not an eventfd file.
+ */
 struct file *eventfd_fget(int fd)
 {
 	struct file *file;
@@ -201,6 +256,48 @@ struct file *eventfd_fget(int fd)
 }
 EXPORT_SYMBOL_GPL(eventfd_fget);
 
+/**
+ * eventfd_ctx_fdget - Acquires a reference to the internal eventfd context.
+ * @fd: [in] Eventfd file descriptor.
+ *
+ * Returns a pointer to the internal eventfd context, otherwise the error
+ * pointers returned by the following functions:
+ *
+ * eventfd_fget
+ */
+struct eventfd_ctx *eventfd_ctx_fdget(int fd)
+{
+	struct file *file;
+	struct eventfd_ctx *ctx;
+
+	file = eventfd_fget(fd);
+	if (IS_ERR(file))
+		return (struct eventfd_ctx *) file;
+	ctx = eventfd_ctx_get(file->private_data);
+	fput(file);
+
+	return ctx;
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_fdget);
+
+/**
+ * eventfd_ctx_fileget - Acquires a reference to the internal eventfd context.
+ * @file: [in] Eventfd file pointer.
+ *
+ * Returns a pointer to the internal eventfd context, otherwise the error
+ * pointer:
+ *
+ * -EINVAL   : The @fd file descriptor is not an eventfd file.
+ */
+struct eventfd_ctx *eventfd_ctx_fileget(struct file *file)
+{
+	if (file->f_op != &eventfd_fops)
+		return ERR_PTR(-EINVAL);
+
+	return eventfd_ctx_get(file->private_data);
+}
+EXPORT_SYMBOL_GPL(eventfd_ctx_fileget);
+
 SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
 {
 	int fd;
@@ -217,6 +314,7 @@ SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
 	if (!ctx)
 		return -ENOMEM;
 
+	kref_init(&ctx->kref);
 	init_waitqueue_head(&ctx->wqh);
 	ctx->count = count;
 	ctx->flags = flags;
diff --git a/include/linux/aio.h b/include/linux/aio.h
index b16a957030f8..47f7d932a01d 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -121,9 +121,9 @@ struct kiocb {
 
 	/*
 	 * If the aio_resfd field of the userspace iocb is not zero,
-	 * this is the underlying file* to deliver event to.
+	 * this is the underlying eventfd context to deliver events to.
 	 */
-	struct file		*ki_eventfd;
+	struct eventfd_ctx	*ki_eventfd;
 };
 
 #define is_sync_kiocb(iocb)	((iocb)->ki_key == KIOCB_SYNC_KEY)
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index f45a8ae5f828..3b85ba6479f4 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -8,10 +8,8 @@
 #ifndef _LINUX_EVENTFD_H
 #define _LINUX_EVENTFD_H
 
-#ifdef CONFIG_EVENTFD
-
-/* For O_CLOEXEC and O_NONBLOCK */
 #include <linux/fcntl.h>
+#include <linux/file.h>
 
 /*
  * CAREFUL: Check include/asm-generic/fcntl.h when defining
@@ -27,16 +25,37 @@
 #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
 #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE)
 
+#ifdef CONFIG_EVENTFD
+
+struct eventfd_ctx *eventfd_ctx_get(struct eventfd_ctx *ctx);
+void eventfd_ctx_put(struct eventfd_ctx *ctx);
 struct file *eventfd_fget(int fd);
-int eventfd_signal(struct file *file, int n);
+struct eventfd_ctx *eventfd_ctx_fdget(int fd);
+struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
+int eventfd_signal(struct eventfd_ctx *ctx, int n);
 
 #else /* CONFIG_EVENTFD */
 
-#define eventfd_fget(fd) ERR_PTR(-ENOSYS)
-static inline int eventfd_signal(struct file *file, int n)
-{ return 0; }
+/*
+ * Ugly ugly ugly error layer to support modules that uses eventfd but
+ * pretend to work in !CONFIG_EVENTFD configurations. Namely, AIO.
+ */
+static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline int eventfd_signal(struct eventfd_ctx *ctx, int n)
+{
+	return -ENOSYS;
+}
+
+static inline void eventfd_ctx_put(struct eventfd_ctx *ctx)
+{
+
+}
 
-#endif /* CONFIG_EVENTFD */
+#endif
 
 #endif /* _LINUX_EVENTFD_H */
 
-- 
cgit v1.2.3


From 2a2325e6e8a3782795fb520220c36fd805775972 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 30 Jun 2009 11:41:13 -0700
Subject: gcov: fix __ctors_start alignment

The ctors section for each object file is eight byte aligned (on 64 bit).
However the __ctors_start symbol starts at an arbitrary address dependent
on the size of the previous sections.

Therefore the linker may add some zeroes after __ctors_start to make sure
the ctors contents are properly aligned.  However the extra zeroes at the
beginning aren't expected by the code.  When walking the functions
pointers contained in there and extra zeroes are added this may result in
random jumps.  So make sure that the __ctors_start symbol is always
aligned as well.

Fixes this crash on an allyesconfig on s390:

[    0.582482] Kernel BUG at 0000000000000012 [verbose debug info unavailable]
[    0.582489] illegal operation: 0001 [#1] SMP DEBUG_PAGEALLOC
[    0.582496] Modules linked in:
[    0.582501] CPU: 0 Tainted: G        W  2.6.31-rc1-dirty #273
[    0.582506] Process swapper (pid: 1, task: 000000003f218000, ksp: 000000003f2238e8)
[    0.582510] Krnl PSW : 0704200180000000 0000000000000012 (0x12)
[    0.582518]            R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:0 CC:2 PM:0 EA:3
[    0.582524] Krnl GPRS: 0000000000036727 0000000000000010 0000000000000001 0000000000000001
[    0.582529]            00000000001dfefa 0000000000000000 0000000000000000 0000000000000040
[    0.582534]            0000000001fff0f0 0000000001790628 0000000002296048 0000000002296048
[    0.582540]            00000000020c438e 0000000001786000 0000000002014a66 000000003f223e60
[    0.582553] Krnl Code:>0000000000000012: 0000                unknown
[    0.582559]            0000000000000014: 0000                unknown
[    0.582564]            0000000000000016: 0000                unknown
[    0.582570]            0000000000000018: 0000                unknown
[    0.582575]            000000000000001a: 0000                unknown
[    0.582580]            000000000000001c: 0000                unknown
[    0.582585]            000000000000001e: 0000                unknown
[    0.582591]            0000000000000020: 0000                unknown
[    0.582596] Call Trace:
[    0.582599] ([<0000000002014a46>] kernel_init+0x622/0x7a0)
[    0.582607]  [<0000000000113e22>] kernel_thread_starter+0x6/0xc
[    0.582615]  [<0000000000113e1c>] kernel_thread_starter+0x0/0xc
[    0.582621] INFO: lockdep is turned off.
[    0.582624] Last Breaking-Event-Address:
[    0.582627]  [<0000000002014a64>] kernel_init+0x640/0x7a0

Cc: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/vmlinux.lds.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 92b73b6140ff..dccdbed05848 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -441,7 +441,8 @@
 	}
 
 #ifdef CONFIG_CONSTRUCTORS
-#define KERNEL_CTORS()	VMLINUX_SYMBOL(__ctors_start) = .; \
+#define KERNEL_CTORS()	. = ALIGN(8);			   \
+			VMLINUX_SYMBOL(__ctors_start) = .; \
 			*(.ctors)			   \
 			VMLINUX_SYMBOL(__ctors_end) = .;
 #else
-- 
cgit v1.2.3


From b01e8dc34379f4ba2f454390e340a025edbaaa7e Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 30 Jun 2009 11:41:18 -0700
Subject: alpha: fix percpu build breakage

alpha percpu access requires custom SHIFT_PERCPU_PTR() definition for
modules to work around addressing range limitation.  This is done via
generating inline assembly using C preprocessing which forces the
assembler to generate external reference.  This happens behind the
compiler's back and makes the compiler think that static percpu variables
in modules are unused.

This used to be worked around by using __unused attribute for percpu
variables which prevent the compiler from omitting the variable; however,
recent declare/definition attribute unification change broke this as
__used can't be used for declaration.  Also, in the process,
PER_CPU_ATTRIBUTES definition in alpha percpu.h got broken.

This patch adds PER_CPU_DEF_ATTRIBUTES which is only used for definitions
and make alpha use it to add __used for percpu variables in modules.  This
also fixes the PER_CPU_ATTRIBUTES double definition bug.

Signed-off-by: Tejun Heo <tj@kernel.org>
Tested-by: maximilian attems <max@stro.at>
Acked-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Richard Henderson <rth@twiddle.net>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/percpu.h | 6 +++---
 include/asm-generic/percpu.h    | 4 ++++
 include/linux/percpu-defs.h     | 3 ++-
 3 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/percpu.h b/arch/alpha/include/asm/percpu.h
index 06c5c7a4afd3..b663f1f10b6a 100644
--- a/arch/alpha/include/asm/percpu.h
+++ b/arch/alpha/include/asm/percpu.h
@@ -30,7 +30,7 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 
 #ifndef MODULE
 #define SHIFT_PERCPU_PTR(var, offset) RELOC_HIDE(&per_cpu_var(var), (offset))
-#define PER_CPU_ATTRIBUTES
+#define PER_CPU_DEF_ATTRIBUTES
 #else
 /*
  * To calculate addresses of locally defined variables, GCC uses 32-bit
@@ -49,7 +49,7 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 		: "=&r"(__ptr), "=&r"(tmp_gp));		\
 	(typeof(&per_cpu_var(var)))(__ptr + (offset)); })
 
-#define PER_CPU_ATTRIBUTES	__used
+#define PER_CPU_DEF_ATTRIBUTES	__used
 
 #endif /* MODULE */
 
@@ -71,7 +71,7 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #define __get_cpu_var(var)		per_cpu_var(var)
 #define __raw_get_cpu_var(var)		per_cpu_var(var)
 
-#define PER_CPU_ATTRIBUTES
+#define PER_CPU_DEF_ATTRIBUTES
 
 #endif /* SMP */
 
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index d7d50d7ee51e..aa00800adacc 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -97,4 +97,8 @@ extern void setup_per_cpu_areas(void);
 #define PER_CPU_ATTRIBUTES
 #endif
 
+#ifndef PER_CPU_DEF_ATTRIBUTES
+#define PER_CPU_DEF_ATTRIBUTES
+#endif
+
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 8f921d74f49f..68438e18fff4 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -24,7 +24,8 @@
 
 #define DEFINE_PER_CPU_SECTION(type, name, section)			\
 	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+	PER_CPU_ATTRIBUTES PER_CPU_DEF_ATTRIBUTES			\
+	__typeof__(type) per_cpu__##name
 
 /*
  * Variant on the per-CPU variable declaration/definition theme used for
-- 
cgit v1.2.3


From c4285b47b0514e2103584ee829246f813e7ae323 Mon Sep 17 00:00:00 2001
From: Michael Buesch <mb@bu3sch.de>
Date: Tue, 30 Jun 2009 11:41:21 -0700
Subject: parport/serial: add support for NetMos 9901 Multi-IO card

Add support for the PCI-Express NetMos 9901 Multi-IO card.

0001:06:00.0 Serial controller [0700]: NetMos Technology Device [9710:9901] (prog-if 02 [16550])
        Subsystem: Device [a000:1000]
        Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
        Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
        Latency: 0, Cache Line Size: 64 bytes
        Interrupt: pin A routed to IRQ 65
        Region 0: I/O ports at 0030 [size=8]
        Region 1: Memory at 80105000 (32-bit, non-prefetchable) [size=4K]
        Region 4: Memory at 80104000 (32-bit, non-prefetchable) [size=4K]
        Capabilities: <access denied>
        Kernel driver in use: serial
        Kernel modules: 8250_pci

0001:06:00.1 Serial controller [0700]: NetMos Technology Device [9710:9901] (prog-if 02 [16550])
        Subsystem: Device [a000:1000]
        Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
        Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
        Latency: 0, Cache Line Size: 64 bytes
        Interrupt: pin B routed to IRQ 65
        Region 0: I/O ports at 0020 [size=8]
        Region 1: Memory at 80103000 (32-bit, non-prefetchable) [size=4K]
        Region 4: Memory at 80102000 (32-bit, non-prefetchable) [size=4K]
        Capabilities: <access denied>
        Kernel driver in use: serial
        Kernel modules: 8250_pci

0001:06:00.2 Parallel controller [0701]: NetMos Technology Device [9710:9901] (prog-if 03 [IEEE1284])
        Subsystem: Device [a000:2000]
        Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
        Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
        Latency: 0, Cache Line Size: 64 bytes
        Interrupt: pin C routed to IRQ 65
        Region 0: I/O ports at 0010 [size=8]
        Region 1: I/O ports at <unassigned>
        Region 2: Memory at 80101000 (32-bit, non-prefetchable) [size=4K]
        Region 4: Memory at 80100000 (32-bit, non-prefetchable) [size=4K]
        Capabilities: <access denied>
        Kernel driver in use: parport_pc
        Kernel modules: parport_pc

[   16.760181] PCI parallel port detected: 416c:0100, I/O at 0x812010(0x0), IRQ 65
[   16.760225] parport0: PC-style at 0x812010, irq 65 [PCSPP,TRISTATE,EPP]
[   16.851842] serial 0001:06:00.0: enabling device (0004 -> 0007)
[   16.883776] 0001:06:00.0: ttyS0 at I/O 0x812030 (irq = 65) is a ST16650V2
[   16.893832] serial 0001:06:00.1: enabling device (0004 -> 0007)
[   16.926537] 0001:06:00.1: ttyS1 at I/O 0x812020 (irq = 65) is a ST16650V2

Signed-off-by: Michael Buesch <mb@bu3sch.de>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/parport/parport_pc.c | 5 ++++-
 drivers/serial/8250_pci.c    | 6 ++++++
 include/linux/pci_ids.h      | 1 +
 3 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 1032d5fdbd42..2597145a066e 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -2907,6 +2907,7 @@ enum parport_pc_pci_cards {
 	netmos_9755,
 	netmos_9805,
 	netmos_9815,
+	netmos_9901,
 	quatech_sppxp100,
 };
 
@@ -2987,7 +2988,7 @@ static struct parport_pc_pci {
 	/* netmos_9755 */               { 2, { { 0, 1 }, { 2, 3 },} },
 	/* netmos_9805 */               { 1, { { 0, -1 }, } },
 	/* netmos_9815 */               { 2, { { 0, -1 }, { 2, -1 }, } },
-
+	/* netmos_9901 */               { 1, { { 0, -1 }, } },
 	/* quatech_sppxp100 */		{ 1, { { 0, 1 }, } },
 };
 
@@ -3089,6 +3090,8 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9805 },
 	{ PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9815,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9815 },
+	{ PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9901,
+	  0xA000, 0x2000, 0, 0, netmos_9901 },
 	/* Quatech SPPXP-100 Parallel port PCI ExpressCard */
 	{ PCI_VENDOR_ID_QUATECH, PCI_DEVICE_ID_QUATECH_SPPXP_100,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, quatech_sppxp100 },
diff --git a/drivers/serial/8250_pci.c b/drivers/serial/8250_pci.c
index a07015d646dd..6160e03f410c 100644
--- a/drivers/serial/8250_pci.c
+++ b/drivers/serial/8250_pci.c
@@ -759,6 +759,8 @@ static int pci_netmos_init(struct pci_dev *dev)
 	/* subdevice 0x00PS means <P> parallel, <S> serial */
 	unsigned int num_serial = dev->subsystem_device & 0xf;
 
+	if (dev->device == PCI_DEVICE_ID_NETMOS_9901)
+		return 0;
 	if (dev->subsystem_vendor == PCI_VENDOR_ID_IBM &&
 			dev->subsystem_device == 0x0299)
 		return 0;
@@ -3557,6 +3559,10 @@ static struct pci_device_id serial_pci_tbl[] = {
 		PCI_VENDOR_ID_IBM, 0x0299,
 		0, 0, pbn_b0_bt_2_115200 },
 
+	{	PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9901,
+		0xA000, 0x1000,
+		0, 0, pbn_b0_1_115200 },
+
 	/*
 	 * These entries match devices with class COMMUNICATION_SERIAL,
 	 * COMMUNICATION_MODEM or COMMUNICATION_MULTISERIAL
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index a3b000365795..73b46b6b904f 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2645,6 +2645,7 @@
 #define PCI_DEVICE_ID_NETMOS_9835	0x9835
 #define PCI_DEVICE_ID_NETMOS_9845	0x9845
 #define PCI_DEVICE_ID_NETMOS_9855	0x9855
+#define PCI_DEVICE_ID_NETMOS_9901	0x9901
 
 #define PCI_VENDOR_ID_3COM_2		0xa727
 
-- 
cgit v1.2.3


From 341c87bf346f57748230628c5ad6ee69219250e8 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Tue, 30 Jun 2009 11:41:23 -0700
Subject: elf: limit max map count to safe value

With ELF, at generating coredump, some more headers other than used
vmas are added.

When max_map_count == 65536, a core generated by following kinds of
code can be unreadable because the number of ELF's program header is
written in 16bit in Ehdr (please see elf.h) and the number overflows.

==
	... = mmap(); (munmap, mprotect, etc...)
	if (failed)
		abort();
==

This can happen in mmap/munmap/mprotect/etc...which calls split_vma().

I think 65536 is not safe as _default_ and reduce it to 65530 is good
for avoiding unexpected corrupted core.

Anyway, max_map_count can be enlarged by sysctl if a user is brave..

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Jakub Jelinek <jakub@redhat.com>
Acked-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_elf.c       |  5 ++++-
 include/linux/sched.h | 16 ++++++++++++++--
 2 files changed, 18 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 9fa212b014a5..f1867900e459 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1929,7 +1929,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
 	elf = kmalloc(sizeof(*elf), GFP_KERNEL);
 	if (!elf)
 		goto out;
-	
+	/*
+	 * The number of segs are recored into ELF header as 16bit value.
+	 * Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
+	 */
 	segs = current->mm->map_count;
 #ifdef ELF_CORE_EXTRA_PHDRS
 	segs += ELF_CORE_EXTRA_PHDRS;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4d0754269884..0085d758d645 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -349,8 +349,20 @@ extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
 struct nsproxy;
 struct user_namespace;
 
-/* Maximum number of active map areas.. This is a random (large) number */
-#define DEFAULT_MAX_MAP_COUNT	65536
+/*
+ * Default maximum number of active map areas, this limits the number of vmas
+ * per mm struct. Users can overwrite this number by sysctl but there is a
+ * problem.
+ *
+ * When a program's coredump is generated as ELF format, a section is created
+ * per a vma. In ELF, the number of sections is represented in unsigned short.
+ * This means the number of sections should be smaller than 65535 at coredump.
+ * Because the kernel adds some informative sections to a image of program at
+ * generating coredump, we need some margin. The number of extra sections is
+ * 1-3 now and depends on arch. We use "5" as safe margin, here.
+ */
+#define MAPCOUNT_ELF_CORE_MARGIN	(5)
+#define DEFAULT_MAX_MAP_COUNT	(USHORT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
 
 extern int sysctl_max_map_count;
 
-- 
cgit v1.2.3


From b55f627feeb9d48fdbde3835e18afbc76712e49b Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Tue, 30 Jun 2009 11:41:26 -0700
Subject: spi: new spi->mode bits

Add two new spi_device.mode bits to accomodate more protocol options, and
pass them through to usermode drivers:

 * SPI_NO_CS ... a second 3-wire variant, where the chipselect
   line is removed instead of a data line; transfers are still
   full duplex.

   This obviously has STRONG protocol implications since the
   chipselect transitions can't be used to synchronize state
   transitions with the SPI master.

 * SPI_READY ... defines open drain signal that's pulled low
   to pause the clock.  This defines a 5-wire variant (normal
   4-wire SPI plus READY) and two 4-wire variants (READY plus
   each of the 3-wire flavors).

   Such hardware flow control can be a big win.  There are ADC
   converters and flash chips that expose READY signals, but not
   many host controllers support it today.

