Merge commit 'origin/master'

Manual merge of:

	arch/powerpc/Kconfig
	arch/powerpc/kernel/stacktrace.c
	arch/powerpc/mm/slice.c
	arch/ppc/kernel/smp.c

26 files changed, 798 insertions, 483 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1ffd8bfdc4c..32a441b05fd 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -651,7 +651,6 @@ extern void generic_make_request(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
-extern void blk_end_sync_rq(struct request *rq, int error);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
 extern void blk_insert_request(struct request_queue *, struct request *, int, void *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index d982eb89c77..98202c672fd 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -3,6 +3,7 @@
 
 #include <asm/atomic.h>
 #include <linux/list.h>
+#include <linux/rculist.h>
 #include <linux/spinlock.h>
 #include <linux/cache.h>
 #include <linux/rcupdate.h>
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index 6c7eff2ebad..c8ecf5b2a20 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -1,18 +1,39 @@
 #ifndef _LINUX_FIRMWARE_H
 #define _LINUX_FIRMWARE_H
+
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/compiler.h>
+
 #define FIRMWARE_NAME_MAX 30 
 #define FW_ACTION_NOHOTPLUG 0
 #define FW_ACTION_HOTPLUG 1
 
 struct firmware {
 	size_t size;
-	u8 *data;
+	const u8 *data;
 };
 
 struct device;
 
+struct builtin_fw {
+	char *name;
+	void *data;
+	unsigned long size;
+};
+
+/* We have to play tricks here much like stringify() to get the
+   __COUNTER__ macro to be expanded as we want it */
+#define __fw_concat1(x, y) x##y
+#define __fw_concat(x, y) __fw_concat1(x, y)
+
+#define DECLARE_BUILTIN_FIRMWARE(name, blob)				     \
+	DECLARE_BUILTIN_FIRMWARE_SIZE(name, &(blob), sizeof(blob))
+
+#define DECLARE_BUILTIN_FIRMWARE_SIZE(name, blob, size)			     \
+	static const struct builtin_fw __fw_concat(__builtin_fw,__COUNTER__) \
+	__used __section(.builtin_fw) = { name, blob, size }
+
 #if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE))
 int request_firmware(const struct firmware **fw, const char *name,
 		     struct device *device);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index faac13e2cc5..52e510a0aec 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1740,6 +1740,8 @@ extern int wait_on_page_writeback_range(struct address_space *mapping,
 				pgoff_t start, pgoff_t end);
 extern int __filemap_fdatawrite_range(struct address_space *mapping,
 				loff_t start, loff_t end, int sync_mode);
+extern int filemap_fdatawrite_range(struct address_space *mapping,
+				loff_t start, loff_t end);
 
 extern long do_fsync(struct file *file, int datasync);
 extern void sync_supers(void);
diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h
index 77afbb60fd1..0177d280f73 100644
--- a/include/linux/i2c-algo-pcf.h
+++ b/include/linux/i2c-algo-pcf.h
@@ -33,9 +33,11 @@ struct i2c_algo_pcf_data {
 	int  (*getclock) (void *data);
 	void (*waitforpin) (void);
 
-	/* local settings */
-	int udelay;
-	int timeout;
+	/* Multi-master lost arbitration back-off delay (msecs)
+	 * This should be set by the bus adapter or knowledgable client
+	 * if bus is multi-mastered, else zero
+	 */
+	unsigned long lab_mdelay;
 };
 
 int i2c_pcf_add_bus(struct i2c_adapter *);
diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h
index 580acc93903..ef13b7c66df 100644
--- a/include/linux/i2c-id.h
+++ b/include/linux/i2c-id.h
@@ -91,8 +91,6 @@
 #define I2C_DRIVERID_M52790 	95      /* Mitsubishi M52790SP/FP AV switch */
 #define I2C_DRIVERID_CS5345	96	/* cs5345 audio processor	*/
 
-#define I2C_DRIVERID_I2CDEV	900
-
 #define I2C_DRIVERID_OV7670 1048	/* Omnivision 7670 camera */
 
 /*
@@ -111,7 +109,6 @@
 #define I2C_HW_B_RIVA		0x010010 /* Riva based graphics cards */
 #define I2C_HW_B_IOC		0x010011 /* IOC bit-wiggling */
 #define I2C_HW_B_IXP2000	0x010016 /* GPIO on IXP2000 systems */
-#define I2C_HW_B_S3VIA		0x010018 /* S3Via ProSavage adapter */
 #define I2C_HW_B_ZR36067	0x010019 /* Zoran-36057/36067 based boards */
 #define I2C_HW_B_PCILYNX	0x01001a /* TI PCILynx I2C adapter */
 #define I2C_HW_B_CX2388x	0x01001b /* connexant 2388x based tv cards */
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 8dc73013219..08be0d21864 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -35,6 +35,8 @@
 #include <linux/sched.h>	/* for completion */
 #include <linux/mutex.h>
 
+extern struct bus_type i2c_bus_type;
+
 /* --- General options ------------------------------------------------	*/
 
 struct i2c_msg;
@@ -43,6 +45,7 @@ struct i2c_adapter;
 struct i2c_client;
 struct i2c_driver;
 union i2c_smbus_data;
+struct i2c_board_info;
 
 /*
  * The master routines are the ones normally used to transmit data to devices
@@ -69,9 +72,8 @@ extern s32 i2c_smbus_xfer (struct i2c_adapter * adapter, u16 addr,
                            union i2c_smbus_data * data);
 
 /* Now follow the 'nice' access routines. These also document the calling
-   conventions of smbus_access. */
+   conventions of i2c_smbus_xfer. */
 
-extern s32 i2c_smbus_write_quick(struct i2c_client * client, u8 value);
 extern s32 i2c_smbus_read_byte(struct i2c_client * client);
 extern s32 i2c_smbus_write_byte(struct i2c_client * client, u8 value);
 extern s32 i2c_smbus_read_byte_data(struct i2c_client * client, u8 command);
@@ -93,15 +95,33 @@ extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client * client,
 					  u8 command, u8 length,
 					  const u8 *values);
 
-/*
- * A driver is capable of handling one or more physical devices present on
- * I2C adapters. This information is used to inform the driver of adapter
- * events.
+/**
+ * struct i2c_driver - represent an I2C device driver
+ * @class: What kind of i2c device we instantiate (for detect)
+ * @detect: Callback for device detection
+ * @address_data: The I2C addresses to probe, ignore or force (for detect)
+ * @clients: List of detected clients we created (for i2c-core use only)
  *
  * The driver.owner field should be set to the module owner of this driver.
  * The driver.name field should be set to the name of this driver.
+ *
+ * For automatic device detection, both @detect and @address_data must
+ * be defined. @class should also be set, otherwise only devices forced
+ * with module parameters will be created. The detect function must
+ * fill at least the name field of the i2c_board_info structure it is
+ * handed upon successful detection, and possibly also the flags field.
+ *
+ * If @detect is missing, the driver will still work fine for enumerated
+ * devices. Detected devices simply won't be supported. This is expected
+ * for the many I2C/SMBus devices which can't be detected reliably, and
+ * the ones which can always be enumerated in practice.
+ *
+ * The i2c_client structure which is handed to the @detect callback is
+ * not a real i2c_client. It is initialized just enough so that you can
+ * call i2c_smbus_read_byte_data and friends on it. Don't do anything
+ * else with it. In particular, calling dev_dbg and friends on it is
+ * not allowed.
  */
-
 struct i2c_driver {
 	int id;
 	unsigned int class;
@@ -141,6 +161,11 @@ struct i2c_driver {
 
 	struct device_driver driver;
 	const struct i2c_device_id *id_table;
+
+	/* Device detection callback for automatic device creation */
+	int (*detect)(struct i2c_client *, int kind, struct i2c_board_info *);
+	const struct i2c_client_address_data *address_data;
+	struct list_head clients;
 };
 #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver)
 
