Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	drivers/pci/dmar.c

30 files changed, 647 insertions, 100 deletions

diff --git a/include/linux/aer.h b/include/linux/aer.h
index f2518141de8..f7df1eefc10 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -10,7 +10,6 @@
 #if defined(CONFIG_PCIEAER)
 /* pci-e port driver needs this function to enable aer */
 extern int pci_enable_pcie_error_reporting(struct pci_dev *dev);
-extern int pci_find_aer_capability(struct pci_dev *dev);
 extern int pci_disable_pcie_error_reporting(struct pci_dev *dev);
 extern int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
 #else
@@ -18,10 +17,6 @@ static inline int pci_enable_pcie_error_reporting(struct pci_dev *dev)
 {
 	return -EINVAL;
 }
-static inline int pci_find_aer_capability(struct pci_dev *dev)
-{
-	return 0;
-}
 static inline int pci_disable_pcie_error_reporting(struct pci_dev *dev)
 {
 	return -EINVAL;
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 55e434feec9..f88d32f8ff7 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -45,7 +45,8 @@ struct clocksource;
  * @read:		returns a cycle value
  * @mask:		bitmask for two's complement
  *			subtraction of non 64 bit counters
- * @mult:		cycle to nanosecond multiplier
+ * @mult:		cycle to nanosecond multiplier (adjusted by NTP)
+ * @mult_orig:		cycle to nanosecond multiplier (unadjusted by NTP)
  * @shift:		cycle to nanosecond divisor (power of two)
  * @flags:		flags describing special properties
  * @vread:		vsyscall based read
@@ -63,6 +64,7 @@ struct clocksource {
 	cycle_t (*read)(void);
 	cycle_t mask;
 	u32 mult;
+	u32 mult_orig;
 	u32 shift;
 	unsigned long flags;
 	cycle_t (*vread)(void);
@@ -77,6 +79,7 @@ struct clocksource {
 	/* timekeeping specific data, ignore */
 	cycle_t cycle_interval;
 	u64	xtime_interval;
+	u32	raw_interval;
 	/*
 	 * Second part is written at each timer interrupt
 	 * Keep it in a different cache line to dirty no
@@ -85,6 +88,7 @@ struct clocksource {
 	cycle_t cycle_last ____cacheline_aligned_in_smp;
 	u64 xtime_nsec;
 	s64 error;
+	struct timespec raw_time;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
@@ -201,17 +205,19 @@ static inline void clocksource_calculate_interval(struct clocksource *c,
 {
 	u64 tmp;
 
-	/* XXX - All of this could use a whole lot of optimization */
+	/* Do the ns -> cycle conversion first, using original mult */
 	tmp = length_nsec;
 	tmp <<= c->shift;
-	tmp += c->mult/2;
-	do_div(tmp, c->mult);
+	tmp += c->mult_orig/2;
+	do_div(tmp, c->mult_orig);
 
 	c->cycle_interval = (cycle_t)tmp;
 	if (c->cycle_interval == 0)
 		c->cycle_interval = 1;
 
+	/* Go back from cycles -> shifted ns, this time use ntp adjused mult */
 	c->xtime_interval = (u64)c->cycle_interval * c->mult;
+	c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift;
 }
 
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 8322141ee48..98115d9d04d 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -44,6 +44,8 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # error Sorry, your compiler is too old/not recognized.
 #endif
 
+#define notrace __attribute__((no_instrument_function))
+
 /* Intel compiler defines __GNUC__. So we will overwrite implementations
  * coming from above header files here
  */
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index c360c558e59..f1984fc3e06 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -45,7 +45,6 @@ extern struct list_head dmar_drhd_units;
 	list_for_each_entry(drhd, &dmar_drhd_units, list)
 
 extern int dmar_table_init(void);
-extern int early_dmar_detect(void);
 extern int dmar_dev_scope_init(void);
 
 /* Intel IOMMU detection */
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 807373d467f..bb66feb164b 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -208,6 +208,9 @@ typedef efi_status_t efi_set_virtual_address_map_t (unsigned long memory_map_siz
 #define EFI_GLOBAL_VARIABLE_GUID \
     EFI_GUID(  0x8be4df61, 0x93ca, 0x11d2, 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c )
 
+#define UV_SYSTEM_TABLE_GUID \
+    EFI_GUID(  0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93 )
+
 typedef struct {
 	efi_guid_t guid;
 	unsigned long table;
@@ -255,6 +258,7 @@ extern struct efi {
 	unsigned long boot_info;	/* boot info table */
 	unsigned long hcdp;		/* HCDP table */
 	unsigned long uga;		/* UGA table */
+	unsigned long uv_systab;	/* UV system table */
 	efi_get_time_t *get_time;
 	efi_set_time_t *set_time;
 	efi_get_wakeup_time_t *get_wakeup_time;
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index bb384068272..a3d46151be1 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1,10 +1,14 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
-#ifdef CONFIG_FTRACE
-
 #include <linux/linkage.h>
 #include <linux/fs.h>
+#include <linux/ktime.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kallsyms.h>
+
+#ifdef CONFIG_FTRACE
 
 extern int ftrace_enabled;
 extern int
@@ -36,6 +40,7 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1);
 # define register_ftrace_function(ops) do { } while (0)
 # define unregister_ftrace_function(ops) do { } while (0)
 # define clear_ftrace_function(ops) do { } while (0)
+static inline void ftrace_kill_atomic(void) { }
 #endif /* CONFIG_FTRACE */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -76,8 +81,10 @@ extern void mcount_call(void);
 
 extern int skip_trace(unsigned long ip);
 
-void ftrace_disable_daemon(void);
-void ftrace_enable_daemon(void);
+extern void ftrace_release(void *start, unsigned long size);
+
+extern void ftrace_disable_daemon(void);
+extern void ftrace_enable_daemon(void);
 
 #else
 # define skip_trace(ip)				({ 0; })
@@ -85,6 +92,7 @@ void ftrace_enable_daemon(void);
 # define ftrace_set_filter(buf, len, reset)	do { } while (0)
 # define ftrace_disable_daemon()		do { } while (0)
 # define ftrace_enable_daemon()			do { } while (0)
+static inline void ftrace_release(void *start, unsigned long size) { }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */
@@ -98,9 +106,11 @@ static inline void tracer_disable(void)
 #endif
 }
 