The spi_bitbang code should be changed to use SPI_NO_CS instead of its
current nonportable hack.  That's a mode most hardware can easily support
(unlike SPI_READY).

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Cc: "Paulraj, Sandeep" <s-paulraj@ti.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/spi/spidev_test.c | 10 +++++++++-
 drivers/spi/spidev.c            | 17 +++++++++++------
 include/linux/spi/spi.h         |  2 ++
 include/linux/spi/spidev.h      |  2 ++
 4 files changed, 24 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c
index cf0e3ce0d526..c1a5aad3c75a 100644
--- a/Documentation/spi/spidev_test.c
+++ b/Documentation/spi/spidev_test.c
@@ -99,11 +99,13 @@ void parse_opts(int argc, char *argv[])
 			{ "lsb",     0, 0, 'L' },
 			{ "cs-high", 0, 0, 'C' },
 			{ "3wire",   0, 0, '3' },
+			{ "no-cs",   0, 0, 'N' },
+			{ "ready",   0, 0, 'R' },
 			{ NULL, 0, 0, 0 },
 		};
 		int c;
 
-		c = getopt_long(argc, argv, "D:s:d:b:lHOLC3", lopts, NULL);
+		c = getopt_long(argc, argv, "D:s:d:b:lHOLC3NR", lopts, NULL);
 
 		if (c == -1)
 			break;
@@ -139,6 +141,12 @@ void parse_opts(int argc, char *argv[])
 		case '3':
 			mode |= SPI_3WIRE;
 			break;
+		case 'N':
+			mode |= SPI_NO_CS;
+			break;
+		case 'R':
+			mode |= SPI_READY;
+			break;
 		default:
 			print_usage(argv[0]);
 			break;
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 5d869c4d3eb2..606e7a40a8da 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -58,15 +58,20 @@ static unsigned long	minors[N_SPI_MINORS / BITS_PER_LONG];
 
 
 /* Bit masks for spi_device.mode management.  Note that incorrect
- * settings for CS_HIGH and 3WIRE can cause *lots* of trouble for other
- * devices on a shared bus:  CS_HIGH, because this device will be
- * active when it shouldn't be;  3WIRE, because when active it won't
- * behave as it should.
+ * settings for some settings can cause *lots* of trouble for other
+ * devices on a shared bus:
  *
- * REVISIT should changing those two modes be privileged?
+ *  - CS_HIGH ... this device will be active when it shouldn't be
+ *  - 3WIRE ... when active, it won't behave as it should
+ *  - NO_CS ... there will be no explicit message boundaries; this
+ *	is completely incompatible with the shared bus model
+ *  - READY ... transfers may proceed when they shouldn't.
+ *
+ * REVISIT should changing those flags be privileged?
  */
 #define SPI_MODE_MASK		(SPI_CPHA | SPI_CPOL | SPI_CS_HIGH \
-				| SPI_LSB_FIRST | SPI_3WIRE | SPI_LOOP)
+				| SPI_LSB_FIRST | SPI_3WIRE | SPI_LOOP \
+				| SPI_NO_CS | SPI_READY)
 
 struct spidev_data {
 	dev_t			devt;
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 9c4cd27f4685..743c933ac4e7 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -80,6 +80,8 @@ struct spi_device {
 #define	SPI_LSB_FIRST	0x08			/* per-word bits-on-wire */
 #define	SPI_3WIRE	0x10			/* SI/SO signals shared */
 #define	SPI_LOOP	0x20			/* loopback mode */
+#define	SPI_NO_CS	0x40			/* 1 dev/bus, no chipselect */
+#define	SPI_READY	0x80			/* slave pulls low to pause */
 	u8			bits_per_word;
 	int			irq;
 	void			*controller_state;
diff --git a/include/linux/spi/spidev.h b/include/linux/spi/spidev.h
index 95251ccd5a07..bf0570a84f7a 100644
--- a/include/linux/spi/spidev.h
+++ b/include/linux/spi/spidev.h
@@ -40,6 +40,8 @@
 #define SPI_LSB_FIRST		0x08
 #define SPI_3WIRE		0x10
 #define SPI_LOOP		0x20
+#define SPI_NO_CS		0x40
+#define SPI_READY		0x80
 
 /*---------------------------------------------------------------------------*/
 
-- 
cgit v1.2.3


From 70d6027ff2bc8bab180273b77e7ab3e8a62cca51 Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Tue, 30 Jun 2009 11:41:27 -0700
Subject: spi: add spi_master flag word

Add a new spi_master.flags word listing constraints relevant to that
controller.  Define the first constraint bit: a half duplex restriction.
Include that constraint in the OMAP1 MicroWire controller driver.

Have the mmc_spi host be the first customer of this flag.  Its coding
relies heavily on full duplex transfers, so it must fail when the
underlying controller driver won't perform them.

(The spi_write_then_read routine could use it too: use the
temporarily-withdrawn full-duplex speedup unless this flag is set, in
which case the existing code applies.  Similarly, any spi_master
implementing only SPI_3WIRE should set the flag.)

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/mmc/host/mmc_spi.c | 6 ++++++
 drivers/spi/omap_uwire.c   | 2 ++
 include/linux/spi/spi.h    | 4 ++++
 3 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 240608cc7ae9..a461017ce5ce 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1313,6 +1313,12 @@ static int mmc_spi_probe(struct spi_device *spi)
 	struct mmc_spi_host	*host;
 	int			status;
 
+	/* We rely on full duplex transfers, mostly to reduce
+	 * per-transfer overheads (by making fewer transfers).
+	 */
+	if (spi->master->flags & SPI_MASTER_HALF_DUPLEX)
+		return -EINVAL;
+
 	/* MMC and SD specs only seem to care that sampling is on the
 	 * rising edge ... meaning SPI modes 0 or 3.  So either SPI mode
 	 * should be legit.  We'll use mode 0 since the steady state is 0,
diff --git a/drivers/spi/omap_uwire.c b/drivers/spi/omap_uwire.c
index aa90ddb37066..8980a5640bd9 100644
--- a/drivers/spi/omap_uwire.c
+++ b/drivers/spi/omap_uwire.c
@@ -514,6 +514,8 @@ static int __init uwire_probe(struct platform_device *pdev)
 	/* the spi->mode bits understood by this driver: */
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 
+	master->flags = SPI_MASTER_HALF_DUPLEX;
+
 	master->bus_num = 2;	/* "official" */
 	master->num_chipselect = 4;
 	master->setup = uwire_setup;
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 743c933ac4e7..c47c4b4da97e 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -250,6 +250,10 @@ struct spi_master {
 	/* spi_device.mode flags understood by this controller driver */
 	u16			mode_bits;
 
+	/* other constraints relevant to this driver */
+	u16			flags;
+#define SPI_MASTER_HALF_DUPLEX	BIT(0)		/* can't do full duplex */
+
 	/* Setup mode and clock, etc (spi driver may call many times).
 	 *
 	 * IMPORTANT:  this may be called when transfers to another
-- 
cgit v1.2.3


From 537a1bf059fa312355696fa6db80726e655e7f17 Mon Sep 17 00:00:00 2001
From: Krzysztof Helt <krzysztof.h1@wp.pl>
Date: Tue, 30 Jun 2009 11:41:29 -0700
Subject: fbdev: add mutex for fb_mmap locking

Add a mutex to avoid a circular locking problem between the mm layer
semaphore and fbdev ioctl mutex through the fb_mmap() call.

Also, add mutex to all places where smem_start and smem_len fields change
so the mutex inside the fb_mmap() is actually used.  Changing of these
fields before calling the framebuffer_register() are not mutexed.

This is 2.6.31 material.  It removes one lockdep (fb_mmap() and
register_framebuffer()) but there is still another one (fb_release() and
register_framebuffer()).  It also cleans up handling of the smem_start and
smem_len fields used by mutexed section of the fb_mmap().

Signed-off-by: Krzysztof Helt <krzysztof.h1@wp.pl>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/video/atafb.c                 |  7 ++++++-
 drivers/video/atmel_lcdfb.c           |  2 ++
 drivers/video/fbmem.c                 | 13 +++++--------
 drivers/video/fsl-diu-fb.c            | 14 +++++++++-----
 drivers/video/i810/i810_main.c        |  2 ++
 drivers/video/matrox/matroxfb_base.c  |  3 +++
 drivers/video/matrox/matroxfb_crtc2.c |  5 ++++-
 drivers/video/mx3fb.c                 | 17 +++++++++++------
 drivers/video/omap/omapfb_main.c      |  4 ++++
 drivers/video/platinumfb.c            |  2 ++
 drivers/video/pxafb.c                 |  2 ++
 drivers/video/sh7760fb.c              | 19 ++++++-------------
 drivers/video/sis/sis_main.c          |  2 ++
 drivers/video/sm501fb.c               | 21 +++++++++++++--------
 drivers/video/w100fb.c                |  2 ++
 include/linux/fb.h                    |  1 +
 16 files changed, 74 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/video/atafb.c b/drivers/video/atafb.c
index 018850c116c6..497ff8af03ed 100644
--- a/drivers/video/atafb.c
+++ b/drivers/video/atafb.c
@@ -2414,7 +2414,10 @@ static int atafb_get_fix(struct fb_fix_screeninfo *fix, struct fb_info *info)
 	if (err)
 		return err;
 	memset(fix, 0, sizeof(struct fb_fix_screeninfo));
-	return fbhw->encode_fix(fix, &par);
+	mutex_lock(&info->mm_lock);
+	err = fbhw->encode_fix(fix, &par);
+	mutex_unlock(&info->mm_lock);
+	return err;
 }
 
 static int atafb_get_var(struct fb_var_screeninfo *var, struct fb_info *info)
@@ -2743,7 +2746,9 @@ static int atafb_set_par(struct fb_info *info)
 
 	/* Decode wanted screen parameters */
 	fbhw->decode_var(&info->var, par);
+	mutex_lock(&info->mm_lock);
 	fbhw->encode_fix(&info->fix, par);
+	mutex_unlock(&info->mm_lock);
 
 	/* Set new videomode */
 	ata_set_par(par);
diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c
index 5afd64482f55..cb88394ba995 100644
--- a/drivers/video/atmel_lcdfb.c
+++ b/drivers/video/atmel_lcdfb.c
@@ -270,7 +270,9 @@ static int atmel_lcdfb_alloc_video_memory(struct atmel_lcdfb_info *sinfo)
 
 	smem_len = (var->xres_virtual * var->yres_virtual
 		    * ((var->bits_per_pixel + 7) / 8));
+	mutex_lock(&info->mm_lock);
 	info->fix.smem_len = max(smem_len, sinfo->smem_len);
+	mutex_unlock(&info->mm_lock);
 
 	info->screen_base = dma_alloc_writecombine(info->device, info->fix.smem_len,
 					(dma_addr_t *)&info->fix.smem_start, GFP_KERNEL);
diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
index f8a09bf8d0cd..53ea05645ff8 100644
--- a/drivers/video/fbmem.c
+++ b/drivers/video/fbmem.c
@@ -1310,8 +1310,6 @@ static long fb_compat_ioctl(struct file *file, unsigned int cmd,
 
 static int
 fb_mmap(struct file *file, struct vm_area_struct * vma)
-__acquires(&info->lock)
-__releases(&info->lock)
 {
 	int fbidx = iminor(file->f_path.dentry->d_inode);
 	struct fb_info *info = registered_fb[fbidx];
@@ -1325,16 +1323,14 @@ __releases(&info->lock)
 	off = vma->vm_pgoff << PAGE_SHIFT;
 	if (!fb)
 		return -ENODEV;
+	mutex_lock(&info->mm_lock);
 	if (fb->fb_mmap) {
 		int res;
-		mutex_lock(&info->lock);
 		res = fb->fb_mmap(info, vma);
-		mutex_unlock(&info->lock);
+		mutex_unlock(&info->mm_lock);
 		return res;
 	}
 
-	mutex_lock(&info->lock);
-
 	/* frame buffer memory */
 	start = info->fix.smem_start;
 	len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.smem_len);
@@ -1342,13 +1338,13 @@ __releases(&info->lock)
 		/* memory mapped io */
 		off -= len;
 		if (info->var.accel_flags) {
-			mutex_unlock(&info->lock);
+			mutex_unlock(&info->mm_lock);
 			return -EINVAL;
 		}
 		start = info->fix.mmio_start;
 		len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.mmio_len);
 	}
-	mutex_unlock(&info->lock);
+	mutex_unlock(&info->mm_lock);
 	start &= PAGE_MASK;
 	if ((vma->vm_end - vma->vm_start + off) > len)
 		return -EINVAL;
@@ -1518,6 +1514,7 @@ register_framebuffer(struct fb_info *fb_info)
 			break;
 	fb_info->node = i;
 	mutex_init(&fb_info->lock);
+	mutex_init(&fb_info->mm_lock);
 
 	fb_info->dev = device_create(fb_class, fb_info->device,
 				     MKDEV(FB_MAJOR, i), NULL, "fb%d", i);
diff --git a/drivers/video/fsl-diu-fb.c b/drivers/video/fsl-diu-fb.c
index f153c581cbd7..0bf2190928d0 100644
--- a/drivers/video/fsl-diu-fb.c
+++ b/drivers/video/fsl-diu-fb.c
@@ -750,24 +750,26 @@ static void update_lcdc(struct fb_info *info)
 static int map_video_memory(struct fb_info *info)
 {
 	phys_addr_t phys;
+	u32 smem_len = info->fix.line_length * info->var.yres_virtual;
 
 	pr_debug("info->var.xres_virtual = %d\n", info->var.xres_virtual);
 	pr_debug("info->var.yres_virtual = %d\n", info->var.yres_virtual);
 	pr_debug("info->fix.line_length  = %d\n", info->fix.line_length);
+	pr_debug("MAP_VIDEO_MEMORY: smem_len = %u\n", smem_len);
 
-	info->fix.smem_len = info->fix.line_length * info->var.yres_virtual;
-	pr_debug("MAP_VIDEO_MEMORY: smem_len = %d\n", info->fix.smem_len);
-	info->screen_base = fsl_diu_alloc(info->fix.smem_len, &phys);
+	info->screen_base = fsl_diu_alloc(smem_len, &phys);
 	if (info->screen_base == NULL) {
 		printk(KERN_ERR "Unable to allocate fb memory\n");
 		return -ENOMEM;
 	}
+	mutex_lock(&info->mm_lock);
 	info->fix.smem_start = (unsigned long) phys;
+	info->fix.smem_len = smem_len;
+	mutex_unlock(&info->mm_lock);
 	info->screen_size = info->fix.smem_len;
 
 	pr_debug("Allocated fb @ paddr=0x%08lx, size=%d.\n",
-				info->fix.smem_start,
-		info->fix.smem_len);
+		 info->fix.smem_start, info->fix.smem_len);
 	pr_debug("screen base %p\n", info->screen_base);
 
 	return 0;
@@ -776,9 +778,11 @@ static int map_video_memory(struct fb_info *info)
 static void unmap_video_memory(struct fb_info *info)
 {
 	fsl_diu_free(info->screen_base, info->fix.smem_len);
+	mutex_lock(&info->mm_lock);
 	info->screen_base = NULL;
 	info->fix.smem_start = 0;
 	info->fix.smem_len = 0;
+	mutex_unlock(&info->mm_lock);
 }
 
 /*
diff --git a/drivers/video/i810/i810_main.c b/drivers/video/i810/i810_main.c
index 2e940199fc89..71960672d721 100644
--- a/drivers/video/i810/i810_main.c
+++ b/drivers/video/i810/i810_main.c
@@ -1090,8 +1090,10 @@ static int encode_fix(struct fb_fix_screeninfo *fix, struct fb_info *info)
     	memset(fix, 0, sizeof(struct fb_fix_screeninfo));
 
     	strcpy(fix->id, "I810");
+	mutex_lock(&info->mm_lock);
     	fix->smem_start = par->fb.physical;
     	fix->smem_len = par->fb.size;
+	mutex_unlock(&info->mm_lock);
     	fix->type = FB_TYPE_PACKED_PIXELS;
     	fix->type_aux = 0;
 	fix->xpanstep = 8;
diff --git a/drivers/video/matrox/matroxfb_base.c b/drivers/video/matrox/matroxfb_base.c
index 8e7a275df50c..59c3a2e14913 100644
--- a/drivers/video/matrox/matroxfb_base.c
+++ b/drivers/video/matrox/matroxfb_base.c
@@ -724,8 +724,10 @@ static void matroxfb_update_fix(WPMINFO2)
 	struct fb_fix_screeninfo *fix = &ACCESS_FBINFO(fbcon).fix;
 	DBG(__func__)
 
+	mutex_lock(&ACCESS_FBINFO(fbcon).mm_lock);
 	fix->smem_start = ACCESS_FBINFO(video.base) + ACCESS_FBINFO(curr.ydstorg.bytes);
 	fix->smem_len = ACCESS_FBINFO(video.len_usable) - ACCESS_FBINFO(curr.ydstorg.bytes);
+	mutex_unlock(&ACCESS_FBINFO(fbcon).mm_lock);
 }
 
 static int matroxfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
@@ -2081,6 +2083,7 @@ static int matroxfb_probe(struct pci_dev* pdev, const struct pci_device_id* dumm
 	spin_lock_init(&ACCESS_FBINFO(lock.accel));
 	init_rwsem(&ACCESS_FBINFO(crtc2.lock));
 	init_rwsem(&ACCESS_FBINFO(altout.lock));
+	mutex_init(&ACCESS_FBINFO(fbcon).mm_lock);
 	ACCESS_FBINFO(irq_flags) = 0;
 	init_waitqueue_head(&ACCESS_FBINFO(crtc1.vsync.wait));
 	init_waitqueue_head(&ACCESS_FBINFO(crtc2.vsync.wait));
diff --git a/drivers/video/matrox/matroxfb_crtc2.c b/drivers/video/matrox/matroxfb_crtc2.c
index 7ac4c5f6145d..909e10a11898 100644
--- a/drivers/video/matrox/matroxfb_crtc2.c
+++ b/drivers/video/matrox/matroxfb_crtc2.c
@@ -289,13 +289,16 @@ static int matroxfb_dh_release(struct fb_info* info, int user) {
 #undef m2info
 }
 
-static void matroxfb_dh_init_fix(struct matroxfb_dh_fb_info *m2info) {
+static void matroxfb_dh_init_fix(struct matroxfb_dh_fb_info *m2info)
+{
 	struct fb_fix_screeninfo *fix = &m2info->fbcon.fix;
 
 	strcpy(fix->id, "MATROX DH");
 
+	mutex_lock(&m2info->fbcon.mm_lock);
 	fix->smem_start = m2info->video.base;
 	fix->smem_len = m2info->video.len_usable;
+	mutex_unlock(&m2info->fbcon.mm_lock);
 	fix->ypanstep = 1;
 	fix->ywrapstep = 0;
 	fix->xpanstep = 8;	/* TBD */
diff --git a/drivers/video/mx3fb.c b/drivers/video/mx3fb.c
index b7af5256e887..567fb944bd2a 100644
--- a/drivers/video/mx3fb.c
+++ b/drivers/video/mx3fb.c
@@ -669,7 +669,7 @@ static uint32_t bpp_to_pixfmt(int bpp)
 }
 
 static int mx3fb_blank(int blank, struct fb_info *fbi);
-static int mx3fb_map_video_memory(struct fb_info *fbi);
+static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len);
 static int mx3fb_unmap_video_memory(struct fb_info *fbi);
 
 /**
@@ -742,8 +742,7 @@ static int mx3fb_set_par(struct fb_info *fbi)
 		if (fbi->fix.smem_start)
 			mx3fb_unmap_video_memory(fbi);
 