@@ -156,6 +181,7 @@ struct i2c_driver {
  * @dev: Driver model device node for the slave.
  * @irq: indicates the IRQ generated by this device (if any)
  * @list: list of active/busy clients (DEPRECATED)
+ * @detected: member of an i2c_driver.clients list
  * @released: used to synchronize client releases & detaches and references
  *
  * An i2c_client identifies a single device (i.e. chip) connected to an
@@ -173,6 +199,7 @@ struct i2c_client {
 	struct device dev;		/* the device structure		*/
 	int irq;			/* irq issued by device		*/
 	struct list_head list;		/* DEPRECATED */
+	struct list_head detected;
 	struct completion released;
 };
 #define to_i2c_client(d) container_of(d, struct i2c_client, dev)
@@ -350,10 +377,11 @@ static inline void i2c_set_adapdata (struct i2c_adapter *dev, void *data)
 #define I2C_CLASS_HWMON		(1<<0)	/* lm_sensors, ... */
 #define I2C_CLASS_TV_ANALOG	(1<<1)	/* bttv + friends */
 #define I2C_CLASS_TV_DIGITAL	(1<<2)	/* dvb cards */
-#define I2C_CLASS_DDC		(1<<3)	/* i2c-matroxfb ? */
+#define I2C_CLASS_DDC		(1<<3)	/* DDC bus on graphics adapters */
 #define I2C_CLASS_CAM_ANALOG	(1<<4)	/* camera with analog CCD */
 #define I2C_CLASS_CAM_DIGITAL	(1<<5)	/* most webcams */
 #define I2C_CLASS_SOUND		(1<<6)	/* sound devices */
+#define I2C_CLASS_SPD		(1<<7)	/* SPD EEPROMs and similar */
 #define I2C_CLASS_ALL		(UINT_MAX) /* all of the above */
 
 /* i2c_client_address_data is the struct for holding default client
@@ -537,7 +565,7 @@ union i2c_smbus_data {
 	                       /* and one more for user-space compatibility */
 };
 
-/* smbus_access read or write markers */
+/* i2c_smbus_xfer read or write markers */
 #define I2C_SMBUS_READ	1
 #define I2C_SMBUS_WRITE	0
 
diff --git a/include/linux/i2c/at24.h b/include/linux/i2c/at24.h
new file mode 100644
index 00000000000..f6edd522a92
--- /dev/null
+++ b/include/linux/i2c/at24.h
@@ -0,0 +1,28 @@
+#ifndef _LINUX_AT24_H
+#define _LINUX_AT24_H
+
+#include <linux/types.h>
+
+/*
+ * As seen through Linux I2C, differences between the most common types of I2C
+ * memory include:
+ * - How much memory is available (usually specified in bit)?
+ * - What write page size does it support?
+ * - Special flags (16 bit addresses, read_only, world readable...)?
+ *
+ * If you set up a custom eeprom type, please double-check the parameters.
+ * Especially page_size needs extra care, as you risk data loss if your value
+ * is bigger than what the chip actually supports!
+ */
+
+struct at24_platform_data {
+	u32		byte_len;		/* size (sum of all addr) */
+	u16		page_size;		/* for writes */
+	u8		flags;
+#define AT24_FLAG_ADDR16	0x80	/* address pointer is 16 bit */
+#define AT24_FLAG_READONLY	0x40	/* sysfs-entry will be read-only */
+#define AT24_FLAG_IRUGO		0x20	/* sysfs-entry will be world-readable */
+#define AT24_FLAG_TAKE8ADDR	0x10	/* take always 8 addresses (24c00) */
+};
+
+#endif /* _LINUX_AT24_H */
diff --git a/include/linux/ide.h b/include/linux/ide.h
index eddb6daadf4..ac4eeb2932e 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -364,7 +364,6 @@ typedef struct ide_drive_s {
         u8	wcache;		/* status of write cache */
 	u8	acoustic;	/* acoustic management */
 	u8	media;		/* disk, cdrom, tape, floppy, ... */
-	u8	ctl;		/* "normal" value for Control register */
 	u8	ready_stat;	/* min status value for drive ready */
 	u8	mult_count;	/* current multiple sector setting */
 	u8	mult_req;	/* requested multiple sector setting */
@@ -493,7 +492,7 @@ typedef struct hwif_s {
 	void (*ide_dma_clear_irq)(ide_drive_t *drive);
 
 	void (*OUTB)(u8 addr, unsigned long port);
-	void (*OUTBSYNC)(ide_drive_t *drive, u8 addr, unsigned long port);
+	void (*OUTBSYNC)(struct hwif_s *hwif, u8 addr, unsigned long port);
 
 	u8  (*INB)(unsigned long port);
 
@@ -532,7 +531,6 @@ typedef struct hwif_s {
 	unsigned	serialized : 1;	/* serialized all channel operation */
 	unsigned	sharing_irq: 1;	/* 1 = sharing irq with another hwif */
 	unsigned	sg_mapped  : 1;	/* sg_table and sg_nents are ready */
-	unsigned	mmio       : 1; /* host uses MMIO */
 
 	struct device		gendev;
 	struct device		*portdev;
@@ -604,12 +602,13 @@ enum {
 	PC_FLAG_SUPPRESS_ERROR		= (1 << 1),
 	PC_FLAG_WAIT_FOR_DSC		= (1 << 2),
 	PC_FLAG_DMA_OK			= (1 << 3),
-	PC_FLAG_DMA_RECOMMENDED		= (1 << 4),
-	PC_FLAG_DMA_IN_PROGRESS		= (1 << 5),
-	PC_FLAG_DMA_ERROR		= (1 << 6),
-	PC_FLAG_WRITING			= (1 << 7),
+	PC_FLAG_DMA_IN_PROGRESS		= (1 << 4),
+	PC_FLAG_DMA_ERROR		= (1 << 5),
+	PC_FLAG_WRITING			= (1 << 6),
 	/* command timed out */
-	PC_FLAG_TIMEDOUT		= (1 << 8),
+	PC_FLAG_TIMEDOUT		= (1 << 7),
+	PC_FLAG_ZIP_DRIVE		= (1 << 8),
+	PC_FLAG_DRQ_INTERRUPT		= (1 << 9),
 };
 
 struct ide_atapi_pc {
@@ -642,8 +641,8 @@ struct ide_atapi_pc {
 	 * to change/removal later.
 	 */
 	u8 pc_buf[256];
-	void (*idefloppy_callback) (ide_drive_t *);
-	ide_startstop_t (*idetape_callback) (ide_drive_t *);
+
+	void (*callback)(ide_drive_t *);
 
 	/* idetape only */
 	struct idetape_bh *bh;
@@ -813,10 +812,6 @@ int generic_ide_ioctl(ide_drive_t *, struct file *, struct block_device *, unsig
 #ifndef _IDE_C
 extern	ide_hwif_t	ide_hwifs[];		/* master data repository */
 #endif
-extern int ide_noacpi;
-extern int ide_acpigtf;
-extern int ide_acpionboot;
-extern int noautodma;
 
 extern int ide_vlb_clk;
 extern int ide_pci_clk;
@@ -857,25 +852,12 @@ int ide_wait_stat(ide_startstop_t *, ide_drive_t *, u8, u8, unsigned long);
 
 extern ide_startstop_t ide_do_reset (ide_drive_t *);
 
-extern void ide_init_drive_cmd (struct request *rq);
-
-/*
- * "action" parameter type for ide_do_drive_cmd() below.
- */
-typedef enum {
-	ide_wait,	/* insert rq at end of list, and wait for it */
-	ide_preempt,	/* insert rq in front of current request */
-	ide_head_wait,	/* insert rq in front of current request and wait for it */
-	ide_end		/* insert rq at end of list, but don't wait for it */
-} ide_action_t;
-
-extern int ide_do_drive_cmd(ide_drive_t *, struct request *, ide_action_t);
+extern void ide_do_drive_cmd(ide_drive_t *, struct request *);
 
 extern void ide_end_drive_cmd(ide_drive_t *, u8, u8);
 
 enum {
 	IDE_TFLAG_LBA48			= (1 << 0),
-	IDE_TFLAG_NO_SELECT_MASK	= (1 << 1),
 	IDE_TFLAG_FLAGGED		= (1 << 2),
 	IDE_TFLAG_OUT_DATA		= (1 << 3),
 	IDE_TFLAG_OUT_HOB_FEATURE	= (1 << 4),
@@ -980,11 +962,23 @@ typedef struct ide_task_s {
 void ide_tf_dump(const char *, struct ide_taskfile *);
 
 extern void SELECT_DRIVE(ide_drive_t *);
+void SELECT_MASK(ide_drive_t *, int);
 
 extern int drive_is_ready(ide_drive_t *);
 
 void ide_pktcmd_tf_load(ide_drive_t *, u32, u16, u8);
 