-/* Ftrace disable/restore without lock. Some synchronization mechanism
+/*
+ * Ftrace disable/restore without lock. Some synchronization mechanism
  * must be used to prevent ftrace_enabled to be changed between
- * disable/restore. */
+ * disable/restore.
+ */
 static inline int __ftrace_enabled_save(void)
 {
 #ifdef CONFIG_FTRACE
@@ -157,9 +167,71 @@ static inline void __ftrace_enabled_restore(int enabled)
 #ifdef CONFIG_TRACING
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
+
+/**
+ * ftrace_printk - printf formatting in the ftrace buffer
+ * @fmt: the printf format for printing
+ *
+ * Note: __ftrace_printk is an internal function for ftrace_printk and
+ *       the @ip is passed in via the ftrace_printk macro.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please refrain from leaving ftrace_printks scattered around in
+ * your code.
+ */
+# define ftrace_printk(fmt...) __ftrace_printk(_THIS_IP_, fmt)
+extern int
+__ftrace_printk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern void ftrace_dump(void);
 #else
 static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
+static inline int
+ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
+
+static inline int
+ftrace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+static inline void ftrace_dump(void) { }
 #endif
 
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+extern void ftrace_init(void);
+extern void ftrace_init_module(unsigned long *start, unsigned long *end);
+#else
+static inline void ftrace_init(void) { }
+static inline void
+ftrace_init_module(unsigned long *start, unsigned long *end) { }
+#endif
+
+
+struct boot_trace {
+	pid_t			caller;
+	char			func[KSYM_NAME_LEN];
+	int			result;
+	unsigned long long	duration;		/* usecs */
+	ktime_t			calltime;
+	ktime_t			rettime;
+};
+
+#ifdef CONFIG_BOOT_TRACER
+extern void trace_boot(struct boot_trace *it, initcall_t fn);
+extern void start_boot_trace(void);
+extern void stop_boot_trace(void);
+#else
+static inline void trace_boot(struct boot_trace *it, initcall_t fn) { }
+static inline void start_boot_trace(void) { }
+static inline void stop_boot_trace(void) { }
+#endif
+
+
+
 #endif /* _LINUX_FTRACE_H */
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index 265635dc990..350fe9767bb 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -17,8 +17,14 @@
  *  - add lock_owner field to fuse_setattr_in, fuse_read_in and fuse_write_in
  *  - add blksize field to fuse_attr
  *  - add file flags field to fuse_read_in and fuse_write_in
+ *
+ * 7.10
+ *  - add nonseekable open flag
  */
 
+#ifndef _LINUX_FUSE_H
+#define _LINUX_FUSE_H
+
 #include <asm/types.h>
 #include <linux/major.h>
 
@@ -26,7 +32,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 9
+#define FUSE_KERNEL_MINOR_VERSION 10
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -98,9 +104,11 @@ struct fuse_file_lock {
  *
  * FOPEN_DIRECT_IO: bypass page cache for this open file
  * FOPEN_KEEP_CACHE: don't invalidate the data cache on open
+ * FOPEN_NONSEEKABLE: the file is not seekable
  */
 #define FOPEN_DIRECT_IO		(1 << 0)
 #define FOPEN_KEEP_CACHE	(1 << 1)
+#define FOPEN_NONSEEKABLE	(1 << 2)
 
 /**
  * INIT request/reply flags
@@ -409,3 +417,5 @@ struct fuse_dirent {
 #define FUSE_DIRENT_ALIGN(x) (((x) + sizeof(__u64) - 1) & ~(sizeof(__u64) - 1))
 #define FUSE_DIRENT_SIZE(d) \
 	FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen)
+
+#endif /* _LINUX_FUSE_H */
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 2f245fe63bd..9a4e35cd5f7 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -125,12 +125,12 @@ struct hrtimer {
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
-	enum hrtimer_cb_mode		cb_mode;
 	struct list_head		cb_entry;
+	enum hrtimer_cb_mode		cb_mode;
 #ifdef CONFIG_TIMER_STATS
+	int				start_pid;
 	void				*start_site;
 	char				start_comm[16];
-	int				start_pid;
 #endif
 };
 
@@ -155,10 +155,8 @@ struct hrtimer_sleeper {
  * @first:		pointer to the timer node which expires first
  * @resolution:		the resolution of the clock, in nanoseconds
  * @get_time:		function to retrieve the current time of the clock
- * @get_softirq_time:	function to retrieve the current time from the softirq
  * @softirq_time:	the time when running the hrtimer queue in the softirq
  * @offset:		offset of this clock to the monotonic base
- * @reprogram:		function to reprogram the timer event
  */
 struct hrtimer_clock_base {
 	struct hrtimer_cpu_base	*cpu_base;
@@ -167,13 +165,9 @@ struct hrtimer_clock_base {
 	struct rb_node		*first;
 	ktime_t			resolution;
 	ktime_t			(*get_time)(void);
-	ktime_t			(*get_softirq_time)(void);
 	ktime_t			softirq_time;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	ktime_t			offset;
-	int			(*reprogram)(struct hrtimer *t,
-					     struct hrtimer_clock_base *b,
-					     ktime_t n);
 #endif
 };
 
diff --git a/include/linux/ide.h b/include/linux/ide.h
index c47e371554c..89e53cfbc78 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -461,12 +461,26 @@ struct ide_acpi_drive_link;
 struct ide_acpi_hwif_link;
 #endif
 