-		fbi->fix.smem_len = mem_len;
-		if (mx3fb_map_video_memory(fbi) < 0) {
+		if (mx3fb_map_video_memory(fbi, mem_len) < 0) {
 			mutex_unlock(&mx3_fbi->mutex);
 			return -ENOMEM;
 		}
@@ -1198,6 +1197,7 @@ static int mx3fb_resume(struct platform_device *pdev)
 /**
  * mx3fb_map_video_memory() - allocates the DRAM memory for the frame buffer.
  * @fbi:	framebuffer information pointer
+ * @mem_len:	length of mapped memory
  * @return:	Error code indicating success or failure
  *
  * This buffer is remapped into a non-cached, non-buffered, memory region to
@@ -1205,23 +1205,26 @@ static int mx3fb_resume(struct platform_device *pdev)
  * area is remapped, all virtual memory access to the video memory should occur
  * at the new region.
  */
-static int mx3fb_map_video_memory(struct fb_info *fbi)
+static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len)
 {
 	int retval = 0;
 	dma_addr_t addr;
 
 	fbi->screen_base = dma_alloc_writecombine(fbi->device,
-						  fbi->fix.smem_len,
+						  mem_len,
 						  &addr, GFP_DMA);
 
 	if (!fbi->screen_base) {
 		dev_err(fbi->device, "Cannot allocate %u bytes framebuffer memory\n",
-			fbi->fix.smem_len);
+			mem_len);
 		retval = -EBUSY;
 		goto err0;
 	}
 
+	mutex_lock(&fbi->mm_lock);
 	fbi->fix.smem_start = addr;
+	fbi->fix.smem_len = mem_len;
+	mutex_unlock(&fbi->mm_lock);
 
 	dev_dbg(fbi->device, "allocated fb @ p=0x%08x, v=0x%p, size=%d.\n",
 		(uint32_t) fbi->fix.smem_start, fbi->screen_base, fbi->fix.smem_len);
@@ -1251,8 +1254,10 @@ static int mx3fb_unmap_video_memory(struct fb_info *fbi)
 			      fbi->screen_base, fbi->fix.smem_start);
 
 	fbi->screen_base = 0;
+	mutex_lock(&fbi->mm_lock);
 	fbi->fix.smem_start = 0;
 	fbi->fix.smem_len = 0;
+	mutex_unlock(&fbi->mm_lock);
 	return 0;
 }
 
diff --git a/drivers/video/omap/omapfb_main.c b/drivers/video/omap/omapfb_main.c
index 060d72fe57cb..4ea99bfc37b4 100644
--- a/drivers/video/omap/omapfb_main.c
+++ b/drivers/video/omap/omapfb_main.c
@@ -393,8 +393,10 @@ static void set_fb_fix(struct fb_info *fbi)
 
 	rg = &plane->fbdev->mem_desc.region[plane->idx];
 	fbi->screen_base	= rg->vaddr;
+	mutex_lock(&fbi->mm_lock);
 	fix->smem_start		= rg->paddr;
 	fix->smem_len		= rg->size;
+	mutex_unlock(&fbi->mm_lock);
 
 	fix->type = FB_TYPE_PACKED_PIXELS;
 	bpp = var->bits_per_pixel;
@@ -886,8 +888,10 @@ static int omapfb_setup_mem(struct fb_info *fbi, struct omapfb_mem_info *mi)
 				 * plane memory is dealloce'd, the other
 				 * screen parameters in var / fix are invalid.
 				 */
+				mutex_lock(&fbi->mm_lock);
 				fbi->fix.smem_start = 0;
 				fbi->fix.smem_len = 0;
+				mutex_unlock(&fbi->mm_lock);
 			}
 		}
 	}
diff --git a/drivers/video/platinumfb.c b/drivers/video/platinumfb.c
index 03b3670130a0..bacfabd9ce16 100644
--- a/drivers/video/platinumfb.c
+++ b/drivers/video/platinumfb.c
@@ -141,7 +141,9 @@ static int platinumfb_set_par (struct fb_info *info)
   		offset = 0x10;
 
 	info->screen_base = pinfo->frame_buffer + init->fb_offset + offset;
+	mutex_lock(&info->mm_lock);
 	info->fix.smem_start = (pinfo->frame_buffer_phys) + init->fb_offset + offset;
+	mutex_unlock(&info->mm_lock);
 	info->fix.visual = (pinfo->cmode == CMODE_8) ?
 		FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_DIRECTCOLOR;
  	info->fix.line_length = vmode_attrs[pinfo->vmode-1].hres * (1<<pinfo->cmode)
diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c
index 0889d50c3288..6506117c134b 100644
--- a/drivers/video/pxafb.c
+++ b/drivers/video/pxafb.c
@@ -815,8 +815,10 @@ static int overlayfb_map_video_memory(struct pxafb_layer *ofb)
 	ofb->video_mem_phys = virt_to_phys(ofb->video_mem);
 	ofb->video_mem_size = size;
 
+	mutex_lock(&ofb->fb.mm_lock);
 	ofb->fb.fix.smem_start	= ofb->video_mem_phys;
 	ofb->fb.fix.smem_len	= ofb->fb.fix.line_length * var->yres_virtual;
+	mutex_unlock(&ofb->fb.mm_lock);
 	ofb->fb.screen_base	= ofb->video_mem;
 	return 0;
 }
diff --git a/drivers/video/sh7760fb.c b/drivers/video/sh7760fb.c
index 653bdfee3057..9f6d6e61f0cc 100644
--- a/drivers/video/sh7760fb.c
+++ b/drivers/video/sh7760fb.c
@@ -120,18 +120,6 @@ static int sh7760_setcolreg (u_int regno,
 	return 0;
 }
 
-static void encode_fix(struct fb_fix_screeninfo *fix, struct fb_info *info,
-		       unsigned long stride)
-{
-	memset(fix, 0, sizeof(struct fb_fix_screeninfo));
-	strcpy(fix->id, "sh7760-lcdc");
-
-	fix->smem_start = (unsigned long)info->screen_base;
-	fix->smem_len = info->screen_size;
-
-	fix->line_length = stride;
-}
-
 static int sh7760fb_get_color_info(struct device *dev,
 				   u16 lddfr, int *bpp, int *gray)
 {
@@ -334,7 +322,8 @@ static int sh7760fb_set_par(struct fb_info *info)
 
 	iowrite32(ldsarl, par->base + LDSARL);	/* mem for lower half of DSTN */
 
-	encode_fix(&info->fix, info, stride);
+	info->fix.line_length = stride;
+
 	sh7760fb_check_var(&info->var, info);
 
 	sh7760fb_blank(FB_BLANK_UNBLANK, info);	/* panel on! */
@@ -435,6 +424,8 @@ static int sh7760fb_alloc_mem(struct fb_info *info)
 
 	info->screen_base = fbmem;
 	info->screen_size = vram;
+	info->fix.smem_start = (unsigned long)info->screen_base;
+	info->fix.smem_len = info->screen_size;
 
 	return 0;
 }
@@ -520,6 +511,8 @@ static int __devinit sh7760fb_probe(struct platform_device *pdev)
 	info->var.transp.length = 0;
 	info->var.transp.msb_right = 0;
 
+	strcpy(info->fix.id, "sh7760-lcdc");
+
 	/* set the DON2 bit now, before cmap allocation, as it will randomize
 	 * palette memory.
 	 */
diff --git a/drivers/video/sis/sis_main.c b/drivers/video/sis/sis_main.c
index 7072d19080d5..fd33455389b8 100644
--- a/drivers/video/sis/sis_main.c
+++ b/drivers/video/sis/sis_main.c
@@ -1847,8 +1847,10 @@ sisfb_get_fix(struct fb_fix_screeninfo *fix, int con, struct fb_info *info)
 
 	strcpy(fix->id, ivideo->myid);
 
+	mutex_lock(&info->mm_lock);
 	fix->smem_start  = ivideo->video_base + ivideo->video_offset;
 	fix->smem_len    = ivideo->sisfb_mem;
+	mutex_unlock(&info->mm_lock);
 	fix->type        = FB_TYPE_PACKED_PIXELS;
 	fix->type_aux    = 0;
 	fix->visual      = (ivideo->video_bpp == 8) ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
diff --git a/drivers/video/sm501fb.c b/drivers/video/sm501fb.c
index eb5d73a06702..98f24f0ec00d 100644
--- a/drivers/video/sm501fb.c
+++ b/drivers/video/sm501fb.c
@@ -145,7 +145,7 @@ static inline void sm501fb_sync_regs(struct sm501fb_info *info)
 #define SM501_MEMF_ACCEL		(8)
 
 static int sm501_alloc_mem(struct sm501fb_info *inf, struct sm501_mem *mem,
-			   unsigned int why, size_t size)
+			   unsigned int why, size_t size, u32 smem_len)
 {
 	struct sm501fb_par *par;
 	struct fb_info *fbi;
@@ -172,7 +172,7 @@ static int sm501_alloc_mem(struct sm501fb_info *inf, struct sm501_mem *mem,
 		if (ptr > 0)
 			ptr &= ~(PAGE_SIZE - 1);
 
-		if (fbi && ptr < fbi->fix.smem_len)
+		if (fbi && ptr < smem_len)
 			return -ENOMEM;
 
 		break;
@@ -197,7 +197,7 @@ static int sm501_alloc_mem(struct sm501fb_info *inf, struct sm501_mem *mem,
 
 	case SM501_MEMF_ACCEL:
 		fbi = inf->fb[HEAD_CRT];
-		ptr = fbi ? fbi->fix.smem_len : 0;
+		ptr = fbi ? smem_len : 0;
 
 		fbi = inf->fb[HEAD_PANEL];
 		if (fbi) {
@@ -413,6 +413,7 @@ static int sm501fb_set_par_common(struct fb_info *info,
 	unsigned int mem_type;
 	unsigned int clock_type;
 	unsigned int head_addr;
+	unsigned int smem_len;
 
 	dev_dbg(fbi->dev, "%s: %dx%d, bpp = %d, virtual %dx%d\n",
 		__func__, var->xres, var->yres, var->bits_per_pixel,
@@ -453,18 +454,20 @@ static int sm501fb_set_par_common(struct fb_info *info,
 
 	/* allocate fb memory within 501 */
 	info->fix.line_length = (var->xres_virtual * var->bits_per_pixel)/8;
-	info->fix.smem_len    = info->fix.line_length * var->yres_virtual;
+	smem_len = info->fix.line_length * var->yres_virtual;
 
 	dev_dbg(fbi->dev, "%s: line length = %u\n", __func__,
 		info->fix.line_length);
 
-	if (sm501_alloc_mem(fbi, &par->screen, mem_type,
-			    info->fix.smem_len)) {
+	if (sm501_alloc_mem(fbi, &par->screen, mem_type, smem_len, smem_len)) {
 		dev_err(fbi->dev, "no memory available\n");
 		return -ENOMEM;
 	}
 
+	mutex_lock(&info->mm_lock);
 	info->fix.smem_start = fbi->fbmem_res->start + par->screen.sm_addr;
+	info->fix.smem_len   = smem_len;
+	mutex_unlock(&info->mm_lock);
 
 	info->screen_base = fbi->fbmem + par->screen.sm_addr;
 	info->screen_size = info->fix.smem_len;
@@ -637,7 +640,8 @@ static int sm501fb_set_par_crt(struct fb_info *info)
 	if ((control & SM501_DC_CRT_CONTROL_SEL) == 0) {
 		/* the head is displaying panel data... */
 
-		sm501_alloc_mem(fbi, &par->screen, SM501_MEMF_CRT, 0);
+		sm501_alloc_mem(fbi, &par->screen, SM501_MEMF_CRT, 0,
+				info->fix.smem_len);
 		goto out_update;
 	}
 
@@ -1289,7 +1293,8 @@ static int sm501_init_cursor(struct fb_info *fbi, unsigned int reg_base)
 
 	par->cursor_regs = info->regs + reg_base;
 
-	ret = sm501_alloc_mem(info, &par->cursor, SM501_MEMF_CURSOR, 1024);
+	ret = sm501_alloc_mem(info, &par->cursor, SM501_MEMF_CURSOR, 1024,
+			      fbi->fix.smem_len);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/video/w100fb.c b/drivers/video/w100fb.c
index d0674f1e3f10..8a141c2c637b 100644
--- a/drivers/video/w100fb.c
+++ b/drivers/video/w100fb.c
@@ -523,6 +523,7 @@ static int w100fb_set_par(struct fb_info *info)
 		info->fix.ywrapstep = 0;
 		info->fix.line_length = par->xres * BITS_PER_PIXEL / 8;
 
+		mutex_lock(&info->mm_lock);
 		if ((par->xres*par->yres*BITS_PER_PIXEL/8) > (MEM_INT_SIZE+1)) {
 			par->extmem_active = 1;
 			info->fix.smem_len = par->mach->mem->size+1;
@@ -530,6 +531,7 @@ static int w100fb_set_par(struct fb_info *info)
 			par->extmem_active = 0;
 			info->fix.smem_len = MEM_INT_SIZE+1;
 		}
+		mutex_unlock(&info->mm_lock);
 
 		w100fb_activate_var(par);
 	}
diff --git a/include/linux/fb.h b/include/linux/fb.h
index dd68358996b7..f847df9e99b6 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -819,6 +819,7 @@ struct fb_info {
 	int node;
 	int flags;
 	struct mutex lock;		/* Lock for open/release/ioctl funcs */
+	struct mutex mm_lock;		/* Lock for fb_mmap and smem_* fields */
 	struct fb_var_screeninfo var;	/* Current var */
 	struct fb_fix_screeninfo fix;	/* Current fix */
 	struct fb_monspecs monspecs;	/* Current Monitor specs */
-- 
cgit v1.2.3


From d9d62f3f2c6fa609883714f6fd6cd710a83d307f Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 29 Jun 2009 16:54:12 +0000
Subject: usbnet: Remove private stats structure

Now that nothing uses the private stats structure we can remove it.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/usb/usbnet.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 5d44059f6d63..310e18a880ff 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -42,7 +42,6 @@ struct usbnet {
 
 	/* protocol/interface state */
 	struct net_device	*net;
-	struct net_device_stats	stats;
 	int			msg_enable;
 	unsigned long		data [5];
 	u32			xid;
-- 
cgit v1.2.3


From 7878cba9f0037f5599004b03a1260b32d9050360 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 26 Jun 2009 15:37:49 +0200
Subject: block: Create bip slabs with embedded integrity vectors

This patch restores stacking ability to the block layer integrity
infrastructure by creating a set of dedicated bip slabs.  Each bip slab
has an embedded bio_vec array at the end.  This cuts down on memory
allocations and also simplifies the code compared to the original bvec
version.  Only the largest bip slab is backed by a mempool.  The pool is
contained in the bio_set so stacking drivers can ensure forward
progress.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@carl.(none)>
---
 block/blk-core.c    |   2 +-
 drivers/md/dm.c     |   4 +-
 fs/bio-integrity.c  | 170 ++++++++++++++++++++++++++++++++++++++--------------
 fs/bio.c            |  11 +++-
 include/linux/bio.h |  22 +++++--
 5 files changed, 152 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index b06cf5c2a829..345d99da8d41 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2365,7 +2365,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
 		__bio_clone(bio, bio_src);
 
 		if (bio_integrity(bio_src) &&
-		    bio_integrity_clone(bio, bio_src, gfp_mask))
+		    bio_integrity_clone(bio, bio_src, gfp_mask, bs))
 			goto free_and_out;
 
 		if (bio_ctr && bio_ctr(bio, bio_src, data))
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3c6d4ee8921d..9acd54a5cffb 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1017,7 +1017,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
 	clone->bi_flags |= 1 << BIO_CLONED;
 
 	if (bio_integrity(bio)) {
-		bio_integrity_clone(clone, bio, GFP_NOIO);
+		bio_integrity_clone(clone, bio, GFP_NOIO, bs);
 		bio_integrity_trim(clone,
 				   bio_sector_offset(bio, idx, offset), len);
 	}
@@ -1045,7 +1045,7 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
 	clone->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 	if (bio_integrity(bio)) {
-		bio_integrity_clone(clone, bio, GFP_NOIO);
+		bio_integrity_clone(clone, bio, GFP_NOIO, bs);
 
 		if (idx != bio->bi_idx || clone->bi_size < bio->bi_size)
 			bio_integrity_trim(clone,
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 31c46a241bac..49a34e7f7306 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -1,7 +1,7 @@
 /*
  * bio-integrity.c - bio data integrity extensions
  *
- * Copyright (C) 2007, 2008 Oracle Corporation
+ * Copyright (C) 2007, 2008, 2009 Oracle Corporation
  * Written by: Martin K. Petersen <martin.petersen@oracle.com>
  *
  * This program is free software; you can redistribute it and/or
@@ -25,63 +25,121 @@
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 
-static struct kmem_cache *bio_integrity_slab __read_mostly;
-static mempool_t *bio_integrity_pool;
-static struct bio_set *integrity_bio_set;
+struct integrity_slab {
+	struct kmem_cache *slab;
+	unsigned short nr_vecs;
+	char name[8];
+};
+
+#define IS(x) { .nr_vecs = x, .name = "bip-"__stringify(x) }
+struct integrity_slab bip_slab[BIOVEC_NR_POOLS] __read_mostly = {
+	IS(1), IS(4), IS(16), IS(64), IS(128), IS(BIO_MAX_PAGES),
+};
+#undef IS
+
 static struct workqueue_struct *kintegrityd_wq;
 
+static inline unsigned int vecs_to_idx(unsigned int nr)
+{
+	switch (nr) {
+	case 1:
+		return 0;
+	case 2 ... 4:
+		return 1;
+	case 5 ... 16:
+		return 2;
+	case 17 ... 64:
+		return 3;
+	case 65 ... 128:
+		return 4;
+	case 129 ... BIO_MAX_PAGES:
+		return 5;
+	default:
+		BUG();
+	}
+}
+
+static inline int use_bip_pool(unsigned int idx)
+{
+	if (idx == BIOVEC_NR_POOLS)
+		return 1;
+
+	return 0;
+}
+
 /**
- * bio_integrity_alloc - Allocate integrity payload and attach it to bio
+ * bio_integrity_alloc_bioset - Allocate integrity payload and attach it to bio
  * @bio:	bio to attach integrity metadata to
  * @gfp_mask:	Memory allocation mask
  * @nr_vecs:	Number of integrity metadata scatter-gather elements
+ * @bs:		bio_set to allocate from
  *
  * Description: This function prepares a bio for attaching integrity
  * metadata.  nr_vecs specifies the maximum number of pages containing
  * integrity metadata that can be attached.
  */
-struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
-						  gfp_t gfp_mask,
-						  unsigned int nr_vecs)
+struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *bio,
+							 gfp_t gfp_mask,
+							 unsigned int nr_vecs,
+							 struct bio_set *bs)
 {
 	struct bio_integrity_payload *bip;
-	struct bio_vec *iv;
-	unsigned long idx;
+	unsigned int idx = vecs_to_idx(nr_vecs);
 
 	BUG_ON(bio == NULL);
+	bip = NULL;
 
-	bip = mempool_alloc(bio_integrity_pool, gfp_mask);
-	if (unlikely(bip == NULL)) {
-		printk(KERN_ERR "%s: could not alloc bip\n", __func__);
-		return NULL;
-	}
+	/* Lower order allocations come straight from slab */
+	if (!use_bip_pool(idx))
+		bip = kmem_cache_alloc(bip_slab[idx].slab, gfp_mask);
 
-	memset(bip, 0, sizeof(*bip));
+	/* Use mempool if lower order alloc failed or max vecs were requested */
+	if (bip == NULL) {
+		bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask);
 
-	iv = bvec_alloc_bs(gfp_mask, nr_vecs, &idx, integrity_bio_set);
-	if (unlikely(iv == NULL)) {
-		printk(KERN_ERR "%s: could not alloc bip_vec\n", __func__);
-		mempool_free(bip, bio_integrity_pool);
-		return NULL;
+		if (unlikely(bip == NULL)) {
+			printk(KERN_ERR "%s: could not alloc bip\n", __func__);
+			return NULL;
+		}
 	}
 