+ide_startstop_t ide_pc_intr(ide_drive_t *drive, struct ide_atapi_pc *pc,
+	ide_handler_t *handler, unsigned int timeout, ide_expiry_t *expiry,
+	void (*update_buffers)(ide_drive_t *, struct ide_atapi_pc *),
+	void (*retry_pc)(ide_drive_t *), void (*dsc_handle)(ide_drive_t *),
+	void (*io_buffers)(ide_drive_t *, struct ide_atapi_pc *, unsigned int,
+			   int));
+ide_startstop_t ide_transfer_pc(ide_drive_t *, struct ide_atapi_pc *,
+				ide_handler_t *, unsigned int, ide_expiry_t *);
+ide_startstop_t ide_issue_pc(ide_drive_t *, struct ide_atapi_pc *,
+			     ide_handler_t *, unsigned int, ide_expiry_t *);
+
 ide_startstop_t do_rw_taskfile(ide_drive_t *, ide_task_t *);
 
 void task_end_request(ide_drive_t *, struct request *, u8);
@@ -996,8 +990,6 @@ int ide_taskfile_ioctl(ide_drive_t *, unsigned int, unsigned long);
 int ide_cmd_ioctl(ide_drive_t *, unsigned int, unsigned long);
 int ide_task_ioctl(ide_drive_t *, unsigned int, unsigned long);
 
-extern int system_bus_clock(void);
-
 extern int ide_driveid_update(ide_drive_t *);
 extern int ide_config_drive_speed(ide_drive_t *, u8);
 extern u8 eighty_ninty_three (ide_drive_t *);
@@ -1349,7 +1341,8 @@ static inline void ide_set_irq(ide_drive_t *drive, int on)
 {
 	ide_hwif_t *hwif = drive->hwif;
 
-	hwif->OUTB(drive->ctl | (on ? 0 : 2), hwif->io_ports.ctl_addr);
+	hwif->OUTBSYNC(hwif, ATA_DEVCTL_OBS | (on ? 0 : 2),
+		       hwif->io_ports.ctl_addr);
 }
 
 static inline u8 ide_read_status(ide_drive_t *drive)
diff --git a/include/linux/ihex.h b/include/linux/ihex.h
new file mode 100644
index 00000000000..2baace2788a
--- /dev/null
+++ b/include/linux/ihex.h
@@ -0,0 +1,74 @@
+/*
+ * Compact binary representation of ihex records. Some devices need their
+ * firmware loaded in strange orders rather than a single big blob, but
+ * actually parsing ihex-as-text within the kernel seems silly. Thus,...
+ */
+
+#ifndef __LINUX_IHEX_H__
+#define __LINUX_IHEX_H__
+
+#include <linux/types.h>
+#include <linux/firmware.h>
+#include <linux/device.h>
+
+/* Intel HEX files actually limit the length to 256 bytes, but we have
+   drivers which would benefit from using separate records which are
+   longer than that, so we extend to 16 bits of length */
+struct ihex_binrec {
+	__be32 addr;
+	__be16 len;
+	uint8_t data[0];
+} __attribute__((aligned(4)));
+
+/* Find the next record, taking into account the 4-byte alignment */
+static inline const struct ihex_binrec *
+ihex_next_binrec(const struct ihex_binrec *rec)
+{
+	int next = ((be16_to_cpu(rec->len) + 5) & ~3) - 2;
+	rec = (void *)&rec->data[next];
+
+	return be16_to_cpu(rec->len) ? rec : NULL;
+}
+
+/* Check that ihex_next_binrec() won't take us off the end of the image... */
+static inline int ihex_validate_fw(const struct firmware *fw)
+{
+	const struct ihex_binrec *rec;
+	size_t ofs = 0;
+
+	while (ofs <= fw->size - sizeof(*rec)) {
+		rec = (void *)&fw->data[ofs];
+
+		/* Zero length marks end of records */
+		if (!be16_to_cpu(rec->len))
+			return 0;
+
+		/* Point to next record... */
+		ofs += (sizeof(*rec) + be16_to_cpu(rec->len) + 3) & ~3;
+	}
+	return -EINVAL;
+}
+
+/* Request firmware and validate it so that we can trust we won't
+ * run off the end while reading records... */
+static inline int request_ihex_firmware(const struct firmware **fw,
+					const char *fw_name,
+					struct device *dev)
+{
+	const struct firmware *lfw;
+	int ret;
+
+	ret = request_firmware(&lfw, fw_name, dev);
+	if (ret)
+		return ret;
+	ret = ihex_validate_fw(lfw);
+	if (ret) {
+		dev_err(dev, "Firmware \"%s\" not valid IHEX records\n",
+			fw_name);
+		release_firmware(lfw);
+		return ret;
+	}
+	*fw = lfw;
+	return 0;
+}
+#endif /* __LINUX_IHEX_H__ */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a86186dd047..62aa4f895ab 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -104,8 +104,11 @@ extern void enable_irq(unsigned int irq);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
 
+extern cpumask_t irq_default_affinity;
+
 extern int irq_set_affinity(unsigned int irq, cpumask_t cpumask);
 extern int irq_can_set_affinity(unsigned int irq);
+extern int irq_select_affinity(unsigned int irq);
 
 #else /* CONFIG_SMP */
 
@@ -119,6 +122,8 @@ static inline int irq_can_set_affinity(unsigned int irq)
 	return 0;
 }
 
+static inline int irq_select_affinity(unsigned int irq)  { return 0; }
+
 #endif /* CONFIG_SMP && CONFIG_GENERIC_HARDIRQS */
 
 #ifdef CONFIG_GENERIC_HARDIRQS
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 552e0ec269c..8ccb462ea42 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -244,15 +244,6 @@ static inline void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
 }
 #endif
 
-#ifdef CONFIG_AUTO_IRQ_AFFINITY
-extern int select_smp_affinity(unsigned int irq);
-#else
-static inline int select_smp_affinity(unsigned int irq)
-{
-	return 1;
-}
-#endif
-
 extern int no_irq_affinity;
 
 static inline int irq_balancing_disabled(unsigned int irq)
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d147f0f9036..3dd20900709 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -168,6 +168,8 @@ struct commit_header {
 	unsigned char   h_chksum_size;
 	unsigned char 	h_padding[2];
 	__be32 		h_chksum[JBD2_CHECKSUM_BYTES];
+	__be64		h_commit_sec;
+	__be32		h_commit_nsec;
 };
 
 /*
@@ -379,6 +381,38 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
 	bit_spin_unlock(BH_JournalHead, &bh->b_state);
 }
 
+/* Flags in jbd_inode->i_flags */
+#define __JI_COMMIT_RUNNING 0
+/* Commit of the inode data in progress. We use this flag to protect us from
+ * concurrent deletion of inode. We cannot use reference to inode for this
+ * since we cannot afford doing last iput() on behalf of kjournald
+ */
+#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
+
+/**
+ * struct jbd_inode is the structure linking inodes in ordered mode
+ *   present in a transaction so that we can sync them during commit.
+ */
+struct jbd2_inode {
+	/* Which transaction does this inode belong to? Either the running
+	 * transaction or the committing one. [j_list_lock] */
+	transaction_t *i_transaction;
+
+	/* Pointer to the running transaction modifying inode's data in case
+	 * there is already a committing transaction touching it. [j_list_lock] */
+	transaction_t *i_next_transaction;
+
+	/* List of inodes in the i_transaction [j_list_lock] */
+	struct list_head i_list;
+
+	/* VFS inode this inode belongs to [constant during the lifetime
+	 * of the structure] */
+	struct inode *i_vfs_inode;
+
+	/* Flags of inode [j_list_lock] */
+	unsigned int i_flags;
+};
+
 struct jbd2_revoke_table_s;
 
 /**
@@ -509,24 +543,12 @@ struct transaction_s
 	struct journal_head	*t_reserved_list;
 
 	/*
-	 * Doubly-linked circular list of all buffers under writeout during
-	 * commit [j_list_lock]
-	 */
-	struct journal_head	*t_locked_list;
-
-	/*
 	 * Doubly-linked circular list of all metadata buffers owned by this
 	 * transaction [j_list_lock]
 	 */
 	struct journal_head	*t_buffers;
 
 	/*
-	 * Doubly-linked circular list of all data buffers still to be
-	 * flushed before this transaction can be committed [j_list_lock]
-	 */
-	struct journal_head	*t_sync_datalist;
-
-	/*
 	 * Doubly-linked circular list of all forget buffers (superseded
 	 * buffers which we can un-checkpoint once this transaction commits)
 	 * [j_list_lock]
@@ -565,6 +587,12 @@ struct transaction_s
 	struct journal_head	*t_log_list;
 