+struct ide_drive_s;
+
+struct ide_disk_ops {
+	int		(*check)(struct ide_drive_s *, const char *);
+	int		(*get_capacity)(struct ide_drive_s *);
+	void		(*setup)(struct ide_drive_s *);
+	void		(*flush)(struct ide_drive_s *);
+	int		(*init_media)(struct ide_drive_s *, struct gendisk *);
+	int		(*set_doorlock)(struct ide_drive_s *, struct gendisk *,
+					int);
+	ide_startstop_t	(*do_request)(struct ide_drive_s *, struct request *,
+				      sector_t);
+	int		(*end_request)(struct ide_drive_s *, int, int);
+	int		(*ioctl)(struct ide_drive_s *, struct inode *,
+				 struct file *, unsigned int, unsigned long);
+};
+
 /* ATAPI device flags */
 enum {
 	IDE_AFLAG_DRQ_INTERRUPT		= (1 << 0),
-	IDE_AFLAG_MEDIA_CHANGED		= (1 << 1),
-	/* Drive cannot lock the door. */
-	IDE_AFLAG_NO_DOORLOCK		= (1 << 2),
 
 	/* ide-cd */
 	/* Drive cannot eject the disc. */
@@ -498,14 +512,10 @@ enum {
 	IDE_AFLAG_LE_SPEED_FIELDS	= (1 << 17),
 
 	/* ide-floppy */
-	/* Format in progress */
-	IDE_AFLAG_FORMAT_IN_PROGRESS	= (1 << 18),
 	/* Avoid commands not supported in Clik drive */
 	IDE_AFLAG_CLIK_DRIVE		= (1 << 19),
 	/* Requires BH algorithm for packets */
 	IDE_AFLAG_ZIP_DRIVE		= (1 << 20),
-	/* Write protect */
-	IDE_AFLAG_WP			= (1 << 21),
 	/* Supports format progress report */
 	IDE_AFLAG_SRFP			= (1 << 22),
 
@@ -578,7 +588,11 @@ enum {
 	/* don't unload heads */
 	IDE_DFLAG_NO_UNLOAD		= (1 << 27),
 	/* heads unloaded, please don't reset port */
-	IDE_DFLAG_PARKED		= (1 << 28)
+	IDE_DFLAG_PARKED		= (1 << 28),
+	IDE_DFLAG_MEDIA_CHANGED		= (1 << 29),
+	/* write protect */
+	IDE_DFLAG_WP			= (1 << 30),
+	IDE_DFLAG_FORMAT_IN_PROGRESS	= (1 << 31),
 };
 
 struct ide_drive_s {
@@ -597,6 +611,8 @@ struct ide_drive_s {
 #endif
 	struct hwif_s		*hwif;	/* actually (ide_hwif_t *) */
 
+	const struct ide_disk_ops *disk_ops;
+
 	unsigned long dev_flags;
 
 	unsigned long sleep;		/* sleep until this time */
@@ -1123,8 +1139,8 @@ struct ide_driver_s {
 	void		(*resume)(ide_drive_t *);
 	void		(*shutdown)(ide_drive_t *);
 #ifdef CONFIG_IDE_PROC_FS
-	ide_proc_entry_t		*proc;
-	const struct ide_proc_devset	*settings;
+	ide_proc_entry_t *		(*proc_entries)(ide_drive_t *);
+	const struct ide_proc_devset *	(*proc_devsets)(ide_drive_t *);
 #endif
 };
 
diff --git a/include/linux/init.h b/include/linux/init.h
index ad63824460e..0c1264668be 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -40,7 +40,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold
+#define __init		__section(.init.text) __cold notrace
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 35a61dc60d5..f58a0cf8929 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -8,6 +8,7 @@
 #include <linux/preempt.h>
 #include <linux/cpumask.h>
 #include <linux/irqreturn.h>
+#include <linux/irqnr.h>
 #include <linux/hardirq.h>
 #include <linux/sched.h>
 #include <linux/irqflags.h>
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 8d9411bc60f..d058c57be02 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -18,6 +18,7 @@
 #include <linux/spinlock.h>
 #include <linux/cpumask.h>
 #include <linux/irqreturn.h>
+#include <linux/irqnr.h>
 #include <linux/errno.h>
 
 #include <asm/irq.h>
@@ -152,6 +153,7 @@ struct irq_chip {
  * @name:		flow handler name for /proc/interrupts output
  */
 struct irq_desc {
+	unsigned int		irq;
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
 	struct msi_desc		*msi_desc;
@@ -170,7 +172,7 @@ struct irq_desc {
 	cpumask_t		affinity;
 	unsigned int		cpu;
 #endif
-#if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE)
+#ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_t		pending_mask;
 #endif
 #ifdef CONFIG_PROC_FS
@@ -179,8 +181,14 @@ struct irq_desc {
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
 
+
 extern struct irq_desc irq_desc[NR_IRQS];
 
+static inline struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	return (irq < nr_irqs) ? irq_desc + irq : NULL;
+}
+
 /*
  * Migration helpers for obsolete names, they will go away:
  */
@@ -198,19 +206,15 @@ extern int setup_irq(unsigned int irq, struct irqaction *new);
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
-#ifndef handle_dynamic_tick
-# define handle_dynamic_tick(a)		do { } while (0)
-#endif
-
 #ifdef CONFIG_SMP
 
-#if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE)
+#ifdef CONFIG_GENERIC_PENDING_IRQ
 
 void set_pending_irq(unsigned int irq, cpumask_t mask);
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
 
-#else /* CONFIG_GENERIC_PENDING_IRQ || CONFIG_IRQBALANCE */
+#else /* CONFIG_GENERIC_PENDING_IRQ */
 
 static inline void move_irq(int irq)
 {
@@ -237,19 +241,14 @@ static inline void set_pending_irq(unsigned int irq, cpumask_t mask)
 
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_IRQBALANCE
-extern void set_balance_irq_affinity(unsigned int irq, cpumask_t mask);
-#else
-static inline void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
-{
-}
-#endif
-
 extern int no_irq_affinity;
 
 static inline int irq_balancing_disabled(unsigned int irq)
 {
-	return irq_desc[irq].status & IRQ_NO_BALANCING_MASK;
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	return desc->status & IRQ_NO_BALANCING_MASK;
 }
 
 /* Handle irq action chains: */
@@ -279,10 +278,8 @@ extern unsigned int __do_IRQ(unsigned int irq);
  * irqchip-style controller then we call the ->handle_irq() handler,
  * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
  */
-static inline void generic_handle_irq(unsigned int irq)
+static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_desc + irq;
-
 #ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
 	desc->handle_irq(irq, desc);
 #else
@@ -293,6 +290,11 @@ static inline void generic_handle_irq(unsigned int irq)
 #endif
 }
 