-	bip->bip_pool = idx;
-	bip->bip_vec = iv;
+	memset(bip, 0, sizeof(*bip));
+
+	bip->bip_slab = idx;
 	bip->bip_bio = bio;
 	bio->bi_integrity = bip;
 
 	return bip;
 }
+EXPORT_SYMBOL(bio_integrity_alloc_bioset);
+
+/**
+ * bio_integrity_alloc - Allocate integrity payload and attach it to bio
+ * @bio:	bio to attach integrity metadata to
+ * @gfp_mask:	Memory allocation mask
+ * @nr_vecs:	Number of integrity metadata scatter-gather elements
+ *
+ * Description: This function prepares a bio for attaching integrity
+ * metadata.  nr_vecs specifies the maximum number of pages containing
+ * integrity metadata that can be attached.
+ */
+struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
+						  gfp_t gfp_mask,
+						  unsigned int nr_vecs)
+{
+	return bio_integrity_alloc_bioset(bio, gfp_mask, nr_vecs, fs_bio_set);
+}
 EXPORT_SYMBOL(bio_integrity_alloc);
 
 /**
  * bio_integrity_free - Free bio integrity payload
  * @bio:	bio containing bip to be freed
+ * @bs:		bio_set this bio was allocated from
  *
  * Description: Used to free the integrity portion of a bio. Usually
  * called from bio_free().
  */
-void bio_integrity_free(struct bio *bio)
+void bio_integrity_free(struct bio *bio, struct bio_set *bs)
 {
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 
@@ -92,8 +150,10 @@ void bio_integrity_free(struct bio *bio)
 	    && bip->bip_buf != NULL)
 		kfree(bip->bip_buf);
 
-	bvec_free_bs(integrity_bio_set, bip->bip_vec, bip->bip_pool);
-	mempool_free(bip, bio_integrity_pool);
+	if (use_bip_pool(bip->bip_slab))
+		mempool_free(bip, bs->bio_integrity_pool);
+	else
+		kmem_cache_free(bip_slab[bip->bip_slab].slab, bip);
 
 	bio->bi_integrity = NULL;
 }
@@ -114,7 +174,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 	struct bio_integrity_payload *bip = bio->bi_integrity;
 	struct bio_vec *iv;
 
-	if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_pool)) {
+	if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) {
 		printk(KERN_ERR "%s: bip_vec full\n", __func__);
 		return 0;
 	}
@@ -647,8 +707,8 @@ void bio_integrity_split(struct bio *bio, struct bio_pair *bp, int sectors)
 	bp->iv1 = bip->bip_vec[0];
 	bp->iv2 = bip->bip_vec[0];
 
-	bp->bip1.bip_vec = &bp->iv1;
-	bp->bip2.bip_vec = &bp->iv2;
+	bp->bip1.bip_vec[0] = bp->iv1;
+	bp->bip2.bip_vec[0] = bp->iv2;
 
 	bp->iv1.bv_len = sectors * bi->tuple_size;
 	bp->iv2.bv_offset += sectors * bi->tuple_size;
@@ -667,17 +727,19 @@ EXPORT_SYMBOL(bio_integrity_split);
  * @bio:	New bio
  * @bio_src:	Original bio
  * @gfp_mask:	Memory allocation mask
+ * @bs:		bio_set to allocate bip from
  *
  * Description:	Called to allocate a bip when cloning a bio
  */
-int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask)
+int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
+			gfp_t gfp_mask, struct bio_set *bs)
 {
 	struct bio_integrity_payload *bip_src = bio_src->bi_integrity;
 	struct bio_integrity_payload *bip;
 
 	BUG_ON(bip_src == NULL);
 
-	bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
+	bip = bio_integrity_alloc_bioset(bio, gfp_mask, bip_src->bip_vcnt, bs);
 
 	if (bip == NULL)
 		return -EIO;
@@ -693,25 +755,43 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(bio_integrity_clone);
 
-static int __init bio_integrity_init(void)
+int bioset_integrity_create(struct bio_set *bs, int pool_size)
 {
-	kintegrityd_wq = create_workqueue("kintegrityd");
+	unsigned int max_slab = vecs_to_idx(BIO_MAX_PAGES);
+
+	bs->bio_integrity_pool =
+		mempool_create_slab_pool(pool_size, bip_slab[max_slab].slab);
 
+	if (!bs->bio_integrity_pool)
+		return -1;
+
+	return 0;
+}
+EXPORT_SYMBOL(bioset_integrity_create);
+
+void bioset_integrity_free(struct bio_set *bs)
+{
+	if (bs->bio_integrity_pool)
+		mempool_destroy(bs->bio_integrity_pool);
+}
+EXPORT_SYMBOL(bioset_integrity_free);
+
+void __init bio_integrity_init(void)
+{
+	unsigned int i;
+
+	kintegrityd_wq = create_workqueue("kintegrityd");
 	if (!kintegrityd_wq)
 		panic("Failed to create kintegrityd\n");
 
-	bio_integrity_slab = KMEM_CACHE(bio_integrity_payload,
-					SLAB_HWCACHE_ALIGN|SLAB_PANIC);
+	for (i = 0 ; i < BIOVEC_NR_POOLS ; i++) {
+		unsigned int size;
 
-	bio_integrity_pool = mempool_create_slab_pool(BIO_POOL_SIZE,
-						      bio_integrity_slab);
-	if (!bio_integrity_pool)
-		panic("bio_integrity: can't allocate bip pool\n");
+		size = sizeof(struct bio_integrity_payload)
+			+ bip_slab[i].nr_vecs * sizeof(struct bio_vec);
 
-	integrity_bio_set = bioset_create(BIO_POOL_SIZE, 0);
-	if (!integrity_bio_set)
-		panic("bio_integrity: can't allocate bio_set\n");
-
-	return 0;
+		bip_slab[i].slab =
+			kmem_cache_create(bip_slab[i].name, size, 0,
+					  SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	}
 }
-subsys_initcall(bio_integrity_init);
diff --git a/fs/bio.c b/fs/bio.c
index 24c914043532..1486b19fc431 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -238,7 +238,7 @@ void bio_free(struct bio *bio, struct bio_set *bs)
 		bvec_free_bs(bs, bio->bi_io_vec, BIO_POOL_IDX(bio));
 
 	if (bio_integrity(bio))
-		bio_integrity_free(bio);
+		bio_integrity_free(bio, bs);
 
 	/*
 	 * If we have front padding, adjust the bio pointer before freeing
@@ -341,7 +341,7 @@ struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
 static void bio_kmalloc_destructor(struct bio *bio)
 {
 	if (bio_integrity(bio))
-		bio_integrity_free(bio);
+		bio_integrity_free(bio, fs_bio_set);
 	kfree(bio);
 }
 
@@ -472,7 +472,7 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
 	if (bio_integrity(bio)) {
 		int ret;
 
-		ret = bio_integrity_clone(b, bio, gfp_mask);
+		ret = bio_integrity_clone(b, bio, gfp_mask, fs_bio_set);
 
 		if (ret < 0) {
 			bio_put(b);
@@ -1539,6 +1539,7 @@ void bioset_free(struct bio_set *bs)
 	if (bs->bio_pool)
 		mempool_destroy(bs->bio_pool);
 
+	bioset_integrity_free(bs);
 	biovec_free_pools(bs);
 	bio_put_slab(bs);
 
@@ -1579,6 +1580,9 @@ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
 	if (!bs->bio_pool)
 		goto bad;
 
+	if (bioset_integrity_create(bs, pool_size))
+		goto bad;
+
 	if (!biovec_create_pools(bs, pool_size))
 		return bs;
 
@@ -1616,6 +1620,7 @@ static int __init init_bio(void)
 	if (!bio_slabs)
 		panic("bio: can't allocate bios\n");
 
+	bio_integrity_init();
 	biovec_init_slabs();
 
 	fs_bio_set = bioset_create(BIO_POOL_SIZE, 0);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 2a04eb54c0dd..2892b710771c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -319,7 +319,6 @@ static inline int bio_has_allocated_vec(struct bio *bio)
  */
 struct bio_integrity_payload {
 	struct bio		*bip_bio;	/* parent bio */
-	struct bio_vec		*bip_vec;	/* integrity data vector */
 
 	sector_t		bip_sector;	/* virtual start sector */
 
@@ -328,11 +327,12 @@ struct bio_integrity_payload {
 
 	unsigned int		bip_size;
 
-	unsigned short		bip_pool;	/* pool the ivec came from */
+	unsigned short		bip_slab;	/* slab the bip came from */
 	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
 	unsigned short		bip_idx;	/* current bip_vec index */
 
 	struct work_struct	bip_work;	/* I/O completion */
+	struct bio_vec		bip_vec[0];	/* embedded bvec array */
 };
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
@@ -430,6 +430,9 @@ struct bio_set {
 	unsigned int front_pad;
 
 	mempool_t *bio_pool;
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+	mempool_t *bio_integrity_pool;
+#endif
 	mempool_t *bvec_pool;
 };
 
@@ -634,8 +637,9 @@ static inline struct bio *bio_list_get(struct bio_list *bl)
 
 #define bio_integrity(bio) (bio->bi_integrity != NULL)
 
+extern struct bio_integrity_payload *bio_integrity_alloc_bioset(struct bio *, gfp_t, unsigned int, struct bio_set *);
 extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
-extern void bio_integrity_free(struct bio *);
+extern void bio_integrity_free(struct bio *, struct bio_set *);
 extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
 extern int bio_integrity_enabled(struct bio *bio);
 extern int bio_integrity_set_tag(struct bio *, void *, unsigned int);
@@ -645,21 +649,27 @@ extern void bio_integrity_endio(struct bio *, int);
 extern void bio_integrity_advance(struct bio *, unsigned int);
 extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int);
 extern void bio_integrity_split(struct bio *, struct bio_pair *, int);
-extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
+extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t, struct bio_set *);
+extern int bioset_integrity_create(struct bio_set *, int);
+extern void bioset_integrity_free(struct bio_set *);
+extern void bio_integrity_init(void);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 #define bio_integrity(a)		(0)
+#define bioset_integrity_create(a, b)	(0)
 #define bio_integrity_prep(a)		(0)
 #define bio_integrity_enabled(a)	(0)
-#define bio_integrity_clone(a, b, c)	(0)
-#define bio_integrity_free(a)		do { } while (0)
+#define bio_integrity_clone(a, b, c, d)	(0)
+#define bioset_integrity_free(a)	do { } while (0)
+#define bio_integrity_free(a, b)	do { } while (0)
 #define bio_integrity_endio(a, b)	do { } while (0)
 #define bio_integrity_advance(a, b)	do { } while (0)
 #define bio_integrity_trim(a, b, c)	do { } while (0)
 #define bio_integrity_split(a, b, c)	do { } while (0)
 #define bio_integrity_set_tag(a, b, c)	do { } while (0)
 #define bio_integrity_get_tag(a, b, c)	do { } while (0)
+#define bio_integrity_init(a)		do { } while (0)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-- 
cgit v1.2.3


From 018e0446890661504783f92388ecce7138c1566d Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Fri, 26 Jun 2009 16:27:10 +0200
Subject: block: get rid of queue-private command filter

The initial patches to support this through sysfs export were broken
and have been if 0'ed out in any release. So lets just kill the code
and reclaim some space in struct request_queue, if anyone would later
like to fixup the sysfs bits, the git history can easily restore
the removed bits.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/Makefile         |   2 +-
 block/blk-core.c       |   2 -
 block/bsg.c            |   2 +-
 block/cmd-filter.c     | 233 -------------------------------------------------
 block/scsi_ioctl.c     |  43 +++++++--
 drivers/scsi/sg.c      |   4 +-
 include/linux/blkdev.h |  15 +---
 7 files changed, 42 insertions(+), 259 deletions(-)
 delete mode 100644 block/cmd-filter.c

(limited to 'include')

diff --git a/block/Makefile b/block/Makefile
index e9fa4dd690f2..6c54ed0ff755 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-barrier.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
-			ioctl.o genhd.o scsi_ioctl.o cmd-filter.o
+			ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
diff --git a/block/blk-core.c b/block/blk-core.c
index 345d99da8d41..02b87134a167 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -595,8 +595,6 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 
 	q->sg_reserved_size = INT_MAX;
 
-	blk_set_cmd_filter_defaults(&q->cmd_filter);
-
 	/*
 	 * all done
 	 */
diff --git a/block/bsg.c b/block/bsg.c
index e7d475254248..5f184bb3ff9e 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -186,7 +186,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 		return -EFAULT;
 
 	if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) {
-		if (blk_verify_command(&q->cmd_filter, rq->cmd, has_write_perm))
+		if (blk_verify_command(rq->cmd, has_write_perm))
 			return -EPERM;
 	} else if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
diff --git a/block/cmd-filter.c b/block/cmd-filter.c
deleted file mode 100644
index 572bbc2f900d..000000000000
--- a/block/cmd-filter.c
+++ /dev/null
@@ -1,233 +0,0 @@
-/*
- * Copyright 2004 Peter M. Jones <pjones@redhat.com>
- *
- * 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- *
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public Licens
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
- *
- */
-
-#include <linux/list.h>
-#include <linux/genhd.h>
-#include <linux/spinlock.h>
-#include <linux/capability.h>
-#include <linux/bitops.h>
-#include <linux/blkdev.h>
-
-#include <scsi/scsi.h>
-#include <linux/cdrom.h>
-
-int blk_verify_command(struct blk_cmd_filter *filter,
-		       unsigned char *cmd, fmode_t has_write_perm)
-{
-	/* root can do any command. */
-	if (capable(CAP_SYS_RAWIO))
-		return 0;
-
-	/* if there's no filter set, assume we're filtering everything out */
-	if (!filter)
-		return -EPERM;
-
-	/* Anybody who can open the device can do a read-safe command */
-	if (test_bit(cmd[0], filter->read_ok))
-		return 0;
-
-	/* Write-safe commands require a writable open */
-	if (test_bit(cmd[0], filter->write_ok) && has_write_perm)
-		return 0;
-
-	return -EPERM;
-}
-EXPORT_SYMBOL(blk_verify_command);
-
-#if 0
-/* and now, the sysfs stuff */
-static ssize_t rcf_cmds_show(struct blk_cmd_filter *filter, char *page,
-			     int rw)
-{
-	char *npage = page;
-	unsigned long *okbits;
-	int i;
-
-	if (rw == READ)
-		okbits = filter->read_ok;
-	else
-		okbits = filter->write_ok;
-
-	for (i = 0; i < BLK_SCSI_MAX_CMDS; i++) {
-		if (test_bit(i, okbits)) {
-			npage += sprintf(npage, "0x%02x", i);
-			if (i < BLK_SCSI_MAX_CMDS - 1)
-				sprintf(npage++, " ");
-		}
-	}
-
-	if (npage != page)
-		npage += sprintf(npage, "\n");
-
-	return npage - page;
-}
-
-static ssize_t rcf_readcmds_show(struct blk_cmd_filter *filter, char *page)
-{
-	return rcf_cmds_show(filter, page, READ);
-}
-
-static ssize_t rcf_writecmds_show(struct blk_cmd_filter *filter,
-				 char *page)
-{
-	return rcf_cmds_show(filter, page, WRITE);
-}
-
-static ssize_t rcf_cmds_store(struct blk_cmd_filter *filter,
-			      const char *page, size_t count, int rw)
-{
-	unsigned long okbits[BLK_SCSI_CMD_PER_LONG], *target_okbits;
-	int cmd, set;
-	char *p, *status;
-
-	if (rw == READ) {
-		memcpy(&okbits, filter->read_ok, sizeof(okbits));
-		target_okbits = filter->read_ok;
-	} else {
-		memcpy(&okbits, filter->write_ok, sizeof(okbits));
-		target_okbits = filter->write_ok;
-	}
-
-	while ((p = strsep((char **)&page, " ")) != NULL) {
-		set = 1;
-
-		if (p[0] == '+') {
-			p++;
-		} else if (p[0] == '-') {
-			set = 0;
-			p++;
-		}
-
-		cmd = simple_strtol(p, &status, 16);
-
-		/* either of these cases means invalid input, so do nothing. */
-		if ((status == p) || cmd >= BLK_SCSI_MAX_CMDS)
-			return -EINVAL;
-
-		if (set)
-			__set_bit(cmd, okbits);
-		else
-			__clear_bit(cmd, okbits);
-	}
-
-	memcpy(target_okbits, okbits, sizeof(okbits));
-	return count;
-}
-
-static ssize_t rcf_readcmds_store(struct blk_cmd_filter *filter,
-				  const char *page, size_t count)
-{
-	return rcf_cmds_store(filter, page, count, READ);
-}
-
-static ssize_t rcf_writecmds_store(struct blk_cmd_filter *filter,
-				   const char *page, size_t count)
-{
-	return rcf_cmds_store(filter, page, count, WRITE);
-}
-
-struct rcf_sysfs_entry {
-	struct attribute attr;
-	ssize_t (*show)(struct blk_cmd_filter *, char *);
-	ssize_t (*store)(struct blk_cmd_filter *, const char *, size_t);
-};
-
-static struct rcf_sysfs_entry rcf_readcmds_entry = {
-	.attr = { .name = "read_table", .mode = S_IRUGO | S_IWUSR },
-	.show = rcf_readcmds_show,
-	.store = rcf_readcmds_store,
-};
-
-static struct rcf_sysfs_entry rcf_writecmds_entry = {
-	.attr = {.name = "write_table", .mode = S_IRUGO | S_IWUSR },
-	.show = rcf_writecmds_show,
-	.store = rcf_writecmds_store,
-};
-
-static struct attribute *default_attrs[] = {
-	&rcf_readcmds_entry.attr,
-	&rcf_writecmds_entry.attr,
-	NULL,
-};
-
-#define to_rcf(atr) container_of((atr), struct rcf_sysfs_entry, attr)
-
-static ssize_t
-rcf_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
-{
-	struct rcf_sysfs_entry *entry = to_rcf(attr);
-	struct blk_cmd_filter *filter;
-
-	filter = container_of(kobj, struct blk_cmd_filter, kobj);
-	if (entry->show)
-		return entry->show(filter, page);
-
-	return 0;
-}
-
-static ssize_t
-rcf_attr_store(struct kobject *kobj, struct attribute *attr,
-			const char *page, size_t length)
-{
-	struct rcf_sysfs_entry *entry = to_rcf(attr);
-	struct blk_cmd_filter *filter;
-
-	if (!capable(CAP_SYS_RAWIO))
-		return -EPERM;
-
-	if (!entry->store)
-		return -EINVAL;
-
-	filter = container_of(kobj, struct blk_cmd_filter, kobj);
-	return entry->store(filter, page, length);
-}
-
-static struct sysfs_ops rcf_sysfs_ops = {
-	.show = rcf_attr_show,
-	.store = rcf_attr_store,
-};
-
-static struct kobj_type rcf_ktype = {
-	.sysfs_ops = &rcf_sysfs_ops,
-	.default_attrs = default_attrs,
-};
-
-int blk_register_filter(struct gendisk *disk)
-{
-	int ret;
-	struct blk_cmd_filter *filter = &disk->queue->cmd_filter;
-
-	ret = kobject_init_and_add(&filter->kobj, &rcf_ktype,
-				   &disk_to_dev(disk)->kobj,
-				   "%s", "cmd_filter");
-	if (ret < 0)
-		return ret;
-
-	return 0;
-}
-EXPORT_SYMBOL(blk_register_filter);
-
-void blk_unregister_filter(struct gendisk *disk)
-{
-	struct blk_cmd_filter *filter = &disk->queue->cmd_filter;
-
-	kobject_put(&filter->kobj);
-}
-EXPORT_SYMBOL(blk_unregister_filter);
-#endif
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 5f8e798ede4e..f0e0ce0a607d 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -32,6 +32,11 @@
 #include <scsi/scsi_ioctl.h>
 #include <scsi/scsi_cmnd.h>
 
+struct blk_cmd_filter {
+	unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
+	unsigned long write_ok[BLK_SCSI_CMD_PER_LONG];
+} blk_default_cmd_filter;
+
 /* Command group 3 is reserved and should never be used.  */
 const unsigned char scsi_command_size_tbl[8] =
 {
@@ -105,7 +110,7 @@ static int sg_emulated_host(struct request_queue *q, int __user *p)
 	return put_user(1, p);
 }
 