 	/*
+	 * List of inodes whose data we've modified in data=ordered mode.
+	 * [j_list_lock]
+	 */
+	struct list_head	t_inode_list;
+
+	/*
 	 * Protects info related to handles
 	 */
 	spinlock_t		t_handle_lock;
@@ -1004,7 +1032,6 @@ extern int	 jbd2_journal_extend (handle_t *, int nblocks);
 extern int	 jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
-extern int	 jbd2_journal_dirty_data (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
 extern void	 jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
@@ -1044,6 +1071,10 @@ extern void	   jbd2_journal_ack_err    (journal_t *);
 extern int	   jbd2_journal_clear_err  (journal_t *);
 extern int	   jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
 extern int	   jbd2_journal_force_commit(journal_t *);
+extern int	   jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
+extern int	   jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode, loff_t new_size);
+extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
+extern void	   jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode);
 
 /*
  * journal_head management
@@ -1179,15 +1210,13 @@ static inline int jbd_space_needed(journal_t *journal)
 
 /* journaling buffer types */
 #define BJ_None		0	/* Not journaled */
-#define BJ_SyncData	1	/* Normal data: flush before commit */
-#define BJ_Metadata	2	/* Normal journaled metadata */
-#define BJ_Forget	3	/* Buffer superseded by this transaction */
-#define BJ_IO		4	/* Buffer is for temporary IO use */
-#define BJ_Shadow	5	/* Buffer contents being shadowed to the log */
-#define BJ_LogCtl	6	/* Buffer contains log descriptors */
-#define BJ_Reserved	7	/* Buffer is reserved for access by journal */
-#define BJ_Locked	8	/* Locked for I/O during commit */
-#define BJ_Types	9
+#define BJ_Metadata	1	/* Normal journaled metadata */
+#define BJ_Forget	2	/* Buffer superseded by this transaction */
+#define BJ_IO		3	/* Buffer is for temporary IO use */
+#define BJ_Shadow	4	/* Buffer contents being shadowed to the log */
+#define BJ_LogCtl	5	/* Buffer contains log descriptors */
+#define BJ_Reserved	6	/* Buffer is reserved for access by journal */
+#define BJ_Types	7
 
 extern int jbd_blocks_per_page(struct inode *inode);
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index e57e5d08312..5b247b8a6b3 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -27,6 +27,7 @@
 #define __LINUX_LIBATA_H__
 
 #include <linux/delay.h>
+#include <linux/jiffies.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
@@ -115,7 +116,7 @@ enum {
 	/* tag ATA_MAX_QUEUE - 1 is reserved for internal commands */
 	ATA_MAX_QUEUE		= 32,
 	ATA_TAG_INTERNAL	= ATA_MAX_QUEUE - 1,
-	ATA_SHORT_PAUSE		= (HZ >> 6) + 1,
+	ATA_SHORT_PAUSE		= 16,
 
 	ATAPI_MAX_DRAIN		= 16 << 10,
 
@@ -168,6 +169,7 @@ enum {
 	ATA_LFLAG_ASSUME_CLASS	= ATA_LFLAG_ASSUME_ATA | ATA_LFLAG_ASSUME_SEMB,
 	ATA_LFLAG_NO_RETRY	= (1 << 5), /* don't retry this link */
 	ATA_LFLAG_DISABLED	= (1 << 6), /* link is disabled */
+	ATA_LFLAG_SW_ACTIVITY	= (1 << 7), /* keep activity stats */
 
 	/* struct ata_port flags */
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
@@ -190,6 +192,10 @@ enum {
 	ATA_FLAG_AN		= (1 << 18), /* controller supports AN */
 	ATA_FLAG_PMP		= (1 << 19), /* controller supports PMP */
 	ATA_FLAG_IPM		= (1 << 20), /* driver can handle IPM */
+	ATA_FLAG_EM		= (1 << 21), /* driver supports enclosure
+					      * management */
+	ATA_FLAG_SW_ACTIVITY	= (1 << 22), /* driver supports sw activity
+					      * led */
 
 	/* The following flag belongs to ap->pflags but is kept in
 	 * ap->flags because it's referenced in many LLDs and will be
@@ -234,17 +240,16 @@ enum {
 	/* bits 24:31 of host->flags are reserved for LLD specific flags */
 
 	/* various lengths of time */
-	ATA_TMOUT_BOOT		= 30 * HZ,	/* heuristic */
-	ATA_TMOUT_BOOT_QUICK	= 7 * HZ,	/* heuristic */
-	ATA_TMOUT_INTERNAL	= 30 * HZ,
-	ATA_TMOUT_INTERNAL_QUICK = 5 * HZ,
+	ATA_TMOUT_BOOT		= 30000,	/* heuristic */
+	ATA_TMOUT_BOOT_QUICK	=  7000,	/* heuristic */
+	ATA_TMOUT_INTERNAL_QUICK = 5000,
 
 	/* FIXME: GoVault needs 2s but we can't afford that without
 	 * parallel probing.  800ms is enough for iVDR disk
 	 * HHD424020F7SV00.  Increase to 2secs when parallel probing
 	 * is in place.
 	 */
-	ATA_TMOUT_FF_WAIT	= 4 * HZ / 5,
+	ATA_TMOUT_FF_WAIT	=  800,
 
 	/* Spec mandates to wait for ">= 2ms" before checking status
 	 * after reset.  We wait 150ms, because that was the magic
@@ -256,14 +261,14 @@ enum {
 	 *
 	 * Old drivers/ide uses the 2mS rule and then waits for ready.
 	 */
-	ATA_WAIT_AFTER_RESET_MSECS = 150,
+	ATA_WAIT_AFTER_RESET	=  150,
 
 	/* If PMP is supported, we have to do follow-up SRST.  As some
 	 * PMPs don't send D2H Reg FIS after hardreset, LLDs are
 	 * advised to wait only for the following duration before
 	 * doing SRST.
 	 */
-	ATA_TMOUT_PMP_SRST_WAIT	= 1 * HZ,
+	ATA_TMOUT_PMP_SRST_WAIT	= 1000,
 
 	/* ATA bus states */
 	BUS_UNKNOWN		= 0,
@@ -340,6 +345,11 @@ enum {
 
 	SATA_PMP_RW_TIMEOUT	= 3000,		/* PMP read/write timeout */
 
+	/* This should match the actual table size of
+	 * ata_eh_cmd_timeout_table in libata-eh.c.
+	 */
+	ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 5,
+
 	/* Horkage types. May be set by libata or controller on drives
 	   (some horkage may be drive/controller pair dependant */
 
@@ -441,6 +451,15 @@ enum link_pm {
 	MEDIUM_POWER,
 };
 extern struct device_attribute dev_attr_link_power_management_policy;
+extern struct device_attribute dev_attr_em_message_type;
+extern struct device_attribute dev_attr_em_message;
+extern struct device_attribute dev_attr_sw_activity;
+
+enum sw_activity {
+	OFF,
+	BLINK_ON,
+	BLINK_OFF,
+};
 
 #ifdef CONFIG_ATA_SFF
 struct ata_ioports {
@@ -597,10 +616,14 @@ struct ata_eh_info {
 struct ata_eh_context {
 	struct ata_eh_info	i;
 	int			tries[ATA_MAX_DEVICES];
+	int			cmd_timeout_idx[ATA_MAX_DEVICES]
+					       [ATA_EH_CMD_TIMEOUT_TABLE_SIZE];
 	unsigned int		classes[ATA_MAX_DEVICES];
 	unsigned int		did_probe_mask;
 	unsigned int		saved_ncq_enabled;
 	u8			saved_xfer_mode[ATA_MAX_DEVICES];
+	/* timestamp for the last reset attempt or success */
+	unsigned long		last_reset;
 };
 
 struct ata_acpi_drive
@@ -692,6 +715,7 @@ struct ata_port {
 	struct timer_list	fastdrain_timer;
 	unsigned long		fastdrain_cnt;
 
+	int			em_message_type;
 	void			*private_data;
 
 #ifdef CONFIG_ATA_ACPI
@@ -783,6 +807,12 @@ struct ata_port_operations {
 	u8   (*bmdma_status)(struct ata_port *ap);
 #endif /* CONFIG_ATA_SFF */
 