+static inline void generic_handle_irq(unsigned int irq)
+{
+	generic_handle_irq_desc(irq, irq_to_desc(irq));
+}
+
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(unsigned int irq, struct irq_desc *desc,
 			   int action_ret);
@@ -325,7 +327,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 static inline void __set_irq_handler_unlocked(int irq,
 					      irq_flow_handler_t handler)
 {
-	irq_desc[irq].handle_irq = handler;
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->handle_irq = handler;
 }
 
 /*
@@ -353,13 +358,14 @@ extern void set_irq_noprobe(unsigned int irq);
 extern void set_irq_probe(unsigned int irq);
 
 /* Handle dynamic irq creation and destruction */
+extern unsigned int create_irq_nr(unsigned int irq_want);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);
 
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_has_action(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	return desc->action != NULL;
 }
 
@@ -374,10 +380,10 @@ extern int set_irq_chip_data(unsigned int irq, void *data);
 extern int set_irq_type(unsigned int irq, unsigned int type);
 extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
-#define get_irq_chip(irq)	(irq_desc[irq].chip)
-#define get_irq_chip_data(irq)	(irq_desc[irq].chip_data)
-#define get_irq_data(irq)	(irq_desc[irq].handler_data)
-#define get_irq_msi(irq)	(irq_desc[irq].msi_desc)
+#define get_irq_chip(irq)	(irq_to_desc(irq)->chip)
+#define get_irq_chip_data(irq)	(irq_to_desc(irq)->chip_data)
+#define get_irq_data(irq)	(irq_to_desc(irq)->handler_data)
+#define get_irq_msi(irq)	(irq_to_desc(irq)->msi_desc)
 
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
new file mode 100644
index 00000000000..3171ddc3b39
--- /dev/null
+++ b/include/linux/irqnr.h
@@ -0,0 +1,24 @@
+#ifndef _LINUX_IRQNR_H
+#define _LINUX_IRQNR_H
+
+#ifndef CONFIG_GENERIC_HARDIRQS
+#include <asm/irq.h>
+# define nr_irqs		NR_IRQS
+
+# define for_each_irq_desc(irq, desc)		\
+	for (irq = 0; irq < nr_irqs; irq++)
+#else
+extern int nr_irqs;
+
+# define for_each_irq_desc(irq, desc)		\
+	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
+
+# define for_each_irq_desc_reverse(irq, desc)			\
+	for (irq = nr_irqs -1, desc = irq_desc + (nr_irqs -1 );	\
+	     irq > 0; irq--, desc--)
+#endif
+
+#define for_each_irq_nr(irq)			\
+	for (irq = 0; irq < nr_irqs; irq++)
+
+#endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5a566b705ca..94d17ff64c5 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -496,4 +496,9 @@ struct sysinfo {
 #define NUMA_BUILD 0
 #endif
 
+/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
+#endif
+
 #endif
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index cf9f40a91c9..4a145caeee0 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -39,19 +39,34 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 
 extern unsigned long long nr_context_switches(void);
 
+struct irq_desc;
+
+static inline void kstat_incr_irqs_this_cpu(unsigned int irq,
+					    struct irq_desc *desc)
+{
+	kstat_this_cpu.irqs[irq]++;
+}
+
+static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+       return kstat_cpu(cpu).irqs[irq];
+}
+
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
-static inline int kstat_irqs(int irq)
+static inline unsigned int kstat_irqs(unsigned int irq)
 {
-	int cpu, sum = 0;
+	unsigned int sum = 0;
+	int cpu;
 
 	for_each_possible_cpu(cpu)
-		sum += kstat_cpu(cpu).irqs[irq];
+		sum += kstat_irqs_cpu(irq, cpu);
 
 	return sum;
 }
 
+extern unsigned long long task_delta_exec(struct task_struct *);
 extern void account_user_time(struct task_struct *, cputime_t);
 extern void account_user_time_scaled(struct task_struct *, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 0be7795655f..497b1d1f7a0 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -29,6 +29,7 @@
  *		<jkenisto@us.ibm.com>  and Prasanna S Panchamukhi
  *		<prasanna@in.ibm.com> added function-return probes.
  */
+#include <linux/linkage.h>
 #include <linux/list.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
@@ -47,7 +48,7 @@
 #define KPROBE_HIT_SSDONE	0x00000008
 
 /* Attach to insert probes on any functions which should be ignored*/
-#define __kprobes	__attribute__((__section__(".kprobes.text")))
+#define __kprobes	__attribute__((__section__(".kprobes.text"))) notrace
 
 struct kprobe;
 struct pt_regs;
@@ -256,7 +257,7 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
 #else /* CONFIG_KPROBES */
 
-#define __kprobes	/**/
+#define __kprobes	notrace
 struct jprobe;
 struct kretprobe;
 
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 56ba3739465..9fd1f859021 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -4,8 +4,6 @@
 #include <linux/compiler.h>
 #include <asm/linkage.h>
 
-#define notrace __attribute__((no_instrument_function))
-
 #ifdef __cplusplus
 #define CPP_ASMLINKAGE extern "C"
 #else
diff --git a/include/linux/marker.h b/include/linux/marker.h
index 1290653f924..889196c7fbb 100644
--- a/include/linux/marker.h
+++ b/include/linux/marker.h
@@ -160,4 +160,11 @@ extern int marker_probe_unregister_private_data(marker_probe_func *probe,
 extern void *marker_get_private_data(const char *name, marker_probe_func *probe,
 	int num);
 
+/*
+ * marker_synchronize_unregister must be called between the last marker probe
+ * unregistration and the end of module exit to make sure there is no caller
+ * executing a probe when it is freed.
+ */
+#define marker_synchronize_unregister() synchronize_sched()
+
 #endif
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 61d19e1b7a0..139d7c88d9c 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -34,11 +34,15 @@ extern void unregister_kmmio_probe(struct kmmio_probe *p);
 /* Called from page fault handler. */
 extern int kmmio_handler(struct pt_regs *regs, unsigned long addr);
 