-void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
+static void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 {
 	/* Basic read-only commands */
 	__set_bit(TEST_UNIT_READY, filter->read_ok);
@@ -187,14 +192,37 @@ void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter)
 	__set_bit(GPCMD_SET_STREAMING, filter->write_ok);
 	__set_bit(GPCMD_SET_READ_AHEAD, filter->write_ok);
 }
-EXPORT_SYMBOL_GPL(blk_set_cmd_filter_defaults);
+
+int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm)
+{
+	struct blk_cmd_filter *filter = &blk_default_cmd_filter;
+
+	/* root can do any command. */
+	if (capable(CAP_SYS_RAWIO))
+		return 0;
+
+	/* if there's no filter set, assume we're filtering everything out */
+	if (!filter)
+		return -EPERM;
+
+	/* Anybody who can open the device can do a read-safe command */
+	if (test_bit(cmd[0], filter->read_ok))
+		return 0;
+
+	/* Write-safe commands require a writable open */
+	if (test_bit(cmd[0], filter->write_ok) && has_write_perm)
+		return 0;
+
+	return -EPERM;
+}
+EXPORT_SYMBOL(blk_verify_command);
 
 static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 			     struct sg_io_hdr *hdr, fmode_t mode)
 {
 	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
-	if (blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE))
+	if (blk_verify_command(rq->cmd, mode & FMODE_WRITE))
 		return -EPERM;
 
 	/*
@@ -427,7 +455,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
 		goto error;
 
-	err = blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE);
+	err = blk_verify_command(rq->cmd, mode & FMODE_WRITE);
 	if (err)
 		goto error;
 
@@ -645,5 +673,10 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod
 	blk_put_queue(q);
 	return err;
 }
-
 EXPORT_SYMBOL(scsi_cmd_ioctl);
+
+int __init blk_scsi_ioctl_init(void)
+{
+	blk_set_cmd_filter_defaults(&blk_default_cmd_filter);
+	return 0;
+}
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 8201387b4daa..ef142fd47a83 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -210,13 +210,11 @@ static void sg_put_dev(Sg_device *sdp);
 static int sg_allow_access(struct file *filp, unsigned char *cmd)
 {
 	struct sg_fd *sfp = (struct sg_fd *)filp->private_data;
-	struct request_queue *q = sfp->parentdp->device->request_queue;
 
 	if (sfp->parentdp->device->type == TYPE_SCANNER)
 		return 0;
 
-	return blk_verify_command(&q->cmd_filter,
-				  cmd, filp->f_mode & FMODE_WRITE);
+	return blk_verify_command(cmd, filp->f_mode & FMODE_WRITE);
 }
 
 static int
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8963d9149b5f..49ae07951d55 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -301,12 +301,6 @@ struct blk_queue_tag {
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
 
-struct blk_cmd_filter {
-	unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
-	unsigned long write_ok[BLK_SCSI_CMD_PER_LONG];
-	struct kobject kobj;
-};
-
 struct queue_limits {
 	unsigned long		bounce_pfn;
 	unsigned long		seg_boundary_mask;
@@ -445,7 +439,6 @@ struct request_queue
 #if defined(CONFIG_BLK_DEV_BSG)
 	struct bsg_class_device bsg_dev;
 #endif
-	struct blk_cmd_filter cmd_filter;
 };
 
 #define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
@@ -998,13 +991,7 @@ static inline int sb_issue_discard(struct super_block *sb,
 	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL);
 }
 
-/*
-* command filter functions
-*/
-extern int blk_verify_command(struct blk_cmd_filter *filter,
-			      unsigned char *cmd, fmode_t has_write_perm);
-extern void blk_unregister_filter(struct gendisk *disk);
-extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
+extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
 
 #define MAX_PHYS_SEGMENTS 128
 #define MAX_HW_SEGMENTS 128
-- 
cgit v1.2.3


From 887b5ea3683ce04966e35fa2e5fe215bedcde73c Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Wed, 1 Jul 2009 13:38:26 +0000
Subject: if_ether: add define for 1588 aka Timesync

This patch adds ETH_P_1588 protocol ID define.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_ether.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index ae3a1871413d..70fdba2bbf71 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -78,6 +78,7 @@
 #define ETH_P_PAE	0x888E		/* Port Access Entity (IEEE 802.1X) */
 #define ETH_P_AOE	0x88A2		/* ATA over Ethernet		*/
 #define ETH_P_TIPC	0x88CA		/* TIPC 			*/
+#define ETH_P_1588	0x88F7		/* IEEE 1588 Timesync */
 #define ETH_P_FCOE	0x8906		/* Fibre Channel over Ethernet  */
 #define ETH_P_FIP	0x8914		/* FCoE Initialization Protocol */
 #define ETH_P_EDSA	0xDADA		/* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */
-- 
cgit v1.2.3


From 509dd025a4ac6f32921211557cfd434b81d8d7a7 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@redhat.com>
Date: Tue, 30 Jun 2009 16:07:26 -0300
Subject: V4L/DVB (12148): move V4L2_PIX_FMT_SGRBG8 to the proper place

Instead of defining a new pif format on an internal header, move it to
the V4L2 API header.

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/gspca/stv06xx/stv06xx.h | 4 ----
 include/linux/videodev2.h                   | 2 ++
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/gspca/stv06xx/stv06xx.h b/drivers/media/video/gspca/stv06xx/stv06xx.h
index 9df7137fe67e..992ce530f138 100644
--- a/drivers/media/video/gspca/stv06xx/stv06xx.h
+++ b/drivers/media/video/gspca/stv06xx/stv06xx.h
@@ -36,10 +36,6 @@
 
 #define STV_ISOC_ENDPOINT_ADDR		0x81
 
-#ifndef V4L2_PIX_FMT_SGRBG8
-#define V4L2_PIX_FMT_SGRBG8 v4l2_fourcc('G', 'R', 'B', 'G')
-#endif
-
 #define STV_REG23 			0x0423
 
 /* Control registers of the STV0600 ASIC */
diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h
index 8a025d510904..95846d988011 100644
--- a/include/linux/videodev2.h
+++ b/include/linux/videodev2.h
@@ -318,6 +318,8 @@ struct v4l2_pix_format {
 /* see http://www.siliconimaging.com/RGB%20Bayer.htm */
 #define V4L2_PIX_FMT_SBGGR8  v4l2_fourcc('B', 'A', '8', '1') /*  8  BGBG.. GRGR.. */
 #define V4L2_PIX_FMT_SGBRG8  v4l2_fourcc('G', 'B', 'R', 'G') /*  8  GBGB.. RGRG.. */
+#define V4L2_PIX_FMT_SGRBG8  v4l2_fourcc('G', 'R', 'B', 'G') /*  8  GRGR.. BGBG.. */
+
 /*
  * 10bit raw bayer, expanded to 16 bits
  * xxxxrrrrrrrrrrxxxxgggggggggg xxxxggggggggggxxxxbbbbbbbbbb...
-- 
cgit v1.2.3


From 7dfba00d05f3c7db9510f3b54a472981cf1521af Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@redhat.com>
Date: Mon, 29 Jun 2009 05:41:26 -0300
Subject: V4L/DVB (12135): Add a driver for mt9v011 sensor

Adds driver for mt9v011 based on its datasheet, available at:
	http://download.micron.com/pdf/datasheets/imaging/MT9V011.pdf

The driver was tested with a webcam that will be added on a next patch.

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/Kconfig     |   8 +
 drivers/media/video/Makefile    |   1 +
 drivers/media/video/mt9v011.c   | 355 ++++++++++++++++++++++++++++++++++++++++
 drivers/media/video/mt9v011.h   |  35 ++++
 include/media/v4l2-chip-ident.h |   3 +
 5 files changed, 402 insertions(+)
 create mode 100644 drivers/media/video/mt9v011.c
 create mode 100644 drivers/media/video/mt9v011.h

(limited to 'include')

diff --git a/drivers/media/video/Kconfig b/drivers/media/video/Kconfig
index 061e147f6f26..84b6fc15519d 100644
--- a/drivers/media/video/Kconfig
+++ b/drivers/media/video/Kconfig
@@ -312,6 +312,14 @@ config VIDEO_OV7670
 	  OV7670 VGA camera.  It currently only works with the M88ALP01
 	  controller.
 
+config VIDEO_MT9V011
+	tristate "Micron mt9v011 sensor support"
+	depends on I2C && VIDEO_V4L2
+	---help---
+	  This is a Video4Linux2 sensor-level driver for the Micron
+	  mt0v011 1.3 Mpixel camera.  It currently only works with the
+	  em28xx driver.
+
 config VIDEO_TCM825X
 	tristate "TCM825x camera sensor support"
 	depends on I2C && VIDEO_V4L2
diff --git a/drivers/media/video/Makefile b/drivers/media/video/Makefile
index 7fb3add1b387..9f2e3214a482 100644
--- a/drivers/media/video/Makefile
+++ b/drivers/media/video/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_VIDEO_UPD64083) += upd64083.o
 obj-$(CONFIG_VIDEO_OV7670) 	+= ov7670.o
 obj-$(CONFIG_VIDEO_TCM825X) += tcm825x.o
 obj-$(CONFIG_VIDEO_TVEEPROM) += tveeprom.o
+obj-$(CONFIG_VIDEO_MT9V011) += mt9v011.o
 
 obj-$(CONFIG_SOC_CAMERA_MT9M001)	+= mt9m001.o
 obj-$(CONFIG_SOC_CAMERA_MT9M111)	+= mt9m111.o
diff --git a/drivers/media/video/mt9v011.c b/drivers/media/video/mt9v011.c
new file mode 100644
index 000000000000..4389197cedd7
--- /dev/null
+++ b/drivers/media/video/mt9v011.c
@@ -0,0 +1,355 @@
+/*
+ * mt9v011 -Micron 1/4-Inch VGA Digital Image Sensor
+ *
+ * Copyright (c) 2009 Mauro Carvalho Chehab (mchehab@redhat.com)
+ * This code is placed under the terms of the GNU General Public License v2
+ */
+
+#include <linux/i2c.h>
+#include <linux/videodev2.h>
+#include <linux/delay.h>
+#include <media/v4l2-device.h>
+#include "mt9v011.h"
+#include <media/v4l2-i2c-drv.h>
+#include <media/v4l2-chip-ident.h>
+
+MODULE_DESCRIPTION("Micron mt9v011 sensor driver");
+MODULE_AUTHOR("Mauro Carvalho Chehab <mchehab@redhat.com>");
+MODULE_LICENSE("GPL");
+
+
+static int debug;
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Debug level (0-2)");
+
+/* supported controls */
+static struct v4l2_queryctrl mt9v011_qctrl[] = {
+	{
+		.id = V4L2_CID_GAIN,
+		.type = V4L2_CTRL_TYPE_INTEGER,
+		.name = "Gain",
+		.minimum = 0,
+		.maximum = (1 << 10) - 1,
+		.step = 1,
+		.default_value = 0x0020,
+		.flags = 0,
+	}, {
+		.id = V4L2_CID_RED_BALANCE,
+		.type = V4L2_CTRL_TYPE_INTEGER,
+		.name = "Red Balance",
+		.minimum = -1 << 9,
+		.maximum = (1 << 9) - 1,
+		.step = 1,
+		.default_value = 0,
+		.flags = 0,
+	}, {
+		.id = V4L2_CID_BLUE_BALANCE,
+		.type = V4L2_CTRL_TYPE_INTEGER,
+		.name = "Blue Balance",
+		.minimum = -1 << 9,
+		.maximum = (1 << 9) - 1,
+		.step = 1,
+		.default_value = 0,
+		.flags = 0,
+	},
+};
+
+struct mt9v011 {
+	struct v4l2_subdev sd;
+
+	u16 global_gain, red_bal, blue_bal;
+};
+
+static inline struct mt9v011 *to_mt9v011(struct v4l2_subdev *sd)
+{
+	return container_of(sd, struct mt9v011, sd);
+}
+
+static int mt9v011_read(struct v4l2_subdev *sd, unsigned char addr)
+{
+	struct i2c_client *c = v4l2_get_subdevdata(sd);
+	__be16 buffer;
+	int rc, val;
+
+	if (1 != (rc = i2c_master_send(c, &addr, 1)))
+		v4l2_dbg(0, debug, sd,
+			 "i2c i/o error: rc == %d (should be 1)\n", rc);
+
+	msleep(10);
+
+	if (2 != (rc = i2c_master_recv(c, (char *)&buffer, 2)))
+		v4l2_dbg(0, debug, sd,
+			 "i2c i/o error: rc == %d (should be 1)\n", rc);
+
+	val = be16_to_cpu(buffer);
+
+	v4l2_dbg(2, debug, sd, "mt9v011: read 0x%02x = 0x%04x\n", addr, val);
+
+	return val;
+}
+
+static void mt9v011_write(struct v4l2_subdev *sd, unsigned char addr,
+				 u16 value)
+{
+	struct i2c_client *c = v4l2_get_subdevdata(sd);
+	unsigned char buffer[3];
+	int rc;
+
+	buffer[0] = addr;
+	buffer[1] = value >> 8;
+	buffer[2] = value & 0xff;
+
+	v4l2_dbg(2, debug, sd,
+		 "mt9v011: writing 0x%02x 0x%04x\n", buffer[0], value);
+	if (3 != (rc = i2c_master_send(c, buffer, 3)))
+		v4l2_dbg(0, debug, sd,
+			 "i2c i/o error: rc == %d (should be 3)\n", rc);
+}
+
+
+struct i2c_reg_value {
+	unsigned char reg;
+	u16           value;
+};
+
+/*
+ * Values used at the original driver
+ * Some values are marked as Reserved at the datasheet
+ */
+static const struct i2c_reg_value mt9v011_init_default[] = {
+					/* guessed meaning - as mt9m111 */
+		{ R0D_MT9V011_RESET, 0x0001 },
+		{ R0D_MT9V011_RESET, 0x0000 },
+		{ R01_MT9V011_ROWSTART, 0x0008 },
+		{ R02_MT9V011_COLSTART, 0x0014 },
+		{ R03_MT9V011_HEIGHT, 0x01e0 },
+		{ R04_MT9V011_WIDTH, 0x0280 },
+		{ R05_MT9V011_HBLANK, 0x0001 },
+		{ R05_MT9V011_HBLANK, 0x0001 },
+		{ R0A_MT9V011_CLK_SPEED, 0x0000 },
+		{ R05_MT9V011_HBLANK, 0x000a },
+		{ 0x30, 0x0005 },
+		{ 0x34, 0x0100 },
+		{ 0x3d, 0x068f },
+		{ 0x40, 0x01e0 },
+		{ 0x52, 0x0100 },
+		{ 0x58, 0x0038 },	/* Datasheet default 0x0078 */
+		{ 0x59, 0x0723 },	/* Datasheet default 0x0703 */
+		{ 0x62, 0x041a },	/* Datasheet default 0x0418 */
+		{ R09_MT9V011_SHUTTER_WIDTH, 0x0418 },
+		{ R20_MT9V011_READ_MODE, 0x1100 },
+};
+
+static void set_balance(struct v4l2_subdev *sd)
+{
+	struct mt9v011 *core = to_mt9v011(sd);
+	u16 green1_gain, green2_gain, blue_gain, red_gain;
+
+	green1_gain = core->global_gain;
+	green2_gain = core->global_gain;
+
+	blue_gain = core->global_gain +
+		    core->global_gain * core->blue_bal / (1 << 9);
+
+	red_gain = core->global_gain +
+		   core->global_gain * core->blue_bal / (1 << 9);
+
+	mt9v011_write(sd, R2B_MT9V011_GREEN_1_GAIN, green1_gain);
+	mt9v011_write(sd, R2E_MT9V011_GREEN_2_GAIN,  green1_gain);
+	mt9v011_write(sd, R2C_MT9V011_BLUE_GAIN, blue_gain);
+	mt9v011_write(sd, R2D_MT9V011_RED_GAIN, red_gain);
+}
+
+static int mt9v011_reset(struct v4l2_subdev *sd, u32 val)
+{
+	u16 version;
+	int i;
+
+	version = mt9v011_read(sd, R00_MT9V011_CHIP_VERSION);
+
+	if (version != MT9V011_VERSION) {
+		v4l2_info(sd, "*** unknown micron chip detected (0x%04x.\n",
+			  version);
+		return -EINVAL;
+
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt9v011_init_default); i++)
+		mt9v011_write(sd, mt9v011_init_default[i].reg,
+			       mt9v011_init_default[i].value);
+
+	set_balance(sd);
+
+	return 0;
+};
+
+static int mt9v011_g_ctrl(struct v4l2_subdev *sd, struct v4l2_control *ctrl)
+{
+	struct mt9v011 *core = to_mt9v011(sd);
+
+	v4l2_dbg(1, debug, sd, "g_ctrl called\n");
+
+	switch (ctrl->id) {
+	case V4L2_CID_GAIN:
+		ctrl->value = core->global_gain;
+		return 0;
+	case V4L2_CID_RED_BALANCE:
+		ctrl->value = core->red_bal;
+		return 0;
+	case V4L2_CID_BLUE_BALANCE:
+		ctrl->value = core->blue_bal;
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int mt9v011_s_ctrl(struct v4l2_subdev *sd, struct v4l2_control *ctrl)
+{
+	struct mt9v011 *core = to_mt9v011(sd);
+	u8 i, n;
+	n = ARRAY_SIZE(mt9v011_qctrl);
+
+	for (i = 0; i < n; i++) {
+		if (ctrl->id != mt9v011_qctrl[i].id)
+			continue;
+		if (ctrl->value < mt9v011_qctrl[i].minimum ||
+		    ctrl->value > mt9v011_qctrl[i].maximum)
+			return -ERANGE;
+		v4l2_dbg(1, debug, sd, "s_ctrl: id=%d, value=%d\n",
+					ctrl->id, ctrl->value);
+		break;
+	}
+
+	switch (ctrl->id) {
+	case V4L2_CID_GAIN:
+		core->global_gain = ctrl->value;
+		break;
+	case V4L2_CID_RED_BALANCE:
+		core->red_bal = ctrl->value;
+		break;
+	case V4L2_CID_BLUE_BALANCE:
+		core->blue_bal = ctrl->value;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	set_balance(sd);
+
+	return 0;
+}
+
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+static int mt9v011_g_register(struct v4l2_subdev *sd,
+			      struct v4l2_dbg_register *reg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	if (!v4l2_chip_match_i2c_client(client, &reg->match))
+		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	reg->val = mt9v011_read(sd, reg->reg & 0xff);
+	reg->size = 2;
+
+	return 0;
+}
+
+static int mt9v011_s_register(struct v4l2_subdev *sd,
+			      struct v4l2_dbg_register *reg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	if (!v4l2_chip_match_i2c_client(client, &reg->match))
+		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	mt9v011_write(sd, reg->reg & 0xff, reg->val & 0xffff);
+
+	return 0;
+}
+#endif
+
+static int mt9v011_g_chip_ident(struct v4l2_subdev *sd,
+				struct v4l2_dbg_chip_ident *chip)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	return v4l2_chip_ident_i2c_client(client, chip, V4L2_IDENT_MT9V011,
+					  MT9V011_VERSION);
+}
+
+static const struct v4l2_subdev_core_ops mt9v011_core_ops = {
+	.g_ctrl = mt9v011_g_ctrl,
+	.s_ctrl = mt9v011_s_ctrl,
+	.reset = mt9v011_reset,
+	.g_chip_ident = mt9v011_g_chip_ident,
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+	.g_register = mt9v011_g_register,
+	.s_register = mt9v011_s_register,
+#endif
+};
+
+static const struct v4l2_subdev_ops mt9v011_ops = {
+	.core = &mt9v011_core_ops,
+};
+
+
+/****************************************************************************
+			I2C Client & Driver
+ ****************************************************************************/
+
+static int mt9v011_probe(struct i2c_client *c,
+			 const struct i2c_device_id *id)
+{
+	struct mt9v011 *core;
+	struct v4l2_subdev *sd;
+
+	/* Check if the adapter supports the needed features */
+	if (!i2c_check_functionality(c->adapter,
+	     I2C_FUNC_SMBUS_READ_BYTE | I2C_FUNC_SMBUS_WRITE_BYTE_DATA))
+		return -EIO;
+
+	core = kzalloc(sizeof(struct mt9v011), GFP_KERNEL);
+	if (!core)
+		return -ENOMEM;
+
+	core->global_gain = 0x0024;
+
+	sd = &core->sd;
+	v4l2_i2c_subdev_init(sd, c, &mt9v011_ops);
+	v4l_info(c, "chip found @ 0x%02x (%s)\n",
+		 c->addr << 1, c->adapter->name);
+
+	return 0;
+}
+
+static int mt9v011_remove(struct i2c_client *c)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(c);
+
+	v4l2_dbg(1, debug, sd,
+		"mt9v011.c: removing mt9v011 adapter on address 0x%x\n",
+		c->addr << 1);
+
+	v4l2_device_unregister_subdev(sd);
+	kfree(to_mt9v011(sd));
+	return 0;
+}
+
+/* ----------------------------------------------------------------------- */
+
+static const struct i2c_device_id mt9v011_id[] = {
+	{ "mt9v011", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, mt9v011_id);
+
+static struct v4l2_i2c_driver_data v4l2_i2c_data = {
+	.name = "mt9v011",
+	.probe = mt9v011_probe,
+	.remove = mt9v011_remove,
+	.id_table = mt9v011_id,
+};
diff --git a/drivers/media/video/mt9v011.h b/drivers/media/video/mt9v011.h
new file mode 100644
index 000000000000..9e443ee30558
--- /dev/null
+++ b/drivers/media/video/mt9v011.h
@@ -0,0 +1,35 @@
+/*
+ * mt9v011 -Micron 1/4-Inch VGA Digital Image Sensor
+ *
+ * Copyright (c) 2009 Mauro Carvalho Chehab (mchehab@redhat.com)
+ * This code is placed under the terms of the GNU General Public License v2
+ */
+
+#ifndef MT9V011_H_
+#define MT9V011_H_
+
+#define R00_MT9V011_CHIP_VERSION	0x00
+#define R01_MT9V011_ROWSTART		0x01
+#define R02_MT9V011_COLSTART		0x02
+#define R03_MT9V011_HEIGHT		0x03
+#define R04_MT9V011_WIDTH		0x04
+#define R05_MT9V011_HBLANK		0x05
+#define R06_MT9V011_VBLANK		0x06
+#define R07_MT9V011_OUT_CTRL		0x07
+#define R09_MT9V011_SHUTTER_WIDTH	0x09
+#define R0A_MT9V011_CLK_SPEED		0x0a
+#define R0B_MT9V011_RESTART		0x0b
+#define R0C_MT9V011_SHUTTER_DELAY	0x0c
+#define R0D_MT9V011_RESET		0x0d
+#define R1E_MT9V011_DIGITAL_ZOOM	0x1e
+#define R20_MT9V011_READ_MODE		0x20
+#define R2B_MT9V011_GREEN_1_GAIN	0x2b
+#define R2C_MT9V011_BLUE_GAIN		0x2c
+#define R2D_MT9V011_RED_GAIN		0x2d
+#define R2E_MT9V011_GREEN_2_GAIN	0x2e
+#define R35_MT9V011_GLOBAL_GAIN		0x35
+#define RF1_MT9V011_CHIP_ENABLE		0xf1
+
+#define MT9V011_VERSION			0x8243
+
+#endif
diff --git a/include/media/v4l2-chip-ident.h b/include/media/v4l2-chip-ident.h
index 4d7e2272c42f..11a4a2d3e364 100644
--- a/include/media/v4l2-chip-ident.h
+++ b/include/media/v4l2-chip-ident.h
@@ -155,6 +155,9 @@ enum {
 	/* module cafe_ccic, just ident 8801 */
 	V4L2_IDENT_CAFE = 8801,
 