+	ssize_t (*em_show)(struct ata_port *ap, char *buf);
+	ssize_t (*em_store)(struct ata_port *ap, const char *message,
+			    size_t size);
+	ssize_t (*sw_activity_show)(struct ata_device *dev, char *buf);
+	ssize_t (*sw_activity_store)(struct ata_device *dev,
+				     enum sw_activity val);
 	/*
 	 * Obsolete
 	 */
@@ -895,8 +925,7 @@ extern void ata_host_resume(struct ata_host *host);
 #endif
 extern int ata_ratelimit(void);
 extern u32 ata_wait_register(void __iomem *reg, u32 mask, u32 val,
-			     unsigned long interval_msec,
-			     unsigned long timeout_msec);
+			     unsigned long interval, unsigned long timeout);
 extern int atapi_cmd_type(u8 opcode);
 extern void ata_tf_to_fis(const struct ata_taskfile *tf,
 			  u8 pmp, int is_cmd, u8 *fis);
@@ -1389,6 +1418,12 @@ static inline int ata_check_ready(u8 status)
 	return 0;
 }
 
+static inline unsigned long ata_deadline(unsigned long from_jiffies,
+					 unsigned long timeout_msecs)
+{
+	return from_jiffies + msecs_to_jiffies(timeout_msecs);
+}
+
 
 /**************************************************************************
  * PMP - drivers/ata/libata-pmp.c
diff --git a/include/linux/list.h b/include/linux/list.h
index 08cf4f65188..139ec41d9c2 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -85,65 +85,6 @@ static inline void list_add_tail(struct list_head *new, struct list_head *head)
 }
 
 /*
- * Insert a new entry between two known consecutive entries.
- *
- * This is only for internal list manipulation where we know
- * the prev/next entries already!
- */
-static inline void __list_add_rcu(struct list_head * new,
-		struct list_head * prev, struct list_head * next)
-{
-	new->next = next;
-	new->prev = prev;
-	smp_wmb();
-	next->prev = new;
-	prev->next = new;
-}
-
-/**
- * list_add_rcu - add a new entry to rcu-protected list
- * @new: new entry to be added
- * @head: list head to add it after
- *
- * Insert a new entry after the specified head.
- * This is good for implementing stacks.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as list_add_rcu()
- * or list_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * list_for_each_entry_rcu().
- */
-static inline void list_add_rcu(struct list_head *new, struct list_head *head)
-{
-	__list_add_rcu(new, head, head->next);
-}
-
-/**
- * list_add_tail_rcu - add a new entry to rcu-protected list
- * @new: new entry to be added
- * @head: list head to add it before
- *
- * Insert a new entry before the specified head.
- * This is useful for implementing queues.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as list_add_tail_rcu()
- * or list_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * list_for_each_entry_rcu().
- */
-static inline void list_add_tail_rcu(struct list_head *new,
-					struct list_head *head)
-{
-	__list_add_rcu(new, head->prev, head);
-}
-
-/*
  * Delete a list entry by making the prev/next entries
  * point to each other.
  *
@@ -174,36 +115,6 @@ extern void list_del(struct list_head *entry);
 #endif
 
 /**
- * list_del_rcu - deletes entry from list without re-initialization
- * @entry: the element to delete from the list.
- *
- * Note: list_empty() on entry does not return true after this,
- * the entry is in an undefined state. It is useful for RCU based
- * lockfree traversal.
- *
- * In particular, it means that we can not poison the forward
- * pointers that may still be used for walking the list.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as list_del_rcu()
- * or list_add_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * list_for_each_entry_rcu().
- *
- * Note that the caller is not permitted to immediately free
- * the newly deleted entry.  Instead, either synchronize_rcu()
- * or call_rcu() must be used to defer freeing until an RCU
- * grace period has elapsed.
- */
-static inline void list_del_rcu(struct list_head *entry)
-{
-	__list_del(entry->prev, entry->next);
-	entry->prev = LIST_POISON2;
-}
-
-/**
  * list_replace - replace old entry by new one
  * @old : the element to be replaced
  * @new : the new element to insert
@@ -227,25 +138,6 @@ static inline void list_replace_init(struct list_head *old,
 }
 
 /**
- * list_replace_rcu - replace old entry by new one
- * @old : the element to be replaced
- * @new : the new element to insert
- *
- * The @old entry will be replaced with the @new entry atomically.
- * Note: @old should not be empty.
- */
-static inline void list_replace_rcu(struct list_head *old,
-				struct list_head *new)
-{
-	new->next = old->next;
-	new->prev = old->prev;
-	smp_wmb();
-	new->next->prev = new;
-	new->prev->next = new;
-	old->prev = LIST_POISON2;
-}
-
-/**
  * list_del_init - deletes entry from list and reinitialize it.
  * @entry: the element to delete from the list.
  */
@@ -369,62 +261,6 @@ static inline void list_splice_init(struct list_head *list,
 }
 
 /**
- * list_splice_init_rcu - splice an RCU-protected list into an existing list.
- * @list:	the RCU-protected list to splice
- * @head:	the place in the list to splice the first list into
- * @sync:	function to sync: synchronize_rcu(), synchronize_sched(), ...
- *
- * @head can be RCU-read traversed concurrently with this function.
- *
- * Note that this function blocks.
- *
- * Important note: the caller must take whatever action is necessary to
- *	prevent any other updates to @head.  In principle, it is possible
- *	to modify the list as soon as sync() begins execution.
- *	If this sort of thing becomes necessary, an alternative version
- *	based on call_rcu() could be created.  But only if -really-
- *	needed -- there is no shortage of RCU API members.
- */
-static inline void list_splice_init_rcu(struct list_head *list,
-					struct list_head *head,
-					void (*sync)(void))
-{
-	struct list_head *first = list->next;
-	struct list_head *last = list->prev;
-	struct list_head *at = head->next;
-
-	if (list_empty(head))
-		return;
-
-	/* "first" and "last" tracking list, so initialize it. */
-
-	INIT_LIST_HEAD(list);
-
-	/*
-	 * At this point, the list body still points to the source list.
-	 * Wait for any readers to finish using the list before splicing
-	 * the list body into the new list.  Any new readers will see
-	 * an empty list.
-	 */
-
-	sync();
-
-	/*
-	 * Readers are finished with the source list, so perform splice.
-	 * The order is important if the new list is global and accessible
-	 * to concurrent RCU readers.  Note that RCU readers are not
-	 * permitted to traverse the prev pointers without excluding
-	 * this function.
-	 */
-
-	last->next = at;
-	smp_wmb();
-	head->next = first;
-	first->prev = head;
-	at->prev = last;
-}
-
-/**
  * list_entry - get the struct for this entry
  * @ptr:	the &struct list_head pointer.
  * @type:	the type of the struct this is embedded in.
@@ -629,57 +465,6 @@ static inline void list_splice_init_rcu(struct list_head *list,
 	     &pos->member != (head); 					\
 	     pos = n, n = list_entry(n->member.prev, typeof(*n), member))
 
-/**
- * list_for_each_rcu	-	iterate over an rcu-protected list
- * @pos:	the &struct list_head to use as a loop cursor.
- * @head:	the head for your list.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_rcu(pos, head) \
-	for (pos = rcu_dereference((head)->next); \
-		prefetch(pos->next), pos != (head); \
-		pos = rcu_dereference(pos->next))
-
-#define __list_for_each_rcu(pos, head) \
-	for (pos = rcu_dereference((head)->next); \
-		pos != (head); \
-		pos = rcu_dereference(pos->next))
-
-/**
- * list_for_each_entry_rcu	-	iterate over rcu list of given type
- * @pos:	the type * to use as a loop cursor.
- * @head:	the head for your list.
- * @member:	the name of the list_struct within the struct.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_entry_rcu(pos, head, member) \
-	for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
-		prefetch(pos->member.next), &pos->member != (head); \
-		pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
-
-
-/**
- * list_for_each_continue_rcu
- * @pos:	the &struct list_head to use as a loop cursor.
- * @head:	the head for your list.
- *
- * Iterate over an rcu-protected list, continuing after current point.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as list_add_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define list_for_each_continue_rcu(pos, head) \
-	for ((pos) = rcu_dereference((pos)->next); \
-		prefetch((pos)->next), (pos) != (head); \
-		(pos) = rcu_dereference((pos)->next))
-
 /*
  * Double linked lists with a single pointer list head.
  * Mostly useful for hash tables where the two pointer list head is
@@ -730,31 +515,6 @@ static inline void hlist_del(struct hlist_node *n)
 	n->pprev = LIST_POISON2;
 }
 