-/* Called from ioremap.c */
 #ifdef CONFIG_MMIOTRACE
+/* Called from ioremap.c */
 extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size,
 							void __iomem *addr);
 extern void mmiotrace_iounmap(volatile void __iomem *addr);
+
+/* For anyone to insert markers. Remember trailing newline. */
+extern int mmiotrace_printk(const char *fmt, ...)
+				__attribute__ ((format (printf, 1, 2)));
 #else
 static inline void mmiotrace_ioremap(resource_size_t offset,
 					unsigned long size, void __iomem *addr)
@@ -48,15 +52,22 @@ static inline void mmiotrace_ioremap(resource_size_t offset,
 static inline void mmiotrace_iounmap(volatile void __iomem *addr)
 {
 }
-#endif /* CONFIG_MMIOTRACE_HOOKS */
+
+static inline int mmiotrace_printk(const char *fmt, ...)
+				__attribute__ ((format (printf, 1, 0)));
+
+static inline int mmiotrace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+#endif /* CONFIG_MMIOTRACE */
 
 enum mm_io_opcode {
 	MMIO_READ = 0x1,     /* struct mmiotrace_rw */
 	MMIO_WRITE = 0x2,    /* struct mmiotrace_rw */
 	MMIO_PROBE = 0x3,    /* struct mmiotrace_map */
 	MMIO_UNPROBE = 0x4,  /* struct mmiotrace_map */
-	MMIO_MARKER = 0x5,   /* raw char data */
-	MMIO_UNKNOWN_OP = 0x6, /* struct mmiotrace_rw */
+	MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */
 };
 
 struct mmiotrace_rw {
@@ -81,5 +92,6 @@ extern void enable_mmiotrace(void);
 extern void disable_mmiotrace(void);
 extern void mmio_trace_rw(struct mmiotrace_rw *rw);
 extern void mmio_trace_mapping(struct mmiotrace_map *map);
+extern int mmio_trace_printk(const char *fmt, va_list args);
 
 #endif /* MMIOTRACE_H */
diff --git a/include/linux/module.h b/include/linux/module.h
index a41555cbe00..5d2970cdce9 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -16,6 +16,7 @@
 #include <linux/kobject.h>
 #include <linux/moduleparam.h>
 #include <linux/marker.h>
+#include <linux/tracepoint.h>
 #include <asm/local.h>
 
 #include <asm/module.h>
@@ -331,6 +332,10 @@ struct module
 	struct marker *markers;
 	unsigned int num_markers;
 #endif
+#ifdef CONFIG_TRACEPOINTS
+	struct tracepoint *tracepoints;
+	unsigned int num_tracepoints;
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
@@ -453,6 +458,9 @@ extern void print_modules(void);
 
 extern void module_update_markers(void);
 
+extern void module_update_tracepoints(void);
+extern int module_get_iter_tracepoints(struct tracepoint_iter *iter);
+
 #else /* !CONFIG_MODULES... */
 #define EXPORT_SYMBOL(sym)
 #define EXPORT_SYMBOL_GPL(sym)
@@ -557,6 +565,15 @@ static inline void module_update_markers(void)
 {
 }
 
+static inline void module_update_tracepoints(void)
+{
+}
+
+static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter)
+{
+	return 0;
+}
+
 #endif /* CONFIG_MODULES */
 
 struct device_driver;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index acf8f24037c..085187be29c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -214,6 +214,7 @@ struct pci_dev {
 	unsigned int	broken_parity_status:1;	/* Device generates false positive parity */
 	unsigned int 	msi_enabled:1;
 	unsigned int	msix_enabled:1;
+	unsigned int	ari_enabled:1;	/* ARI forwarding */
 	unsigned int	is_managed:1;
 	unsigned int	is_pcie:1;
 	pci_dev_flags_t dev_flags;
@@ -347,7 +348,6 @@ struct pci_bus_region {
 struct pci_dynids {
 	spinlock_t lock;            /* protects list, index */
 	struct list_head list;      /* for IDs added at runtime */
-	unsigned int use_driver_data:1; /* pci_device_id->driver_data is used */
 };
 
 /* ---------------------------------------------------------------- */
@@ -456,8 +456,8 @@ struct pci_driver {
 
 /**
  * PCI_VDEVICE - macro used to describe a specific pci device in short form
- * @vend: the vendor name
- * @dev: the 16 bit PCI Device ID
+ * @vendor: the vendor name
+ * @device: the 16 bit PCI Device ID
  *
  * This macro is used to create a struct pci_device_id that matches a
  * specific PCI device.  The subvendor, and subdevice fields will be set
@@ -645,6 +645,7 @@ pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state);
 bool pci_pme_capable(struct pci_dev *dev, pci_power_t state);
 void pci_pme_active(struct pci_dev *dev, bool enable);
 int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable);
+int pci_wake_from_d3(struct pci_dev *dev, bool enable);
 pci_power_t pci_target_state(struct pci_dev *dev);
 int pci_prepare_to_sleep(struct pci_dev *dev);
 int pci_back_from_sleep(struct pci_dev *dev);
@@ -725,7 +726,7 @@ enum pci_dma_burst_strategy {
 };
 
 struct msix_entry {
-	u16 	vector;	/* kernel uses to write allocated vector */
+	u32	vector;	/* kernel uses to write allocated vector */
 	u16	entry;	/* driver uses to specify entry, OS writes */
 };
 
@@ -1118,5 +1119,20 @@ static inline void pci_mmcfg_early_init(void) { }
 static inline void pci_mmcfg_late_init(void) { }
 #endif
 