+	/* module mt9v011, just ident 8243 */
+	V4L2_IDENT_MT9V011 = 8243,
+
 	/* module tw9910: just ident 9910 */
 	V4L2_IDENT_TW9910 = 9910,
 
-- 
cgit v1.2.3


From a65e7bfcd74e4c0939f235d2bf9f48ddb3a57991 Mon Sep 17 00:00:00 2001
From: Hui Zhu <teawater@gmail.com>
Date: Sun, 5 Jul 2009 12:08:15 -0700
Subject: elf: fix multithreaded program core dumping on arm

Fix the multithread program core thread message error.

This issue affects arches with neither has CORE_DUMP_USE_REGSET nor
ELF_CORE_COPY_TASK_REGS, ARM is one of them.

The thread message of core file is generated in elf_dump_thread_status.
The register values is set by elf_core_copy_task_regs in this function.

If an arch doesn't define ELF_CORE_COPY_TASK_REGS,
elf_core_copy_task_regs() will do nothing.  Then the core file will not
have the register message of thread.

So add elf_core_copy_regs to set regiser values if ELF_CORE_COPY_TASK_REGS
doesn't define.

The following is how to reproduce this issue:

cat 1.c
#include <stdio.h>
#include <pthread.h>
#include <assert.h>

void td1(void * i)
{
       while (1)
       {
               printf ("1\n");
               sleep (1);
       }

       return;
}

void td2(void * i)
{
       while (1)
       {
               printf ("2\n");
               sleep (1);
       }

       return;
}

int
main(int argc,char *argv[],char *envp[])
{
       pthread_t       t1,t2;

       pthread_create(&t1, NULL, (void*)td1, NULL);
       pthread_create(&t2, NULL, (void*)td2, NULL);

       sleep (10);

       assert(0);

       return (0);
}
arm-xxx-gcc -g -lpthread 1.c -o 1
copy 1.c and 1 to a arm board.
Goto this board.
ulimit -c 1800000
./1
# ./1
1
2
1
...
...
1
1: 1.c:37: main: Assertion `0' failed.
Aborted (core dumped)
Then you can get a core file.
gdb 1 core.xxx
Without the patch:
(gdb) info threads
 3 process 909  0x00000000 in ?? ()
 2 process 908  0x00000000 in ?? ()
* 1 process 907  0x4a6e2238 in raise () from /lib/libc.so.6
You can found that the pc of 909 and 908 is 0x00000000.
With the patch:
(gdb) info threads
 3 process 885  0x4a749974 in nanosleep () from /lib/libc.so.6
 2 process 884  0x4a749974 in nanosleep () from /lib/libc.so.6
* 1 process 883  0x4a6e2238 in raise () from /lib/libc.so.6
The pc of 885 and 884 is right.

Signed-off-by: Hui Zhu <teawater@gmail.com>
Cc: Amerigo Wang <xiyou.wangcong@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David Howells <dhowells@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Jakub Jelinek <jakub@redhat.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/elfcore.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 7605c5e9589f..03ec16779802 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -125,6 +125,8 @@ static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t*
 #ifdef ELF_CORE_COPY_TASK_REGS
 	
 	return ELF_CORE_COPY_TASK_REGS(t, elfregs);
+#else
+	elf_core_copy_regs(elfregs, task_pt_regs(t));
 #endif
 	return 0;
 }
-- 
cgit v1.2.3


From 82e3310ace59794ecf0f531eca94647b2863dfda Mon Sep 17 00:00:00 2001
From: Tobias Doerffel <tobias.doerffel@gmail.com>
Date: Sun, 5 Jul 2009 12:08:23 -0700
Subject: linux/sysrq.h needs linux/errno.h

In include/linux/sysrq.h the constant EINVAL is being used but is undefined
if include/linux/errno.h is not included before.

Fix this by adding #include <linux/errno.h> at the beginning.

Signed-off-by: Tobias Doerffel <tobias.doerffel@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sysrq.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h
index 98a1d8cfb73d..99adcdc0d3ca 100644
--- a/include/linux/sysrq.h
+++ b/include/linux/sysrq.h
@@ -14,6 +14,8 @@
 #ifndef _LINUX_SYSRQ_H
 #define _LINUX_SYSRQ_H
 
+#include <linux/errno.h>
+
 struct pt_regs;
 struct tty_struct;
 
-- 
cgit v1.2.3


From 7afdbf23c3acdec3eaf1b94f87132fff3d81ce73 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 7 Jul 2009 10:23:43 +0200
Subject: signals: declare sys_rt_tgsigqueueinfo in syscalls.h

sys_rt_tgsigqueueinfo needs to be declared in linux/syscalls.h so that
architectures defining the system call table in C can reference it.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
LKML-Reference: <200907071023.44008.arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/syscalls.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fa4242cdade8..80de7003d8c2 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -321,6 +321,8 @@ asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese,
 				siginfo_t __user *uinfo,
 				const struct timespec __user *uts,
 				size_t sigsetsize);
+asmlinkage long sys_rt_tgsigqueueinfo(pid_t tgid, pid_t  pid, int sig,
+		siginfo_t __user *uinfo);
 asmlinkage long sys_kill(int pid, int sig);
 asmlinkage long sys_tgkill(int tgid, int pid, int sig);
 asmlinkage long sys_tkill(int pid, int sig);
-- 
cgit v1.2.3


From e9bf0cc7cbfbf3952cdf8028aa0d348d09ecdba1 Mon Sep 17 00:00:00 2001
From: Parag Warudkar <parag.lkml@gmail.com>
Date: Wed, 8 Jul 2009 11:46:02 -0400
Subject: elfcore.h : Fix UML build breakage

Commit a65e7bfcd74e4c0939f235d2bf9f48ddb3a57991 broke the UML build with
the following error -

  In file included from fs/proc/kcore.c:17:
  include/linux/elfcore.h: In function 'elf_core_copy_task_regs':
  include/linux/elfcore.h:129: error: implicit declaration of function 'task_pt_regs'

Fix this by restoring the previous behavior of returning 0 for all arches
like UML that don't define task_pt_regs.

Signed-off-by: Parag Warudkar <parag.lkml@gmail.com>
Acked-by: Amerigo Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/elfcore.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 03ec16779802..00d6a68d0421 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -122,10 +122,9 @@ static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_r
 
 static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs)
 {
-#ifdef ELF_CORE_COPY_TASK_REGS
-	
+#if defined (ELF_CORE_COPY_TASK_REGS)
 	return ELF_CORE_COPY_TASK_REGS(t, elfregs);
-#else
+#elif defined (task_pt_regs)
 	elf_core_copy_regs(elfregs, task_pt_regs(t));
 #endif
 	return 0;
-- 
cgit v1.2.3


From b43f3cbd21ffbd719fd4fa6642bfe6af255ded34 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Wed, 8 Jul 2009 01:54:37 +0400
Subject: headers: mnt_namespace.h redux

Fix various silly problems wrt mnt_namespace.h:

 - exit_mnt_ns() isn't used, remove it
 - done that, sched.h and nsproxy.h inclusions aren't needed
 - mount.h inclusion was need for vfsmount_lock, but no longer
 - remove mnt_namespace.h inclusion from files which don't use anything
   from mnt_namespace.h

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/afs/mntpt.c                |  1 -
 fs/namespace.c                |  1 +
 fs/nfs/getroot.c              |  1 -
 fs/reiserfs/super.c           |  1 -
 include/linux/mnt_namespace.h | 13 ++-----------
 kernel/exit.c                 |  1 -
 kernel/fork.c                 |  1 -
 kernel/kmod.c                 |  1 -
 8 files changed, 3 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index c52be53f6946..5ffb570cd3a8 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -17,7 +17,6 @@
 #include <linux/pagemap.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
-#include <linux/mnt_namespace.h>
 #include "internal.h"
 
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 3dc283fd4716..277c28a63ead 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -22,6 +22,7 @@
 #include <linux/seq_file.h>
 #include <linux/mnt_namespace.h>
 #include <linux/namei.h>
+#include <linux/nsproxy.h>
 #include <linux/security.h>
 #include <linux/mount.h>
 #include <linux/ramfs.h>
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 46177cb87064..b35d2a616066 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -30,7 +30,6 @@
 #include <linux/nfs_idmap.h>
 #include <linux/vfs.h>
 #include <linux/namei.h>
-#include <linux/mnt_namespace.h>
 #include <linux/security.h>
 
 #include <asm/system.h>
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index d3aeb061612b..7adea74d6a8a 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -24,7 +24,6 @@
 #include <linux/exportfs.h>
 #include <linux/quotaops.h>
 #include <linux/vfs.h>
-#include <linux/mnt_namespace.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/crc32.h>
diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
index 3beb2592b03f..d74785c2393a 100644
--- a/include/linux/mnt_namespace.h
+++ b/include/linux/mnt_namespace.h
@@ -2,10 +2,9 @@
 #define _NAMESPACE_H_
 #ifdef __KERNEL__
 
-#include <linux/mount.h>
-#include <linux/sched.h>
-#include <linux/nsproxy.h>
+#include <linux/path.h>
 #include <linux/seq_file.h>
+#include <linux/wait.h>
 
 struct mnt_namespace {
 	atomic_t		count;
@@ -28,14 +27,6 @@ extern struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt);
 extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
 		struct fs_struct *);
 extern void put_mnt_ns(struct mnt_namespace *ns);
-
-static inline void exit_mnt_ns(struct task_struct *p)
-{
-	struct mnt_namespace *ns = p->nsproxy->mnt_ns;
-	if (ns)
-		put_mnt_ns(ns);
-}
-
 static inline void get_mnt_ns(struct mnt_namespace *ns)
 {
 	atomic_inc(&ns->count);
diff --git a/kernel/exit.c b/kernel/exit.c
index 628d41f0dd54..869dc221733e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -12,7 +12,6 @@
 #include <linux/completion.h>
 #include <linux/personality.h>
 #include <linux/tty.h>
-#include <linux/mnt_namespace.h>
 #include <linux/iocontext.h>
 #include <linux/key.h>
 #include <linux/security.h>
diff --git a/kernel/fork.c b/kernel/fork.c
index 467746b3f0aa..bd2959228871 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -17,7 +17,6 @@
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/completion.h>
-#include <linux/mnt_namespace.h>
 #include <linux/personality.h>
 #include <linux/mempolicy.h>
 #include <linux/sem.h>
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 7e95bedb2bfc..385c31a1bdbf 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -24,7 +24,6 @@
 #include <linux/unistd.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
-#include <linux/mnt_namespace.h>
 #include <linux/completion.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
-- 
cgit v1.2.3


From 1ce822fa04fd6878f079461a4b8affe4bb5ec27b Mon Sep 17 00:00:00 2001
From: Jaswinder Singh Rajput <jaswinder@kernel.org>
Date: Wed, 8 Jul 2009 21:25:54 +0530
Subject: includecheck fix: include/linux, rfkill.h

fix the following 'make includecheck' warning:

  include/linux/rfkill.h: linux/types.h is included more than once.

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/rfkill.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h
index e73e2429a1b1..2ce29831feb6 100644
--- a/include/linux/rfkill.h
+++ b/include/linux/rfkill.h
@@ -99,7 +99,6 @@ enum rfkill_user_states {
 #undef RFKILL_STATE_UNBLOCKED
 #undef RFKILL_STATE_HARD_BLOCKED
 
-#include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
-- 
cgit v1.2.3


From a57de0b4336e48db2811a2030bb68dba8dd09d88 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 8 Jul 2009 12:09:13 +0000
Subject: net: adding memory barrier to the poll and receive callbacks

Adding memory barrier after the poll_wait function, paired with
receive callbacks. Adding fuctions sock_poll_wait and sk_has_sleeper
to wrap the memory barrier.

Without the memory barrier, following race can happen.
The race fires, when following code paths meet, and the tp->rcv_nxt
and __add_wait_queue updates stay in CPU caches.

CPU1                         CPU2

sys_select                   receive packet
  ...                        ...
  __add_wait_queue           update tp->rcv_nxt
  ...                        ...
  tp->rcv_nxt check          sock_def_readable
  ...                        {
  schedule                      ...
                                if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
                                        wake_up_interruptible(sk->sk_sleep)
                                ...
                             }

If there was no cache the code would work ok, since the wait_queue and
rcv_nxt are opposit to each other.

Meaning that once tp->rcv_nxt is updated by CPU2, the CPU1 either already
passed the tp->rcv_nxt check and sleeps, or will get the new value for
tp->rcv_nxt and will return with new data mask.
In both cases the process (CPU1) is being added to the wait queue, so the
waitqueue_active (CPU2) call cannot miss and will wake up CPU1.

The bad case is when the __add_wait_queue changes done by CPU1 stay in its
cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1 will then
endup calling schedule and sleep forever if there are no more data on the
socket.

Calls to poll_wait in following modules were ommited:
	net/bluetooth/af_bluetooth.c
	net/irda/af_irda.c
	net/irda/irnet/irnet_ppp.c
	net/mac80211/rc80211_pid_debugfs.c
	net/phonet/socket.c
	net/rds/af_rds.c
	net/rfkill/core.c
	net/sunrpc/cache.c
	net/sunrpc/rpc_pipe.c
	net/tipc/socket.c

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h   | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/atm/common.c     |  6 ++---
 net/core/datagram.c  |  2 +-
 net/core/sock.c      |  8 +++----
 net/dccp/output.c    |  2 +-
 net/dccp/proto.c     |  2 +-
 net/ipv4/tcp.c       |  2 +-
 net/iucv/af_iucv.c   |  4 ++--
 net/rxrpc/af_rxrpc.c |  4 ++--
 net/unix/af_unix.c   |  8 +++----
 10 files changed, 85 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 352f06bbd7a9..4eb8409249f6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -54,6 +54,7 @@
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
+#include <linux/poll.h>
 
 #include <asm/atomic.h>
 #include <net/dst.h>
@@ -1241,6 +1242,71 @@ static inline int sk_has_allocations(const struct sock *sk)
 	return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
 }
 
+/**
+ * sk_has_sleeper - check if there are any waiting processes
+ * @sk: socket
+ *
+ * Returns true if socket has waiting processes
+ *
+ * The purpose of the sk_has_sleeper and sock_poll_wait is to wrap the memory
+ * barrier call. They were added due to the race found within the tcp code.
+ *
+ * Consider following tcp code paths:
+ *
+ * CPU1                  CPU2
+ *
+ * sys_select            receive packet
+ *   ...                 ...
+ *   __add_wait_queue    update tp->rcv_nxt
+ *   ...                 ...
+ *   tp->rcv_nxt check   sock_def_readable
+ *   ...                 {
+ *   schedule               ...
+ *                          if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+ *                              wake_up_interruptible(sk->sk_sleep)
+ *                          ...
+ *                       }
+ *
+ * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
+ * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
+ * could then endup calling schedule and sleep forever if there are no more
+ * data on the socket.
+ */
+static inline int sk_has_sleeper(struct sock *sk)
+{
+	/*
+	 * We need to be sure we are in sync with the
+	 * add_wait_queue modifications to the wait queue.
+	 *
+	 * This memory barrier is paired in the sock_poll_wait.
+	 */
+	smp_mb();
+	return sk->sk_sleep && waitqueue_active(sk->sk_sleep);
+}
+
+/**
+ * sock_poll_wait - place memory barrier behind the poll_wait call.
+ * @filp:           file
+ * @wait_address:   socket wait queue
+ * @p:              poll_table
+ *
+ * See the comments in the sk_has_sleeper function.
+ */
+static inline void sock_poll_wait(struct file *filp,
+		wait_queue_head_t *wait_address, poll_table *p)
+{
+	if (p && wait_address) {
+		poll_wait(filp, wait_address, p);
+		/*
+		 * We need to be sure we are in sync with the
+		 * socket flags modification.
+		 *
+		 * This memory barrier is paired in the sk_has_sleeper.
+		*/
+		smp_mb();
+	}
+}
+
 /*
  * 	Queue a received datagram if it will fit. Stream and sequenced
  *	protocols can't normally use this as they need to fit buffers in
diff --git a/net/atm/common.c b/net/atm/common.c
index c1c97936192c..8c4d843eb17f 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -92,7 +92,7 @@ static void vcc_sock_destruct(struct sock *sk)
 static void vcc_def_wakeup(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up(sk->sk_sleep);
 	read_unlock(&sk->sk_callback_lock);
 }
@@ -110,7 +110,7 @@ static void vcc_write_space(struct sock *sk)
 	read_lock(&sk->sk_callback_lock);
 
 	if (vcc_writable(sk)) {
-		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		if (sk_has_sleeper(sk))
 			wake_up_interruptible(sk->sk_sleep);
 