-/**
- * hlist_del_rcu - deletes entry from hash list without re-initialization
- * @n: the element to delete from the hash list.
- *
- * Note: list_unhashed() on entry does not return true after this,
- * the entry is in an undefined state. It is useful for RCU based
- * lockfree traversal.
- *
- * In particular, it means that we can not poison the forward
- * pointers that may still be used for walking the hash list.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_add_head_rcu()
- * or hlist_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_for_each_entry().
- */
-static inline void hlist_del_rcu(struct hlist_node *n)
-{
-	__hlist_del(n);
-	n->pprev = LIST_POISON2;
-}
-
 static inline void hlist_del_init(struct hlist_node *n)
 {
 	if (!hlist_unhashed(n)) {
@@ -763,27 +523,6 @@ static inline void hlist_del_init(struct hlist_node *n)
 	}
 }
 
-/**
- * hlist_replace_rcu - replace old entry by new one
- * @old : the element to be replaced
- * @new : the new element to insert
- *
- * The @old entry will be replaced with the @new entry atomically.
- */
-static inline void hlist_replace_rcu(struct hlist_node *old,
-					struct hlist_node *new)
-{
-	struct hlist_node *next = old->next;
-
-	new->next = next;
-	new->pprev = old->pprev;
-	smp_wmb();
-	if (next)
-		new->next->pprev = &new->next;
-	*new->pprev = new;
-	old->pprev = LIST_POISON2;
-}
-
 static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
 {
 	struct hlist_node *first = h->first;
@@ -794,38 +533,6 @@ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
 	n->pprev = &h->first;
 }
 
-
-/**
- * hlist_add_head_rcu
- * @n: the element to add to the hash list.
- * @h: the list to add to.
- *
- * Description:
- * Adds the specified element to the specified hlist,
- * while permitting racing traversals.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_add_head_rcu()
- * or hlist_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_for_each_entry_rcu(), used to prevent memory-consistency
- * problems on Alpha CPUs.  Regardless of the type of CPU, the
- * list-traversal primitive must be guarded by rcu_read_lock().
- */
-static inline void hlist_add_head_rcu(struct hlist_node *n,
-					struct hlist_head *h)
-{
-	struct hlist_node *first = h->first;
-	n->next = first;
-	n->pprev = &h->first;
-	smp_wmb();
-	if (first)
-		first->pprev = &n->next;
-	h->first = n;
-}
-
 /* next must be != NULL */
 static inline void hlist_add_before(struct hlist_node *n,
 					struct hlist_node *next)
@@ -847,63 +554,6 @@ static inline void hlist_add_after(struct hlist_node *n,
 		next->next->pprev  = &next->next;
 }
 
-/**
- * hlist_add_before_rcu
- * @n: the new element to add to the hash list.
- * @next: the existing element to add the new element before.
- *
- * Description:
- * Adds the specified element to the specified hlist
- * before the specified node while permitting racing traversals.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_add_head_rcu()
- * or hlist_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_for_each_entry_rcu(), used to prevent memory-consistency
- * problems on Alpha CPUs.
- */
-static inline void hlist_add_before_rcu(struct hlist_node *n,
-					struct hlist_node *next)
-{
-	n->pprev = next->pprev;
-	n->next = next;
-	smp_wmb();
-	next->pprev = &n->next;
-	*(n->pprev) = n;
-}
-
-/**
- * hlist_add_after_rcu
- * @prev: the existing element to add the new element after.
- * @n: the new element to add to the hash list.
- *
- * Description:
- * Adds the specified element to the specified hlist
- * after the specified node while permitting racing traversals.
- *
- * The caller must take whatever precautions are necessary
- * (such as holding appropriate locks) to avoid racing
- * with another list-mutation primitive, such as hlist_add_head_rcu()
- * or hlist_del_rcu(), running on this same list.
- * However, it is perfectly legal to run concurrently with
- * the _rcu list-traversal primitives, such as
- * hlist_for_each_entry_rcu(), used to prevent memory-consistency
- * problems on Alpha CPUs.
- */
-static inline void hlist_add_after_rcu(struct hlist_node *prev,
-				       struct hlist_node *n)
-{
-	n->next = prev->next;
-	n->pprev = &prev->next;
-	smp_wmb();
-	prev->next = n;
-	if (n->next)
-		n->next->pprev = &n->next;
-}
-
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 #define hlist_for_each(pos, head) \
@@ -964,21 +614,4 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
 		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
 	     pos = n)
 
-/**
- * hlist_for_each_entry_rcu - iterate over rcu list of given type
- * @tpos:	the type * to use as a loop cursor.
- * @pos:	the &struct hlist_node to use as a loop cursor.
- * @head:	the head for your list.
- * @member:	the name of the hlist_node within the struct.
- *
- * This list-traversal primitive may safely run concurrently with
- * the _rcu list-mutation primitives such as hlist_add_head_rcu()
- * as long as the traversal is guarded by rcu_read_lock().
- */
-#define hlist_for_each_entry_rcu(tpos, pos, head, member)		 \
-	for (pos = rcu_dereference((head)->first);			 \
-	        pos && ({ prefetch(pos->next); 1;}) &&			 \
-		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
-	     pos = rcu_dereference(pos->next))
-
 #endif
diff --git a/include/linux/lm_interface.h b/include/linux/lm_interface.h
index f274997bc28..2ed8fa1b762 100644
--- a/include/linux/lm_interface.h
+++ b/include/linux/lm_interface.h
@@ -122,11 +122,9 @@ typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data);
  */
 
 #define LM_OUT_ST_MASK		0x00000003
-#define LM_OUT_CACHEABLE	0x00000004
 #define LM_OUT_CANCELED		0x00000008
 #define LM_OUT_ASYNC		0x00000080
 #define LM_OUT_ERROR		0x00000100
-#define LM_OUT_CONV_DEADLK	0x00000200
 
 /*
  * lm_callback_t types
@@ -138,9 +136,6 @@ typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data);
  * LM_CB_NEED_RECOVERY
  * The given journal needs to be recovered.
  *
- * LM_CB_DROPLOCKS
- * Reduce the number of cached locks.
- *
  * LM_CB_ASYNC
  * The given lock has been granted.
  */
@@ -149,7 +144,6 @@ typedef void (*lm_callback_t) (void *ptr, unsigned int type, void *data);
 #define LM_CB_NEED_D		258
 #define LM_CB_NEED_S		259
 #define LM_CB_NEED_RECOVERY	260
-#define LM_CB_DROPLOCKS		261
 #define LM_CB_ASYNC		262
 
 /*
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index a744383d16e..81b3dd5206e 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -398,7 +398,8 @@ int mlx4_srq_query(struct mlx4_dev *dev, struct mlx4_srq *srq, int *limit_waterm
 int mlx4_INIT_PORT(struct mlx4_dev *dev, int port);
 int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port);
 
-int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]);
+int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  int block_mcast_loopback);
 int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]);
 
 int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list,
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 068a0c9946a..5c42821da2d 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -11,11 +11,21 @@
  */
 #ifdef CONFIG_BLOCK
 
+struct mpage_data {
+	struct bio *bio;
+	sector_t last_block_in_bio;
+	get_block_t *get_block;
+	unsigned use_writepage;
+};
+
 struct writeback_control;
 
+struct bio *mpage_bio_submit(int rw, struct bio *bio);
 int mpage_readpages(struct address_space *mapping, struct list_head *pages,
 				unsigned nr_pages, get_block_t get_block);
 int mpage_readpage(struct page *page, get_block_t get_block);
+int __mpage_writepage(struct page *page, struct writeback_control *wbc,
+		      void *data);
 int mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 9007ccdfc11..20838883535 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount);
 void percpu_counter_destroy(struct percpu_counter *fbc);
 void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
 void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
-s64 __percpu_counter_sum(struct percpu_counter *fbc);
+s64 __percpu_counter_sum(struct percpu_counter *fbc, int set);
 
 static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 {
@@ -44,13 +44,19 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 
 static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
 {
-	s64 ret = __percpu_counter_sum(fbc);
+	s64 ret = __percpu_counter_sum(fbc, 0);
 	return ret < 0 ? 0 : ret;
 }
 
+static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc)
+{
+	return __percpu_counter_sum(fbc, 1);
+}
+
+
 static inline s64 percpu_counter_sum(struct percpu_counter *fbc)
 {
-	return __percpu_counter_sum(fbc);
+	return __percpu_counter_sum(fbc, 0);
 }
 
 static inline s64 percpu_counter_read(struct percpu_counter *fbc)
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index b3aa05baab8..8c774905dcf 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -151,7 +151,10 @@ extern struct lockdep_map rcu_lock_map;
 
 #define __synchronize_sched() synchronize_rcu()
 