+#ifdef CONFIG_HAS_IOMEM
+static inline void * pci_ioremap_bar(struct pci_dev *pdev, int bar)
+{
+	/*
+	 * Make sure the BAR is actually a memory resource, not an IO resource
+	 */
+	if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	return ioremap_nocache(pci_resource_start(pdev, bar),
+				     pci_resource_len(pdev, bar));
+}
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* LINUX_PCI_H */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 8edddc240e4..e5d344bfcb7 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2454,9 +2454,9 @@
 #define PCI_DEVICE_ID_INTEL_ICH10_3	0x3a1a
 #define PCI_DEVICE_ID_INTEL_ICH10_4	0x3a30
 #define PCI_DEVICE_ID_INTEL_ICH10_5	0x3a60
-#define PCI_DEVICE_ID_INTEL_PCH_0	0x3b10
-#define PCI_DEVICE_ID_INTEL_PCH_1	0x3b11
-#define PCI_DEVICE_ID_INTEL_PCH_2	0x3b30
+#define PCI_DEVICE_ID_INTEL_PCH_LPC_MIN	0x3b00
+#define PCI_DEVICE_ID_INTEL_PCH_LPC_MAX	0x3b1f
+#define PCI_DEVICE_ID_INTEL_PCH_SMBUS	0x3b30
 #define PCI_DEVICE_ID_INTEL_IOAT_SNB	0x402f
 #define PCI_DEVICE_ID_INTEL_5100_16	0x65f0
 #define PCI_DEVICE_ID_INTEL_5100_21	0x65f5
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index 450684f7eaa..eb6686b88f9 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -419,6 +419,10 @@
 #define  PCI_EXP_RTCTL_CRSSVE	0x10	/* CRS Software Visibility Enable */
 #define PCI_EXP_RTCAP		30	/* Root Capabilities */
 #define PCI_EXP_RTSTA		32	/* Root Status */
+#define PCI_EXP_DEVCAP2		36	/* Device Capabilities 2 */
+#define  PCI_EXP_DEVCAP2_ARI	0x20	/* Alternative Routing-ID */
+#define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
+#define  PCI_EXP_DEVCTL2_ARI	0x20	/* Alternative Routing-ID */
 
 /* Extended Capabilities (PCI-X 2.0 and Express) */
 #define PCI_EXT_CAP_ID(header)		(header & 0x0000ffff)
@@ -429,6 +433,7 @@
 #define PCI_EXT_CAP_ID_VC	2
 #define PCI_EXT_CAP_ID_DSN	3
 #define PCI_EXT_CAP_ID_PWR	4
+#define PCI_EXT_CAP_ID_ARI	14
 
 /* Advanced Error Reporting */
 #define PCI_ERR_UNCOR_STATUS	4	/* Uncorrectable Error Status */
@@ -536,5 +541,14 @@
 #define HT_CAPTYPE_GEN3		0xD0	/* Generation 3 hypertransport configuration */
 #define HT_CAPTYPE_PM		0xE0	/* Hypertransport powermanagement configuration */
 
+/* Alternative Routing-ID Interpretation */
+#define PCI_ARI_CAP		0x04	/* ARI Capability Register */
+#define  PCI_ARI_CAP_MFVC	0x0001	/* MFVC Function Groups Capability */
+#define  PCI_ARI_CAP_ACS	0x0002	/* ACS Function Groups Capability */
+#define  PCI_ARI_CAP_NFN(x)	(((x) >> 8) & 0xff) /* Next Function Number */
+#define PCI_ARI_CTRL		0x06	/* ARI Control Register */
+#define  PCI_ARI_CTRL_MFVC	0x0001	/* MFVC Function Groups Enable */
+#define  PCI_ARI_CTRL_ACS	0x0002	/* ACS Function Groups Enable */
+#define  PCI_ARI_CTRL_FG(x)	(((x) >> 4) & 7) /* Function Group */
 
 #endif /* LINUX_PCI_REGS_H */
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index a7dd38f30ad..a7c72135554 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -45,8 +45,6 @@ struct k_itimer {
 	int it_requeue_pending;		/* waiting to requeue this timer */
 #define REQUEUE_PENDING 1
 	int it_sigev_notify;		/* notify word of sigevent struct */
-	int it_sigev_signo;		/* signo word of sigevent struct */
-	sigval_t it_sigev_value;	/* value word of sigevent struct */
 	struct task_struct *it_process;	/* process to send signal to */
 	struct sigqueue *sigq;		/* signal queue entry. */
 	union {
@@ -115,4 +113,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
 
 long clock_nanosleep_restart(struct restart_block *restart_block);
 