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
@@ -594,7 +594,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
 	struct atm_vcc *vcc;
 	unsigned int mask;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	vcc = ATM_SD(sock);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 58abee1f1df1..b0fe69211eef 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -712,7 +712,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	unsigned int mask;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* exceptional events? */
diff --git a/net/core/sock.c b/net/core/sock.c
index b0ba569bc973..6354863b1c68 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1715,7 +1715,7 @@ EXPORT_SYMBOL(sock_no_sendpage);
 static void sock_def_wakeup(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible_all(sk->sk_sleep);
 	read_unlock(&sk->sk_callback_lock);
 }
@@ -1723,7 +1723,7 @@ static void sock_def_wakeup(struct sock *sk)
 static void sock_def_error_report(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible_poll(sk->sk_sleep, POLLERR);
 	sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
 	read_unlock(&sk->sk_callback_lock);
@@ -1732,7 +1732,7 @@ static void sock_def_error_report(struct sock *sk)
 static void sock_def_readable(struct sock *sk, int len)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN |
 						POLLRDNORM | POLLRDBAND);
 	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
@@ -1747,7 +1747,7 @@ static void sock_def_write_space(struct sock *sk)
 	 * progress.  --DaveM
 	 */
 	if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
-		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		if (sk_has_sleeper(sk))
 			wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT |
 						POLLWRNORM | POLLWRBAND);
 
diff --git a/net/dccp/output.c b/net/dccp/output.c
index c0e88c16d088..c96119fda688 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -196,7 +196,7 @@ void dccp_write_space(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
 
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible(sk->sk_sleep);
 	/* Should agree with poll, otherwise some programs break */
 	if (sock_writeable(sk))
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 314a1b5c033c..94ca8eaace7d 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -311,7 +311,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock,
 	unsigned int mask;
 	struct sock *sk = sock->sk;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	if (sk->sk_state == DCCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7870a535dac6..91145244ea63 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -339,7 +339,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	struct sock *sk = sock->sk;
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	if (sk->sk_state == TCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 6be5f92d1094..49c15b48408e 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -306,7 +306,7 @@ static inline int iucv_below_msglim(struct sock *sk)
 static void iucv_sock_wake_msglim(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
-	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+	if (sk_has_sleeper(sk))
 		wake_up_interruptible_all(sk->sk_sleep);
 	sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	read_unlock(&sk->sk_callback_lock);
@@ -1256,7 +1256,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	unsigned int mask = 0;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 
 	if (sk->sk_state == IUCV_LISTEN)
 		return iucv_accept_poll(sk);
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index eac5e7bb7365..bfe493ebf27c 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -63,7 +63,7 @@ static void rxrpc_write_space(struct sock *sk)
 	_enter("%p", sk);
 	read_lock(&sk->sk_callback_lock);
 	if (rxrpc_writable(sk)) {
-		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		if (sk_has_sleeper(sk))
 			wake_up_interruptible(sk->sk_sleep);
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
@@ -588,7 +588,7 @@ static unsigned int rxrpc_poll(struct file *file, struct socket *sock,
 	unsigned int mask;
 	struct sock *sk = sock->sk;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* the socket is readable if there are any messages waiting on the Rx
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 36d4e44d6233..fc3ebb906911 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -315,7 +315,7 @@ static void unix_write_space(struct sock *sk)
 {
 	read_lock(&sk->sk_callback_lock);
 	if (unix_writable(sk)) {
-		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		if (sk_has_sleeper(sk))
 			wake_up_interruptible_sync(sk->sk_sleep);
 		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
@@ -1985,7 +1985,7 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table
 	struct sock *sk = sock->sk;
 	unsigned int mask;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* exceptional events? */
@@ -2022,7 +2022,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk, *other;
 	unsigned int mask, writable;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* exceptional events? */
@@ -2053,7 +2053,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
 		other = unix_peer_get(sk);
 		if (other) {
 			if (unix_peer(other) != sk) {
-				poll_wait(file, &unix_sk(other)->peer_wait,
+				sock_poll_wait(file, &unix_sk(other)->peer_wait,
 					  wait);
 				if (unix_recvq_full(other))
 					writable = 0;
-- 
cgit v1.2.3


From ad46276952f1af34cd91d46d49ba13d347d56367 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 8 Jul 2009 12:10:31 +0000
Subject: memory barrier: adding smp_mb__after_lock

Adding smp_mb__after_lock define to be used as a smp_mb call after
a lock.

Making it nop for x86, since {read|write|spin}_lock() on x86 are
full memory barriers.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/include/asm/spinlock.h | 4 ++++
 include/linux/spinlock.h        | 5 +++++
 include/net/sock.h              | 5 ++++-
 3 files changed, 13 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index b7e5db876399..4e77853321db 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -302,4 +302,8 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
 
+/* The {read|write|spin}_lock() on x86 are full memory barriers. */
+static inline void smp_mb__after_lock(void) { }
+#define ARCH_HAS_SMP_MB_AFTER_LOCK
+
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 252b245cfcf4..4be57ab03478 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -132,6 +132,11 @@ do {								\
 #endif /*__raw_spin_is_contended*/
 #endif
 
+/* The lock does not imply full memory barrier. */
+#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
+static inline void smp_mb__after_lock(void) { smp_mb(); }
+#endif
+
 /**
  * spin_unlock_wait - wait until the spinlock gets unlocked
  * @lock: the spinlock in question.
diff --git a/include/net/sock.h b/include/net/sock.h
index 4eb8409249f6..2c0da9239b95 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1271,6 +1271,9 @@ static inline int sk_has_allocations(const struct sock *sk)
  * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
  * could then endup calling schedule and sleep forever if there are no more
  * data on the socket.
+ *
+ * The sk_has_sleeper is always called right after a call to read_lock, so we
+ * can use smp_mb__after_lock barrier.
  */
 static inline int sk_has_sleeper(struct sock *sk)
 {
@@ -1280,7 +1283,7 @@ static inline int sk_has_sleeper(struct sock *sk)
 	 *
 	 * This memory barrier is paired in the sock_poll_wait.
 	 */
-	smp_mb();
+	smp_mb__after_lock();
 	return sk->sk_sleep && waitqueue_active(sk->sk_sleep);
 }
 
-- 
cgit v1.2.3


From 8aa7e847d834ed937a9ad37a0f2ad5b8584c1ab0 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Thu, 9 Jul 2009 14:52:32 +0200
Subject: Fix congestion_wait() sync/async vs read/write confusion

Commit 1faa16d22877f4839bd433547d770c676d1d964c accidentally broke
the bdi congestion wait queue logic, causing us to wait on congestion
for WRITE (== 1) when we really wanted BLK_RW_ASYNC (== 0) instead.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 arch/x86/lib/usercopy_32.c  |  2 +-
 drivers/block/pktcdvd.c     | 10 ++++++----
 drivers/md/dm-crypt.c       |  2 +-
 fs/fat/file.c               |  2 +-
 fs/fuse/dev.c               |  8 ++++----
 fs/nfs/write.c              |  8 +++++---
 fs/reiserfs/journal.c       |  2 +-
 fs/xfs/linux-2.6/kmem.c     |  4 ++--
 fs/xfs/linux-2.6/xfs_buf.c  |  2 +-
 include/linux/backing-dev.h |  6 +++---
 include/linux/blkdev.h      |  8 ++++----
 mm/backing-dev.c            |  7 +++----
 mm/memcontrol.c             |  2 +-
 mm/page-writeback.c         |  8 ++++----
 mm/page_alloc.c             |  4 ++--
 mm/vmscan.c                 |  8 ++++----
 16 files changed, 43 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 7c8ca91bb9ec..1f118d462acc 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -751,7 +751,7 @@ survive:
 
 			if (retval == -ENOMEM && is_global_init(current)) {
 				up_read(&current->mm->mmap_sem);
-				congestion_wait(WRITE, HZ/50);
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
 				goto survive;
 			}
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 83650e00632d..99a506f619b7 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -1372,8 +1372,10 @@ try_next_bio:
 	wakeup = (pd->write_congestion_on > 0
 	 		&& pd->bio_queue_size <= pd->write_congestion_off);
 	spin_unlock(&pd->lock);
-	if (wakeup)
-		clear_bdi_congested(&pd->disk->queue->backing_dev_info, WRITE);
+	if (wakeup) {
+		clear_bdi_congested(&pd->disk->queue->backing_dev_info,
+					BLK_RW_ASYNC);
+	}
 
 	pkt->sleep_time = max(PACKET_WAIT_TIME, 1);
 	pkt_set_state(pkt, PACKET_WAITING_STATE);
@@ -2592,10 +2594,10 @@ static int pkt_make_request(struct request_queue *q, struct bio *bio)
 	spin_lock(&pd->lock);
 	if (pd->write_congestion_on > 0
 	    && pd->bio_queue_size >= pd->write_congestion_on) {
-		set_bdi_congested(&q->backing_dev_info, WRITE);
+		set_bdi_congested(&q->backing_dev_info, BLK_RW_ASYNC);
 		do {
 			spin_unlock(&pd->lock);
-			congestion_wait(WRITE, HZ);
+			congestion_wait(BLK_RW_ASYNC, HZ);
 			spin_lock(&pd->lock);
 		} while(pd->bio_queue_size > pd->write_congestion_off);
 	}
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 9933eb861c71..529e2ba505c3 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -776,7 +776,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		 * But don't wait if split was due to the io size restriction
 		 */
 		if (unlikely(out_of_pages))
-			congestion_wait(WRITE, HZ/100);
+			congestion_wait(BLK_RW_ASYNC, HZ/100);
 
 		/*
 		 * With async crypto it is unsafe to share the crypto context
diff --git a/fs/fat/file.c b/fs/fat/file.c
index b28ea646ff60..f042b965c95c 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -134,7 +134,7 @@ static int fat_file_release(struct inode *inode, struct file *filp)
 	if ((filp->f_mode & FMODE_WRITE) &&
 	     MSDOS_SB(inode->i_sb)->options.flush) {
 		fat_flush_inodes(inode->i_sb, inode, NULL);
-		congestion_wait(WRITE, HZ/10);
+		congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	return 0;
 }
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index f58ecbc416c8..6484eb75acd6 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -286,8 +286,8 @@ __releases(&fc->lock)
 		}
 		if (fc->num_background == FUSE_CONGESTION_THRESHOLD &&
 		    fc->connected && fc->bdi_initialized) {
-			clear_bdi_congested(&fc->bdi, READ);
-			clear_bdi_congested(&fc->bdi, WRITE);
+			clear_bdi_congested(&fc->bdi, BLK_RW_SYNC);
+			clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
 		}
 		fc->num_background--;
 		fc->active_background--;
@@ -414,8 +414,8 @@ static void fuse_request_send_nowait_locked(struct fuse_conn *fc,
 		fc->blocked = 1;
 	if (fc->num_background == FUSE_CONGESTION_THRESHOLD &&
 	    fc->bdi_initialized) {
-		set_bdi_congested(&fc->bdi, READ);
-		set_bdi_congested(&fc->bdi, WRITE);
+		set_bdi_congested(&fc->bdi, BLK_RW_SYNC);
+		set_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
 	}
 	list_add_tail(&req->list, &fc->bg_queue);
 	flush_bg_queue(fc);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index ce728829f79a..0a0a2ff767c3 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -202,8 +202,10 @@ static int nfs_set_page_writeback(struct page *page)
 		struct nfs_server *nfss = NFS_SERVER(inode);
 
 		if (atomic_long_inc_return(&nfss->writeback) >
-				NFS_CONGESTION_ON_THRESH)
-			set_bdi_congested(&nfss->backing_dev_info, WRITE);
+				NFS_CONGESTION_ON_THRESH) {
+			set_bdi_congested(&nfss->backing_dev_info,
+						BLK_RW_ASYNC);
+		}
 	}
 	return ret;
 }
@@ -215,7 +217,7 @@ static void nfs_end_page_writeback(struct page *page)
 
 	end_page_writeback(page);
 	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, WRITE);
+		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
 
 /*
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 77f5bb746bf0..90622200b39c 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -997,7 +997,7 @@ static int reiserfs_async_progress_wait(struct super_block *s)
 	DEFINE_WAIT(wait);
 	struct reiserfs_journal *j = SB_JOURNAL(s);
 	if (atomic_read(&j->j_async_throttle))
-		congestion_wait(WRITE, HZ / 10);
+		congestion_wait(BLK_RW_ASYNC, HZ / 10);
 	return 0;
 }
 
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index 1cd3b55ee3d2..2d3f90afe5f1 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags)
 			printk(KERN_ERR "XFS: possible memory allocation "
 					"deadlock in %s (mode:0x%x)\n",
 					__func__, lflags);
-		congestion_wait(WRITE, HZ/50);
+		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (1);
 }
 
@@ -130,7 +130,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags)
 			printk(KERN_ERR "XFS: possible memory allocation "
 					"deadlock in %s (mode:0x%x)\n",
 					__func__, lflags);
-		congestion_wait(WRITE, HZ/50);
+		congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (1);
 }
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 1418b916fc27..0c93c7ef3d18 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -412,7 +412,7 @@ _xfs_buf_lookup_pages(
 
 			XFS_STATS_INC(xb_page_retries);
 			xfsbufd_wakeup(0, gfp_mask);
-			congestion_wait(WRITE, HZ/50);
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
 			goto retry;
 		}
 
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0ec2c594868e..3a52a63c1351 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -229,9 +229,9 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 				  (1 << BDI_async_congested));
 }
 
-void clear_bdi_congested(struct backing_dev_info *bdi, int rw);
-void set_bdi_congested(struct backing_dev_info *bdi, int rw);
-long congestion_wait(int rw, long timeout);
+void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
+void set_bdi_congested(struct backing_dev_info *bdi, int sync);
+long congestion_wait(int sync, long timeout);
 
 
 static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 49ae07951d55..bb3d39978701 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -779,18 +779,18 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
  * congested queues, and wake up anyone who was waiting for requests to be
  * put back.
  */
-static inline void blk_clear_queue_congested(struct request_queue *q, int rw)
+static inline void blk_clear_queue_congested(struct request_queue *q, int sync)
 {
-	clear_bdi_congested(&q->backing_dev_info, rw);
+	clear_bdi_congested(&q->backing_dev_info, sync);
 }
 
 /*
  * A queue has just entered congestion.  Flag that in the queue's VM-visible
  * state flags and increment the global gounter of congested queues.
  */
-static inline void blk_set_queue_congested(struct request_queue *q, int rw)
+static inline void blk_set_queue_congested(struct request_queue *q, int sync)
 {
-	set_bdi_congested(&q->backing_dev_info, rw);
+	set_bdi_congested(&q->backing_dev_info, sync);
 }
 
 extern void blk_start_queue(struct request_queue *q);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 493b468a5035..c86edd244294 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -283,7 +283,6 @@ static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
 	};
 
-
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	enum bdi_state bit;
@@ -308,18 +307,18 @@ EXPORT_SYMBOL(set_bdi_congested);
 
 /**
  * congestion_wait - wait for a backing_dev to become uncongested
- * @rw: READ or WRITE
+ * @sync: SYNC or ASYNC IO
  * @timeout: timeout in jiffies
  *
  * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
  * write congestion.  If no backing_devs are congested then just wait for the
  * next write to be completed.
  */
-long congestion_wait(int rw, long timeout)
+long congestion_wait(int sync, long timeout)
 {
 	long ret;
 	DEFINE_WAIT(wait);
-	wait_queue_head_t *wqh = &congestion_wqh[rw];
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
 	ret = io_schedule_timeout(timeout);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e2fa20dadf40..e717964cb5a0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1973,7 +1973,7 @@ try_to_free:
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 		}
 
 	}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7687879253b9..81627ebcd313 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -575,7 +575,7 @@ static void balance_dirty_pages(struct address_space *mapping)
 		if (pages_written >= write_chunk)
 			break;		/* We've done our duty */
 
-		congestion_wait(WRITE, HZ/10);
+		congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 
 	if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
@@ -669,7 +669,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
                 if (global_page_state(NR_UNSTABLE_NFS) +
 			global_page_state(NR_WRITEBACK) <= dirty_thresh)
                         	break;
-                congestion_wait(WRITE, HZ/10);
+                congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		/*
 		 * The caller might hold locks which can prevent IO completion
@@ -715,7 +715,7 @@ static void background_writeout(unsigned long _min_pages)
 		if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
 			/* Wrote less than expected */
 			if (wbc.encountered_congestion || wbc.more_io)
-				congestion_wait(WRITE, HZ/10);
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
 			else
 				break;
 		}
@@ -787,7 +787,7 @@ static void wb_kupdate(unsigned long arg)
 		writeback_inodes(&wbc);
 		if (wbc.nr_to_write > 0) {
 			if (wbc.encountered_congestion || wbc.more_io)
-				congestion_wait(WRITE, HZ/10);
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
 			else
 				break;	/* All the old data is written */
 		}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ad7cd1c56b07..a35eeab2724c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1666,7 +1666,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 			preferred_zone, migratetype);
 
 		if (!page && gfp_mask & __GFP_NOFAIL)
-			congestion_wait(WRITE, HZ/50);
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
 	} while (!page && (gfp_mask & __GFP_NOFAIL));
 
 	return page;
@@ -1831,7 +1831,7 @@ rebalance:
 	pages_reclaimed += did_some_progress;
 	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
 		/* Wait for some write requests to complete then retry */
-		congestion_wait(WRITE, HZ/50);
+		congestion_wait(BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
 	}
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 54155268dfca..dea7abd31098 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1104,7 +1104,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		 */
 		if (nr_freed < nr_taken && !current_is_kswapd() &&
 		    lumpy_reclaim) {
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 			/*
 			 * The attempt at page out may have made some
@@ -1721,7 +1721,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 		/* Take a nap, wait for some writeback to complete */
 		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (!sc->all_unreclaimable && scanning_global_lru(sc))
@@ -1960,7 +1960,7 @@ loop_again:
 		 * another pass across the zones.
 		 */
 		if (total_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for
@@ -2233,7 +2233,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 				goto out;
 
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				congestion_wait(WRITE, HZ / 10);
+				congestion_wait(BLK_RW_ASYNC, HZ / 10);
 		}
 	}
 
-- 
cgit v1.2.3


From ecb554a846f8e9d2a58f6d6c118168a63ac065aa Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Date: Thu, 9 Jul 2009 14:46:53 +0200
Subject: block: fix sg SG_DXFER_TO_FROM_DEV regression

I overlooked SG_DXFER_TO_FROM_DEV support when I converted sg to use
the block layer mapping API (2.6.28).

Douglas Gilbert explained SG_DXFER_TO_FROM_DEV:

http://www.spinics.net/lists/linux-scsi/msg37135.html

=
The semantics of SG_DXFER_TO_FROM_DEV were:
   - copy user space buffer to kernel (LLD) buffer
   - do SCSI command which is assumed to be of the DATA_IN
     (data from device) variety. This would overwrite
     some or all of the kernel buffer
   - copy kernel (LLD) buffer back to the user space.

The idea was to detect short reads by filling the original
user space buffer with some marker bytes ("0xec" it would
seem in this report). The "resid" value is a better way
of detecting short reads but that was only added this century
and requires co-operation from the LLD.
=

This patch changes the block layer mapping API to support this
semantics. This simply adds another field to struct rq_map_data and
enables __bio_copy_iov() to copy data from user space even with READ
requests.