+#define call_rcu_sched(head, func) call_rcu(head, func)
+
 extern void __rcu_init(void);
+#define rcu_init_sched()	do { } while (0)
 extern void rcu_check_callbacks(int cpu, int user);
 extern void rcu_restart_cpu(int cpu);
 
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index bde4586f438..b0f39be08b6 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -1,6 +1,373 @@
 #ifndef _LINUX_RCULIST_H
 #define _LINUX_RCULIST_H
 
+#ifdef __KERNEL__
+
+/*
+ * RCU-protected list version
+ */
 #include <linux/list.h>
+#include <linux/rcupdate.h>
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_add_rcu(struct list_head *new,
+		struct list_head *prev, struct list_head *next)
+{
+	new->next = next;
+	new->prev = prev;
+	rcu_assign_pointer(prev->next, new);
+	next->prev = new;
+}
+
+/**
+ * list_add_rcu - add a new entry to rcu-protected list
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as list_add_rcu()
+ * or list_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * list_for_each_entry_rcu().
+ */
+static inline void list_add_rcu(struct list_head *new, struct list_head *head)
+{
+	__list_add_rcu(new, head, head->next);
+}
+
+/**
+ * list_add_tail_rcu - add a new entry to rcu-protected list
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head.
+ * This is useful for implementing queues.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as list_add_tail_rcu()
+ * or list_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * list_for_each_entry_rcu().
+ */
+static inline void list_add_tail_rcu(struct list_head *new,
+					struct list_head *head)
+{
+	__list_add_rcu(new, head->prev, head);
+}
+
+/**
+ * list_del_rcu - deletes entry from list without re-initialization
+ * @entry: the element to delete from the list.
+ *
+ * Note: list_empty() on entry does not return true after this,
+ * the entry is in an undefined state. It is useful for RCU based
+ * lockfree traversal.
+ *
+ * In particular, it means that we can not poison the forward
+ * pointers that may still be used for walking the list.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as list_del_rcu()
+ * or list_add_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * list_for_each_entry_rcu().
+ *
+ * Note that the caller is not permitted to immediately free
+ * the newly deleted entry.  Instead, either synchronize_rcu()
+ * or call_rcu() must be used to defer freeing until an RCU
+ * grace period has elapsed.
+ */
+static inline void list_del_rcu(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+	entry->prev = LIST_POISON2;
+}
+
+/**
+ * list_replace_rcu - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * The @old entry will be replaced with the @new entry atomically.
+ * Note: @old should not be empty.
+ */
+static inline void list_replace_rcu(struct list_head *old,
+				struct list_head *new)
+{
+	new->next = old->next;
+	new->prev = old->prev;
+	rcu_assign_pointer(new->prev->next, new);
+	new->next->prev = new;
+	old->prev = LIST_POISON2;
+}
+
+/**
+ * list_splice_init_rcu - splice an RCU-protected list into an existing list.
+ * @list:	the RCU-protected list to splice
+ * @head:	the place in the list to splice the first list into
+ * @sync:	function to sync: synchronize_rcu(), synchronize_sched(), ...
+ *
+ * @head can be RCU-read traversed concurrently with this function.
+ *
+ * Note that this function blocks.
+ *
+ * Important note: the caller must take whatever action is necessary to
+ *	prevent any other updates to @head.  In principle, it is possible
+ *	to modify the list as soon as sync() begins execution.
+ *	If this sort of thing becomes necessary, an alternative version
+ *	based on call_rcu() could be created.  But only if -really-
+ *	needed -- there is no shortage of RCU API members.
+ */
+static inline void list_splice_init_rcu(struct list_head *list,
+					struct list_head *head,
+					void (*sync)(void))
+{
+	struct list_head *first = list->next;
+	struct list_head *last = list->prev;
+	struct list_head *at = head->next;
+
+	if (list_empty(head))
+		return;
+
+	/* "first" and "last" tracking list, so initialize it. */
+
+	INIT_LIST_HEAD(list);
+
+	/*
+	 * At this point, the list body still points to the source list.
+	 * Wait for any readers to finish using the list before splicing
+	 * the list body into the new list.  Any new readers will see
+	 * an empty list.
+	 */
+
+	sync();
+
+	/*
+	 * Readers are finished with the source list, so perform splice.
+	 * The order is important if the new list is global and accessible
+	 * to concurrent RCU readers.  Note that RCU readers are not
+	 * permitted to traverse the prev pointers without excluding
+	 * this function.
+	 */
+
+	last->next = at;
+	rcu_assign_pointer(head->next, first);
+	first->prev = head;
+	at->prev = last;
+}
+
+/**
+ * list_for_each_rcu	-	iterate over an rcu-protected list
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as list_add_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ */
+#define list_for_each_rcu(pos, head) \
+	for (pos = rcu_dereference((head)->next); \
+		prefetch(pos->next), pos != (head); \
+		pos = rcu_dereference(pos->next))
+
+#define __list_for_each_rcu(pos, head) \
+	for (pos = rcu_dereference((head)->next); \
+		pos != (head); \
+		pos = rcu_dereference(pos->next))
+
+/**
+ * list_for_each_entry_rcu	-	iterate over rcu list of given type
+ * @pos:	the type * to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as list_add_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ */
+#define list_for_each_entry_rcu(pos, head, member) \
+	for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
+		prefetch(pos->member.next), &pos->member != (head); \
+		pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
+
+
+/**
+ * list_for_each_continue_rcu
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ *
+ * Iterate over an rcu-protected list, continuing after current point.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as list_add_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ */
+#define list_for_each_continue_rcu(pos, head) \
+	for ((pos) = rcu_dereference((pos)->next); \
+		prefetch((pos)->next), (pos) != (head); \
+		(pos) = rcu_dereference((pos)->next))
+
+/**
+ * hlist_del_rcu - deletes entry from hash list without re-initialization
+ * @n: the element to delete from the hash list.
+ *
+ * Note: list_unhashed() on entry does not return true after this,
+ * the entry is in an undefined state. It is useful for RCU based
+ * lockfree traversal.
+ *
+ * In particular, it means that we can not poison the forward
+ * pointers that may still be used for walking the hash list.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_entry().
+ */
+static inline void hlist_del_rcu(struct hlist_node *n)
+{
+	__hlist_del(n);
+	n->pprev = LIST_POISON2;
+}
+
+/**
+ * hlist_replace_rcu - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * The @old entry will be replaced with the @new entry atomically.
+ */
+static inline void hlist_replace_rcu(struct hlist_node *old,
+					struct hlist_node *new)
+{
+	struct hlist_node *next = old->next;
+
+	new->next = next;
+	new->pprev = old->pprev;
+	rcu_assign_pointer(*new->pprev, new);
+	if (next)
+		new->next->pprev = &new->next;
+	old->pprev = LIST_POISON2;
+}
+
+/**
+ * hlist_add_head_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist,
+ * while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_add_head_rcu(struct hlist_node *n,
+					struct hlist_head *h)
+{
+	struct hlist_node *first = h->first;
+
+	n->next = first;
+	n->pprev = &h->first;
+	rcu_assign_pointer(h->first, n);
+	if (first)
+		first->pprev = &n->next;
+}
+
+/**
+ * hlist_add_before_rcu
+ * @n: the new element to add to the hash list.
+ * @next: the existing element to add the new element before.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist
+ * before the specified node while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.
+ */
+static inline void hlist_add_before_rcu(struct hlist_node *n,
+					struct hlist_node *next)
+{
+	n->pprev = next->pprev;
+	n->next = next;
+	rcu_assign_pointer(*(n->pprev), n);
+	next->pprev = &n->next;
+}
+
+/**
+ * hlist_add_after_rcu
+ * @prev: the existing element to add the new element after.
+ * @n: the new element to add to the hash list.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist
+ * after the specified node while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_add_head_rcu()
+ * or hlist_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.
+ */
+static inline void hlist_add_after_rcu(struct hlist_node *prev,
+				       struct hlist_node *n)
+{
+	n->next = prev->next;
+	n->pprev = &prev->next;
+	rcu_assign_pointer(prev->next, n);
+	if (n->next)
+		n->next->pprev = &n->next;
+}
+
+/**
+ * hlist_for_each_entry_rcu - iterate over rcu list of given type
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct hlist_node to use as a loop cursor.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ *
+ * This list-traversal primitive may safely run concurrently with
+ * the _rcu list-mutation primitives such as hlist_add_head_rcu()
+ * as long as the traversal is guarded by rcu_read_lock().
+ */
+#define hlist_for_each_entry_rcu(tpos, pos, head, member)		 \
+	for (pos = rcu_dereference((head)->first);			 \
+		pos && ({ prefetch(pos->next); 1; }) &&			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
+		pos = rcu_dereference(pos->next))
 