+void update_rlimit_cpu(unsigned long rlim_new);
+
 #endif
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
new file mode 100644
index 00000000000..536b0ca46a0
--- /dev/null
+++ b/include/linux/ring_buffer.h
@@ -0,0 +1,127 @@
+#ifndef _LINUX_RING_BUFFER_H
+#define _LINUX_RING_BUFFER_H
+
+#include <linux/mm.h>
+#include <linux/seq_file.h>
+
+struct ring_buffer;
+struct ring_buffer_iter;
+
+/*
+ * Don't reference this struct directly, use functions below.
+ */
+struct ring_buffer_event {
+	u32		type:2, len:3, time_delta:27;
+	u32		array[];
+};
+
+/**
+ * enum ring_buffer_type - internal ring buffer types
+ *
+ * @RINGBUF_TYPE_PADDING:	Left over page padding
+ *				 array is ignored
+ *				 size is variable depending on how much
+ *				  padding is needed
+ *
+ * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
+ *				 array[0] = time delta (28 .. 59)
+ *				 size = 8 bytes
+ *
+ * @RINGBUF_TYPE_TIME_STAMP:	Sync time stamp with external clock
+ *				 array[0] = tv_nsec
+ *				 array[1] = tv_sec
+ *				 size = 16 bytes
+ *
+ * @RINGBUF_TYPE_DATA:		Data record
+ *				 If len is zero:
+ *				  array[0] holds the actual length
+ *				  array[1..(length+3)/4-1] holds data
+ *				 else
+ *				  length = len << 2
+ *				  array[0..(length+3)/4] holds data
+ */
+enum ring_buffer_type {
+	RINGBUF_TYPE_PADDING,
+	RINGBUF_TYPE_TIME_EXTEND,
+	/* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
+	RINGBUF_TYPE_TIME_STAMP,
+	RINGBUF_TYPE_DATA,
+};
+
+unsigned ring_buffer_event_length(struct ring_buffer_event *event);
+void *ring_buffer_event_data(struct ring_buffer_event *event);
+
+/**
+ * ring_buffer_event_time_delta - return the delta timestamp of the event
+ * @event: the event to get the delta timestamp of
+ *
+ * The delta timestamp is the 27 bit timestamp since the last event.
+ */
+static inline unsigned
+ring_buffer_event_time_delta(struct ring_buffer_event *event)
+{
+	return event->time_delta;
+}
+
+/*
+ * size is in bytes for each per CPU buffer.
+ */
+struct ring_buffer *
+ring_buffer_alloc(unsigned long size, unsigned flags);
+void ring_buffer_free(struct ring_buffer *buffer);
+
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
+
+struct ring_buffer_event *
+ring_buffer_lock_reserve(struct ring_buffer *buffer,
+			 unsigned long length,
+			 unsigned long *flags);
+int ring_buffer_unlock_commit(struct ring_buffer *buffer,
+			      struct ring_buffer_event *event,
+			      unsigned long flags);
+int ring_buffer_write(struct ring_buffer *buffer,
+		      unsigned long length, void *data);
+
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts);
+struct ring_buffer_event *
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts);
+
+struct ring_buffer_iter *
+ring_buffer_read_start(struct ring_buffer *buffer, int cpu);
+void ring_buffer_read_finish(struct ring_buffer_iter *iter);
+
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts);
+struct ring_buffer_event *
+ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts);
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter);
+int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
+
+unsigned long ring_buffer_size(struct ring_buffer *buffer);
+
+void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
+void ring_buffer_reset(struct ring_buffer *buffer);
+
+int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+			 struct ring_buffer *buffer_b, int cpu);
+
+int ring_buffer_empty(struct ring_buffer *buffer);
+int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
+
+void ring_buffer_record_disable(struct ring_buffer *buffer);
+void ring_buffer_record_enable(struct ring_buffer *buffer);
+void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
+void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
+
+unsigned long ring_buffer_entries(struct ring_buffer *buffer);
+unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
+
+u64 ring_buffer_time_stamp(int cpu);
+void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
+
+enum ring_buffer_flags {
+	RB_FL_OVERWRITE		= 1 << 0,
+};
+
+#endif /* _LINUX_RING_BUFFER_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f52dbd3587a..5c38db536e0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -434,6 +434,39 @@ struct pacct_struct {
 	unsigned long		ac_minflt, ac_majflt;
 };
 
+/**
+ * struct task_cputime - collected CPU time counts
+ * @utime:		time spent in user mode, in &cputime_t units
+ * @stime:		time spent in kernel mode, in &cputime_t units
+ * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
+ *
+ * This structure groups together three kinds of CPU time that are
+ * tracked for threads and thread groups.  Most things considering
+ * CPU time want to group these counts together and treat all three
+ * of them in parallel.
+ */
+struct task_cputime {
+	cputime_t utime;
+	cputime_t stime;
+	unsigned long long sum_exec_runtime;
+};
+/* Alternate field names when used to cache expirations. */
+#define prof_exp	stime
+#define virt_exp	utime
+#define sched_exp	sum_exec_runtime
+
+/**
+ * struct thread_group_cputime - thread group interval timer counts
+ * @totals:		thread group interval timers; substructure for
+ *			uniprocessor kernel, per-cpu for SMP kernel.
+ *
+ * This structure contains the version of task_cputime, above, that is
+ * used for thread group CPU clock calculations.
+ */
+struct thread_group_cputime {
+	struct task_cputime *totals;
+};
+
 /*
  * NOTE! "signal_struct" does not have it's own
  * locking, because a shared signal_struct always
@@ -479,6 +512,17 @@ struct signal_struct {
 	cputime_t it_prof_expires, it_virt_expires;
 	cputime_t it_prof_incr, it_virt_incr;
 
+	/*
+	 * Thread group totals for process CPU clocks.
+	 * See thread_group_cputime(), et al, for details.
+	 */
+	struct thread_group_cputime cputime;
+
+	/* Earliest-expiration cache. */
+	struct task_cputime cputime_expires;
+
+	struct list_head cpu_timers[3];
+
 	/* job control IDs */
 
 	/*
@@ -509,7 +553,7 @@ struct signal_struct {
 	 * Live threads maintain their own counters and add to these
 	 * in __exit_signal, except for the group leader.
 	 */
-	cputime_t utime, stime, cutime, cstime;
+	cputime_t cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
@@ -518,14 +562,6 @@ struct signal_struct {
 	struct task_io_accounting ioac;
 
 	/*
-	 * Cumulative ns of scheduled CPU time for dead threads in the
-	 * group, not including a zombie group leader.  (This only differs
-	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
-	 * other than jiffies.)
-	 */
-	unsigned long long sum_sched_runtime;
-
-	/*
 	 * We don't bother to synchronize most readers of this at all,
 	 * because there is no reader checking a limit that actually needs
 	 * to get both rlim_cur and rlim_max atomically, and either one
@@ -536,8 +572,6 @@ struct signal_struct {
 	 */
 	struct rlimit rlim[RLIM_NLIMITS];
 
-	struct list_head cpu_timers[3];
-
 	/* keep the process-shared keyrings here so that they do the right
 	 * thing in threads created with CLONE_THREAD */
 #ifdef CONFIG_KEYS
@@ -1146,8 +1180,7 @@ struct task_struct {
 /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
 	unsigned long min_flt, maj_flt;
 
-  	cputime_t it_prof_expires, it_virt_expires;
-	unsigned long long it_sched_expires;
+	struct task_cputime cputime_expires;
 	struct list_head cpu_timers[3];
 
 /* process credentials */
@@ -1597,6 +1630,7 @@ extern unsigned long long cpu_clock(int cpu);
 
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
+extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
 #ifdef CONFIG_SMP
@@ -2094,6 +2128,30 @@ static inline int spin_needbreak(spinlock_t *lock)
 }
 