It's better to add the flags field and kills null_mapped and the new
from_user fields in struct rq_map_data but that approach makes it
difficult to send this patch to stable trees because st and osst
drivers use struct rq_map_data (they were converted to use the block
layer in 2.6.29 and 2.6.30). Well, I should clean up the block layer
mapping API.

zhou sf reported this regiression and tested this patch:

http://www.spinics.net/lists/linux-scsi/msg37128.html
http://www.spinics.net/lists/linux-scsi/msg37168.html

Reported-by: zhou sf <sxzzsf@gmail.com>
Tested-by: zhou sf <sxzzsf@gmail.com>
Cc: stable@kernel.org
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 drivers/scsi/sg.c      |  4 ++++
 fs/bio.c               | 22 ++++++++++++----------
 include/linux/blkdev.h |  1 +
 3 files changed, 17 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 4d6f2fe1cfe9..9230402c45af 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1656,6 +1656,10 @@ static int sg_start_req(Sg_request *srp, unsigned char *cmd)
 		md->nr_entries = req_schp->k_use_sg;
 		md->offset = 0;
 		md->null_mapped = hp->dxferp ? 0 : 1;
+		if (dxfer_dir == SG_DXFER_TO_FROM_DEV)
+			md->from_user = 1;
+		else
+			md->from_user = 0;
 	}
 
 	if (iov_count) {
diff --git a/fs/bio.c b/fs/bio.c
index 1486b19fc431..76738005c8e8 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -705,14 +705,13 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count,
 }
 
 static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
-			  struct sg_iovec *iov, int iov_count, int uncopy,
-			  int do_free_page)
+			  struct sg_iovec *iov, int iov_count,
+			  int to_user, int from_user, int do_free_page)
 {
 	int ret = 0, i;
 	struct bio_vec *bvec;
 	int iov_idx = 0;
 	unsigned int iov_off = 0;
-	int read = bio_data_dir(bio) == READ;
 
 	__bio_for_each_segment(bvec, bio, i, 0) {
 		char *bv_addr = page_address(bvec->bv_page);
@@ -727,13 +726,14 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 			iov_addr = iov[iov_idx].iov_base + iov_off;
 
 			if (!ret) {
-				if (!read && !uncopy)
-					ret = copy_from_user(bv_addr, iov_addr,
-							     bytes);
-				if (read && uncopy)
+				if (to_user)
 					ret = copy_to_user(iov_addr, bv_addr,
 							   bytes);
 
+				if (from_user)
+					ret = copy_from_user(bv_addr, iov_addr,
+							     bytes);
+
 				if (ret)
 					ret = -EFAULT;
 			}
@@ -770,7 +770,8 @@ int bio_uncopy_user(struct bio *bio)
 
 	if (!bio_flagged(bio, BIO_NULL_MAPPED))
 		ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
-				     bmd->nr_sgvecs, 1, bmd->is_our_pages);
+				     bmd->nr_sgvecs, bio_data_dir(bio) == READ,
+				     0, bmd->is_our_pages);
 	bio_free_map_data(bmd);
 	bio_put(bio);
 	return ret;
@@ -875,8 +876,9 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	/*
 	 * success
 	 */
-	if (!write_to_vm && (!map_data || !map_data->null_mapped)) {
-		ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 0);
+	if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
+	    (map_data && map_data->from_user)) {
+		ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 1, 0);
 		if (ret)
 			goto cleanup;
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bb3d39978701..0146e0fecf1a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -723,6 +723,7 @@ struct rq_map_data {
 	int nr_entries;
 	unsigned long offset;
 	int null_mapped;
+	int from_user;
 };
 
 struct req_iterator {
-- 
cgit v1.2.3


From c99e6efe1ba04561e7d93a81f0be07e37427e835 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Fri, 10 Jul 2009 14:57:56 +0200
Subject: sched: INIT_PREEMPT_COUNT

Pull the initial preempt_count value into a single
definition site.

Maintainers for: alpha, ia64 and m68k, please have a look,
your arch code is funny.

The header magic is a bit odd, but similar to the KERNEL_DS
one, CPP waits with expanding these macros until the
INIT_THREAD_INFO macro itself is expanded, which is in
arch/*/kernel/init_task.c where we've already included
sched.h so we're good.

Cc: tony.luck@intel.com
Cc: rth@twiddle.net
Cc: geert@linux-m68k.org
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/thread_info.h      | 1 +
 arch/arm/include/asm/thread_info.h        | 2 +-
 arch/avr32/include/asm/thread_info.h      | 2 +-
 arch/blackfin/include/asm/thread_info.h   | 2 +-
 arch/cris/include/asm/thread_info.h       | 4 +---
 arch/frv/include/asm/thread_info.h        | 4 +---
 arch/h8300/include/asm/thread_info.h      | 2 +-
 arch/ia64/include/asm/thread_info.h       | 2 +-
 arch/m32r/include/asm/thread_info.h       | 4 +---
 arch/m68k/include/asm/thread_info_mm.h    | 1 +
 arch/m68k/include/asm/thread_info_no.h    | 1 +
 arch/microblaze/include/asm/thread_info.h | 4 +---
 arch/mips/include/asm/thread_info.h       | 4 +---
 arch/mn10300/include/asm/thread_info.h    | 4 +---
 arch/parisc/include/asm/thread_info.h     | 2 +-
 arch/powerpc/include/asm/thread_info.h    | 4 +---
 arch/s390/include/asm/thread_info.h       | 2 +-
 arch/sh/include/asm/thread_info.h         | 2 +-
 arch/sparc/include/asm/thread_info_32.h   | 4 +---
 arch/sparc/include/asm/thread_info_64.h   | 4 +---
 arch/um/include/asm/thread_info.h         | 2 +-
 arch/x86/include/asm/thread_info.h        | 2 +-
 arch/xtensa/include/asm/thread_info.h     | 4 +---
 include/linux/sched.h                     | 6 ++++++
 24 files changed, 29 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index d069526bd767..60c83abfde70 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -37,6 +37,7 @@ struct thread_info {
 	.task		= &tsk,			\
 	.exec_domain	= &default_exec_domain,	\
 	.addr_limit	= KERNEL_DS,		\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
 	},					\
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 4f8848260ee2..73394e50cbca 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -73,7 +73,7 @@ struct thread_info {
 	.task		= &tsk,						\
 	.exec_domain	= &default_exec_domain,				\
 	.flags		= 0,						\
-	.preempt_count	= 1,						\
+	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
 	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
 			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
diff --git a/arch/avr32/include/asm/thread_info.h b/arch/avr32/include/asm/thread_info.h
index 4442f8d2d423..fc42de5ca209 100644
--- a/arch/avr32/include/asm/thread_info.h
+++ b/arch/avr32/include/asm/thread_info.h
@@ -40,7 +40,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,				\
 	.flags		= 0,						\
 	.cpu		= 0,						\
-	.preempt_count	= 1,						\
+	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.restart_block	= {						\
 		.fn	= do_no_restart_syscall				\
 	}								\
diff --git a/arch/blackfin/include/asm/thread_info.h b/arch/blackfin/include/asm/thread_info.h
index 2920087516f2..2bbfdd950afc 100644
--- a/arch/blackfin/include/asm/thread_info.h
+++ b/arch/blackfin/include/asm/thread_info.h
@@ -77,7 +77,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count  = 1,                    \
+	.preempt_count  = INIT_PREEMPT_COUNT,   \
 	.restart_block	= {			\
 		.fn = do_no_restart_syscall,	\
 	},					\
diff --git a/arch/cris/include/asm/thread_info.h b/arch/cris/include/asm/thread_info.h
index bc5b2935ca53..c3aade36c330 100644
--- a/arch/cris/include/asm/thread_info.h
+++ b/arch/cris/include/asm/thread_info.h
@@ -50,8 +50,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #ifndef __ASSEMBLY__
 #define INIT_THREAD_INFO(tsk)				\
@@ -60,7 +58,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,		\
 	.flags		= 0,				\
 	.cpu		= 0,				\
-	.preempt_count	= 1,				\
+	.preempt_count	= INIT_PREEMPT_COUNT,		\
 	.addr_limit	= KERNEL_DS,			\
 	.restart_block = {				\
 		       .fn = do_no_restart_syscall,	\
diff --git a/arch/frv/include/asm/thread_info.h b/arch/frv/include/asm/thread_info.h
index e8a5ed7be021..e608e056bb53 100644
--- a/arch/frv/include/asm/thread_info.h
+++ b/arch/frv/include/asm/thread_info.h
@@ -56,8 +56,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #ifndef __ASSEMBLY__
 
@@ -67,7 +65,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
index 700014d2155f..8bbc8b0ee45d 100644
--- a/arch/h8300/include/asm/thread_info.h
+++ b/arch/h8300/include/asm/thread_info.h
@@ -36,7 +36,7 @@ struct thread_info {
 	.exec_domain =	&default_exec_domain,	\
 	.flags =	0,			\
 	.cpu =		0,			\
-	.preempt_count = 1,			\
+	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.restart_block	= {			\
 		.fn = do_no_restart_syscall,	\
 	},					\
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index ae6922626bf4..8ce2e388e37c 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -48,7 +48,7 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
-	.preempt_count	= 0,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
 	},					\
diff --git a/arch/m32r/include/asm/thread_info.h b/arch/m32r/include/asm/thread_info.h
index 8589d462df27..07bb5bd00e2a 100644
--- a/arch/m32r/include/asm/thread_info.h
+++ b/arch/m32r/include/asm/thread_info.h
@@ -57,8 +57,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #ifndef __ASSEMBLY__
 
@@ -68,7 +66,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/arch/m68k/include/asm/thread_info_mm.h b/arch/m68k/include/asm/thread_info_mm.h
index af0fda46e94b..6ea5c33b3c56 100644
--- a/arch/m68k/include/asm/thread_info_mm.h
+++ b/arch/m68k/include/asm/thread_info_mm.h
@@ -19,6 +19,7 @@ struct thread_info {
 {						\
 	.task		= &tsk,			\
 	.exec_domain	= &default_exec_domain,	\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
 	},					\
diff --git a/arch/m68k/include/asm/thread_info_no.h b/arch/m68k/include/asm/thread_info_no.h
index 82529f424ea3..c2bde5e24b0b 100644
--- a/arch/m68k/include/asm/thread_info_no.h
+++ b/arch/m68k/include/asm/thread_info_no.h
@@ -49,6 +49,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.restart_block	= {			\
 		.fn = do_no_restart_syscall,	\
 	},					\
diff --git a/arch/microblaze/include/asm/thread_info.h b/arch/microblaze/include/asm/thread_info.h
index 7fac44498445..6e92885d381a 100644
--- a/arch/microblaze/include/asm/thread_info.h
+++ b/arch/microblaze/include/asm/thread_info.h
@@ -75,8 +75,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #define INIT_THREAD_INFO(tsk)			\
 {						\
@@ -84,7 +82,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 143a48136a4b..f9df720d2e40 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -39,8 +39,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #define INIT_THREAD_INFO(tsk)			\
 {						\
@@ -48,7 +46,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= _TIF_FIXADE,		\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block	= {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h
index 78a3881f3c12..58d64f8b2cc3 100644
--- a/arch/mn10300/include/asm/thread_info.h
+++ b/arch/mn10300/include/asm/thread_info.h
@@ -65,8 +65,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #ifndef __ASSEMBLY__
 
@@ -76,7 +74,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index 0407959da489..4ce0edfbe969 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -23,7 +23,7 @@ struct thread_info {
 	.flags		= 0,			\
 	.cpu		= 0,			\
 	.addr_limit	= KERNEL_DS,		\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
   	.restart_block	= {			\
 		.fn = do_no_restart_syscall	\
 	}					\
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 9aba5a38a7c4..c8b329255678 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -46,15 +46,13 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.task =		&tsk,			\
 	.exec_domain =	&default_exec_domain,	\
 	.cpu =		0,			\
-	.preempt_count = 1,			\
+	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
 	},					\
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 925bcc649035..ba1cab9fc1f9 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -61,7 +61,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.restart_block	= {			\
 		.fn = do_no_restart_syscall,	\
 	},					\
diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h
index f09ac4806294..d570ac2e5cb9 100644
--- a/arch/sh/include/asm/thread_info.h
+++ b/arch/sh/include/asm/thread_info.h
@@ -51,7 +51,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block	= {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index 0f7b0e5fb1c7..844d73a0340c 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -54,8 +54,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #define INIT_THREAD_INFO(tsk)				\
 {							\
@@ -64,7 +62,7 @@ struct thread_info {
 	.exec_domain	=	&default_exec_domain,	\
 	.flags		=	0,			\
 	.cpu		=	0,			\
-	.preempt_count	=	1,			\
+	.preempt_count	=	INIT_PREEMPT_COUNT,	\
 	.restart_block	= {				\
 		.fn	=	do_no_restart_syscall,	\
 	},						\
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index 65865726b283..1b45a7bbe407 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -125,8 +125,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 #ifndef __ASSEMBLY__
 
@@ -135,7 +133,7 @@ struct thread_info {
 	.task		=	&tsk,			\
 	.flags		= ((unsigned long)ASI_P) << TI_FLAG_CURRENT_DS_SHIFT,	\
 	.exec_domain	=	&default_exec_domain,	\
-	.preempt_count	=	1,			\
+	.preempt_count	=	INIT_PREEMPT_COUNT,	\
 	.restart_block	= {				\
 		.fn	=	do_no_restart_syscall,	\
 	},						\
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
index 62274ab9471f..fd911f855367 100644
--- a/arch/um/include/asm/thread_info.h
+++ b/arch/um/include/asm/thread_info.h
@@ -32,7 +32,7 @@ struct thread_info {
 	.exec_domain =	&default_exec_domain,	\
 	.flags =		0,		\
 	.cpu =		0,			\
-	.preempt_count =	1,		\
+	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit =	KERNEL_DS,		\
 	.restart_block =  {			\
 		.fn =  do_no_restart_syscall,	\
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index b0783520988b..fad7d40b75f8 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -49,7 +49,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/arch/xtensa/include/asm/thread_info.h b/arch/xtensa/include/asm/thread_info.h
index 0f4fe1faf9ba..13165641cc51 100644
--- a/arch/xtensa/include/asm/thread_info.h
+++ b/arch/xtensa/include/asm/thread_info.h
@@ -80,8 +80,6 @@ struct thread_info {
 
 /*
  * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
 
 #ifndef __ASSEMBLY__
@@ -92,7 +90,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= 1,			\
+	.preempt_count	= INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0085d758d645..2a99f1c15cf8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -498,6 +498,12 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
+/*
+ * Disable preemption until the scheduler is running.
+ * Reset by start_kernel()->sched_init()->init_idle().
+ */
+#define INIT_PREEMPT_COUNT	(1)
+
 /**
  * struct thread_group_cputimer - thread group interval timer counts
  * @cputime:		thread group interval timers.
-- 
cgit v1.2.3


From d86ee4809d0329d4aa0d0f2c76c2295a16862799 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Fri, 10 Jul 2009 14:57:57 +0200
Subject: sched: optimize cond_resched()

Optimize cond_resched() by removing one conditional.

Currently cond_resched() checks system_state ==
SYSTEM_RUNNING in order to avoid scheduling before the
scheduler is running.

We can however, as per suggestion of Matt, use
PREEMPT_ACTIVE to accomplish that very same.

Suggested-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h |  5 ++++-
 kernel/sched.c        | 14 +++++++++-----
 2 files changed, 13 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2a99f1c15cf8..16a982e389fb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -501,8 +501,11 @@ struct task_cputime {
 /*
  * Disable preemption until the scheduler is running.
  * Reset by start_kernel()->sched_init()->init_idle().
+ *
+ * We include PREEMPT_ACTIVE to avoid cond_resched() from working
+ * before the scheduler is active -- see should_resched().
  */
-#define INIT_PREEMPT_COUNT	(1)
+#define INIT_PREEMPT_COUNT	(1 + PREEMPT_ACTIVE)
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
diff --git a/kernel/sched.c b/kernel/sched.c
index 7c9098d186e6..01f55ada3598 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6541,6 +6541,11 @@ SYSCALL_DEFINE0(sched_yield)
 	return 0;
 }
 
+static inline int should_resched(void)
+{
+	return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
+}
+
 static void __cond_resched(void)
 {
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
@@ -6560,8 +6565,7 @@ static void __cond_resched(void)
 
 int __sched _cond_resched(void)
 {
-	if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
-					system_state == SYSTEM_RUNNING) {
+	if (should_resched()) {
 		__cond_resched();
 		return 1;
 	}
@@ -6579,12 +6583,12 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int cond_resched_lock(spinlock_t *lock)
 {
-	int resched = need_resched() && system_state == SYSTEM_RUNNING;
+	int resched = should_resched();
 	int ret = 0;
 
 	if (spin_needbreak(lock) || resched) {
 		spin_unlock(lock);
-		if (resched && need_resched())
+		if (resched)
 			__cond_resched();
 		else
 			cpu_relax();
@@ -6599,7 +6603,7 @@ int __sched cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	if (need_resched() && system_state == SYSTEM_RUNNING) {
+	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
 		local_bh_disable();
-- 
cgit v1.2.3


From 24a15a62dcb1968bf4ffdae55c88fa934d971180 Mon Sep 17 00:00:00 2001
From: Alan Cox <alan@linux.intel.com>
Date: Thu, 9 Jul 2009 13:36:22 +0100
Subject: tty: Fix USB kref leak

The sysrq code acquired a kref leak. Fix it by passing the tty separately
from the caller (thus effectively using the callers kref which all the
callers hold anyway)

Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/usb/serial/ftdi_sio.c | 2 +-
 drivers/usb/serial/generic.c  | 7 ++++---
 drivers/usb/serial/pl2303.c   | 2 +-
 include/linux/usb/serial.h    | 3 ++-
 4 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 3dc3768ca71c..5f08702f672f 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -2121,7 +2121,7 @@ static void ftdi_process_read(struct work_struct *work)
 				/* Note that the error flag is duplicated for
 				   every character received since we don't know
 				   which character it applied to */
-				if (!usb_serial_handle_sysrq_char(port,
+				if (!usb_serial_handle_sysrq_char(tty, port,
 						data[packet_offset + i]))
 					tty_insert_flip_char(tty,
 						data[packet_offset + i],
diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index 3d8dc5671bea..ce57f6a32bdf 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -432,7 +432,7 @@ static void flush_and_resubmit_read_urb(struct usb_serial_port *port)
 	else {
 		/* Push data to tty */
 		for (i = 0; i < urb->actual_length; i++, ch++) {
-			if (!usb_serial_handle_sysrq_char(port, *ch))
+			if (!usb_serial_handle_sysrq_char(tty, port, *ch))
 				tty_insert_flip_char(tty, *ch, TTY_NORMAL);
 		}
 	}
@@ -534,11 +534,12 @@ void usb_serial_generic_unthrottle(struct tty_struct *tty)
 	}
 }
 
-int usb_serial_handle_sysrq_char(struct usb_serial_port *port, unsigned int ch)
+int usb_serial_handle_sysrq_char(struct tty_struct *tty,
+			struct usb_serial_port *port, unsigned int ch)
 {
 	if (port->sysrq && port->console) {
 		if (ch && time_before(jiffies, port->sysrq)) {
-			handle_sysrq(ch, tty_port_tty_get(&port->port));
+			handle_sysrq(ch, tty);
 			port->sysrq = 0;
 			return 1;
 		}
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index ec6c132a25b5..8835802067f7 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -1038,7 +1038,7 @@ static void pl2303_read_bulk_callback(struct urb *urb)
 		if (line_status & UART_OVERRUN_ERROR)
 			tty_insert_flip_char(tty, 0, TTY_OVERRUN);
 		for (i = 0; i < urb->actual_length; ++i)
-			if (!usb_serial_handle_sysrq_char(port, data[i]))
+			if (!usb_serial_handle_sysrq_char(tty, port, data[i]))
 				tty_insert_flip_char(tty, data[i], tty_flag);
 		tty_flip_buffer_push(tty);
 	}
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 44801d26a37a..0ec50ba62139 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -317,7 +317,8 @@ extern int usb_serial_generic_register(int debug);
 extern void usb_serial_generic_deregister(void);
 extern void usb_serial_generic_resubmit_read_urb(struct usb_serial_port *port,
 						 gfp_t mem_flags);
-extern int usb_serial_handle_sysrq_char(struct usb_serial_port *port,
+extern int usb_serial_handle_sysrq_char(struct tty_struct *tty,
+					struct usb_serial_port *port,
 					unsigned int ch);
 extern int usb_serial_handle_break(struct usb_serial_port *port);
 
-- 
cgit v1.2.3