-#endif	/* _LINUX_RCULIST_H */
+#endif	/* __KERNEL__ */
+#endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index d42dbec0608..e8b4039cfb2 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -40,6 +40,7 @@
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
 #include <linux/lockdep.h>
+#include <linux/completion.h>
 
 /**
  * struct rcu_head - callback structure for use with RCU
@@ -168,6 +169,27 @@ struct rcu_head {
 		(p) = (v); \
 	})
 
+/* Infrastructure to implement the synchronize_() primitives. */
+
+struct rcu_synchronize {
+	struct rcu_head head;
+	struct completion completion;
+};
+
+extern void wakeme_after_rcu(struct rcu_head  *head);
+
+#define synchronize_rcu_xxx(name, func) \
+void name(void) \
+{ \
+	struct rcu_synchronize rcu; \
+	\
+	init_completion(&rcu.completion); \
+	/* Will wake me after RCU finished. */ \
+	func(&rcu.head, wakeme_after_rcu); \
+	/* Wait for it. */ \
+	wait_for_completion(&rcu.completion); \
+}
+
 /**
  * synchronize_sched - block until all CPUs have exited any non-preemptive
  * kernel code sequences.
@@ -224,8 +246,8 @@ extern void call_rcu_bh(struct rcu_head *head,
 /* Exported common interfaces */
 extern void synchronize_rcu(void);
 extern void rcu_barrier(void);
-extern long rcu_batches_completed(void);
-extern long rcu_batches_completed_bh(void);
+extern void rcu_barrier_bh(void);
+extern void rcu_barrier_sched(void);
 
 /* Internal to kernel */
 extern void rcu_init(void);
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
index 8a05c7e20bc..f04b64eca63 100644
--- a/include/linux/rcupreempt.h
+++ b/include/linux/rcupreempt.h
@@ -40,10 +40,39 @@
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
 
-#define rcu_qsctr_inc(cpu)
+struct rcu_dyntick_sched {
+	int dynticks;
+	int dynticks_snap;
+	int sched_qs;
+	int sched_qs_snap;
+	int sched_dynticks_snap;
+};
+
+DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched);
+
+static inline void rcu_qsctr_inc(int cpu)
+{
+	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
+
+	rdssp->sched_qs++;
+}
 #define rcu_bh_qsctr_inc(cpu)
 #define call_rcu_bh(head, rcu) call_rcu(head, rcu)
 
+/**
+ * call_rcu_sched - Queue RCU callback for invocation after sched grace period.
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual update function to be invoked after the grace period
+ *
+ * The update function will be invoked some time after a full
+ * synchronize_sched()-style grace period elapses, in other words after
+ * all currently executing preempt-disabled sections of code (including
+ * hardirq handlers, NMI handlers, and local_irq_save() blocks) have
+ * completed.
+ */
+extern void call_rcu_sched(struct rcu_head *head,
+			   void (*func)(struct rcu_head *head));
+
 extern void __rcu_read_lock(void)	__acquires(RCU);
 extern void __rcu_read_unlock(void)	__releases(RCU);
 extern int rcu_pending(int cpu);
@@ -55,6 +84,7 @@ extern int rcu_needs_cpu(int cpu);
 extern void __synchronize_sched(void);
 
 extern void __rcu_init(void);
+extern void rcu_init_sched(void);
 extern void rcu_check_callbacks(int cpu, int user);
 extern void rcu_restart_cpu(int cpu);
 extern long rcu_batches_completed(void);
@@ -81,20 +111,20 @@ extern struct rcupreempt_trace *rcupreempt_trace_cpu(int cpu);
 struct softirq_action;
 
 #ifdef CONFIG_NO_HZ
-DECLARE_PER_CPU(long, dynticks_progress_counter);
+DECLARE_PER_CPU(struct rcu_dyntick_sched, rcu_dyntick_sched);
 
 static inline void rcu_enter_nohz(void)
 {
 	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	__get_cpu_var(dynticks_progress_counter)++;
-	WARN_ON(__get_cpu_var(dynticks_progress_counter) & 0x1);
+	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	WARN_ON(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1);
 }
 
 static inline void rcu_exit_nohz(void)
 {
-	__get_cpu_var(dynticks_progress_counter)++;
 	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
-	WARN_ON(!(__get_cpu_var(dynticks_progress_counter) & 0x1));
+	__get_cpu_var(rcu_dyntick_sched).dynticks++;
+	WARN_ON(!(__get_cpu_var(rcu_dyntick_sched).dynticks & 0x1));
 }
 
 #else /* CONFIG_NO_HZ */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 55232ccf9cf..48262f86c96 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -7,9 +7,18 @@
  */
 
 #include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/cpumask.h>
 
 extern void cpu_idle(void);
 
+struct call_single_data {
+	struct list_head list;
+	void (*func) (void *info);
+	void *info;
+	unsigned int flags;
+};
+
 #ifdef CONFIG_SMP
 
 #include <linux/preempt.h>
@@ -52,15 +61,34 @@ extern void smp_cpus_done(unsigned int max_cpus);
 /*
  * Call a function on all other processors
  */
-int smp_call_function(void(*func)(void *info), void *info, int retry, int wait);
-
+int smp_call_function(void(*func)(void *info), void *info, int wait);
+int smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
+				int wait);
 int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
-				int retry, int wait);
+				int wait);
+void __smp_call_function_single(int cpuid, struct call_single_data *data);
+
+/*
+ * Generic and arch helpers
+ */
+#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
+void generic_smp_call_function_single_interrupt(void);
+void generic_smp_call_function_interrupt(void);
+void init_call_single_data(void);
+void ipi_call_lock(void);
+void ipi_call_unlock(void);
+void ipi_call_lock_irq(void);
+void ipi_call_unlock_irq(void);
+#else
+static inline void init_call_single_data(void)
+{
+}
+#endif
 
 /*
  * Call a function on all processors
  */
-int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait);
+int on_each_cpu(void (*func) (void *info), void *info, int wait);
 
 #define MSG_ALL_BUT_SELF	0x8000	/* Assume <32768 CPU's */
 #define MSG_ALL			0x8001
@@ -90,9 +118,9 @@ static inline int up_smp_call_function(void (*func)(void *), void *info)
 {
 	return 0;
 }
-#define smp_call_function(func, info, retry, wait) \
+#define smp_call_function(func, info, wait) \
 			(up_smp_call_function(func, info))
-#define on_each_cpu(func,info,retry,wait)	\
+#define on_each_cpu(func,info,wait)		\
 	({					\
 		local_irq_disable();		\
 		func(info);			\
@@ -102,7 +130,7 @@ static inline int up_smp_call_function(void (*func)(void *), void *info)
 static inline void smp_send_reschedule(int cpu) { }
 #define num_booting_cpus()			1
 #define smp_prepare_boot_cpu()			do {} while (0)
-#define smp_call_function_single(cpuid, func, info, retry, wait) \
+#define smp_call_function_single(cpuid, func, info, wait) \
 ({ \
 	WARN_ON(cpuid != 0);	\
 	local_irq_disable();	\
@@ -112,7 +140,9 @@ static inline void smp_send_reschedule(int cpu) { }
 })
 #define smp_call_function_mask(mask, func, info, wait) \
 			(up_smp_call_function(func, info))
-
+static inline void init_call_single_data(void)
+{
+}
 #endif /* !SMP */
 
 /*
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 24f3d2282e1..2158fc0d5a5 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -179,4 +179,17 @@ void arch_update_cpu_topology(void);
 #endif
 #endif /* CONFIG_NUMA */
 
+#ifndef topology_physical_package_id
+#define topology_physical_package_id(cpu)	((void)(cpu), -1)
+#endif
+#ifndef topology_core_id
+#define topology_core_id(cpu)			((void)(cpu), 0)
+#endif
+#ifndef topology_thread_siblings
+#define topology_thread_siblings(cpu)		cpumask_of_cpu(cpu)
+#endif
+#ifndef topology_core_siblings
+#define topology_core_siblings(cpu)		cpumask_of_cpu(cpu)
+#endif
+
 #endif /* _LINUX_TOPOLOGY_H */
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index bd91987c065..12b15c561a1 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -63,6 +63,7 @@ struct writeback_control {
 	unsigned for_writepages:1;	/* This is a writepages() call */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned more_io:1;		/* more io to be dispatched */
+	unsigned range_cont:1;
 };
 
 /*