 /*
+ * Thread group CPU time accounting.
+ */
+
+extern int thread_group_cputime_alloc(struct task_struct *);
+extern void thread_group_cputime(struct task_struct *, struct task_cputime *);
+
+static inline void thread_group_cputime_init(struct signal_struct *sig)
+{
+	sig->cputime.totals = NULL;
+}
+
+static inline int thread_group_cputime_clone_thread(struct task_struct *curr)
+{
+	if (curr->signal->cputime.totals)
+		return 0;
+	return thread_group_cputime_alloc(curr);
+}
+
+static inline void thread_group_cputime_free(struct signal_struct *sig)
+{
+	free_percpu(sig->cputime.totals);
+}
+
+/*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.
  * This is required every time the blocked sigset_t changes.
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 98921a3e1aa..b6ec8189ac0 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -96,9 +96,11 @@ extern cpumask_t *tick_get_broadcast_oneshot_mask(void);
 extern void tick_clock_notify(void);
 extern int tick_check_oneshot_change(int allow_nohz);
 extern struct tick_sched *tick_get_tick_sched(int cpu);
+extern void tick_check_idle(int cpu);
 # else
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
+static inline void tick_check_idle(int cpu) { }
 # endif
 
 #else /* CONFIG_GENERIC_CLOCKEVENTS */
@@ -106,26 +108,23 @@ static inline void tick_init(void) { }
 static inline void tick_cancel_sched_timer(int cpu) { }
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
+static inline void tick_check_idle(int cpu) { }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
 # ifdef CONFIG_NO_HZ
 extern void tick_nohz_stop_sched_tick(int inidle);
 extern void tick_nohz_restart_sched_tick(void);
-extern void tick_nohz_update_jiffies(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
-extern void tick_nohz_stop_idle(int cpu);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 # else
 static inline void tick_nohz_stop_sched_tick(int inidle) { }
 static inline void tick_nohz_restart_sched_tick(void) { }
-static inline void tick_nohz_update_jiffies(void) { }
 static inline ktime_t tick_nohz_get_sleep_length(void)
 {
 	ktime_t len = { .tv64 = NSEC_PER_SEC/HZ };
 
 	return len;
 }
-static inline void tick_nohz_stop_idle(int cpu) { }
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 # endif /* !NO_HZ */
 
diff --git a/include/linux/time.h b/include/linux/time.h
index 51e883df0fa..4f1c9db5770 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -119,6 +119,7 @@ extern int do_setitimer(int which, struct itimerval *value,
 extern unsigned int alarm_setitimer(unsigned int seconds);
 extern int do_getitimer(int which, struct itimerval *value);
 extern void getnstimeofday(struct timespec *tv);
+extern void getrawmonotonic(struct timespec *ts);
 extern void getboottime(struct timespec *ts);
 extern void monotonic_to_bootbased(struct timespec *ts);
 
@@ -127,6 +128,9 @@ extern int timekeeping_valid_for_hres(void);
 extern void update_wall_time(void);
 extern void update_xtime_cache(u64 nsec);
 
+struct tms;
+extern void do_sys_times(struct tms *);
+
 /**
  * timespec_to_ns - Convert timespec to nanoseconds
  * @ts:		pointer to the timespec variable to be converted
@@ -216,6 +220,7 @@ struct itimerval {
 #define CLOCK_MONOTONIC			1
 #define CLOCK_PROCESS_CPUTIME_ID	2
 #define CLOCK_THREAD_CPUTIME_ID		3
+#define CLOCK_MONOTONIC_RAW		4
 
 /*
  * The IDs of various hardware clocks:
diff --git a/include/linux/timex.h b/include/linux/timex.h
index fc6035d29d5..9007313b5b7 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -82,7 +82,7 @@
  */
 #define SHIFT_USEC 16		/* frequency offset scale (shift) */
 #define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC))
-#define PPM_SCALE_INV_SHIFT 20
+#define PPM_SCALE_INV_SHIFT 19
 #define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \
 		       PPM_SCALE + 1)
 
@@ -141,8 +141,15 @@ struct timex {
 #define ADJ_MICRO		0x1000	/* select microsecond resolution */
 #define ADJ_NANO		0x2000	/* select nanosecond resolution */
 #define ADJ_TICK		0x4000	/* tick value */
+
+#ifdef __KERNEL__
+#define ADJ_ADJTIME		0x8000	/* switch between adjtime/adjtimex modes */
+#define ADJ_OFFSET_SINGLESHOT	0x0001	/* old-fashioned adjtime */
+#define ADJ_OFFSET_READONLY	0x2000	/* read-only adjtime */
+#else
 #define ADJ_OFFSET_SINGLESHOT	0x8001	/* old-fashioned adjtime */
-#define ADJ_OFFSET_SS_READ	0xa001  /* read-only adjtime */
+#define ADJ_OFFSET_SS_READ	0xa001	/* read-only adjtime */
+#endif
 
 /* xntp 3.4 compatibility names */
 #define MOD_OFFSET	ADJ_OFFSET
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
new file mode 100644
index 00000000000..c5bb39c7a77
--- /dev/null
+++ b/include/linux/tracepoint.h
@@ -0,0 +1,137 @@
+#ifndef _LINUX_TRACEPOINT_H
+#define _LINUX_TRACEPOINT_H
+
+/*
+ * Kernel Tracepoint API.
+ *
+ * See Documentation/tracepoint.txt.
+ *
+ * (C) Copyright 2008 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * Heavily inspired from the Linux Kernel Markers.
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+
+struct module;
+struct tracepoint;
+
+struct tracepoint {
+	const char *name;		/* Tracepoint name */
+	int state;			/* State. */
+	void **funcs;
+} __attribute__((aligned(8)));
+
+
+#define TPPROTO(args...)	args
+#define TPARGS(args...)		args
+
+#ifdef CONFIG_TRACEPOINTS
+
+/*
+ * it_func[0] is never NULL because there is at least one element in the array
+ * when the array itself is non NULL.
+ */
+#define __DO_TRACE(tp, proto, args)					\
+	do {								\
+		void **it_func;						\
+									\
+		rcu_read_lock_sched();					\
+		it_func = rcu_dereference((tp)->funcs);			\
+		if (it_func) {						\
+			do {						\
+				((void(*)(proto))(*it_func))(args);	\
+			} while (*(++it_func));				\
+		}							\
+		rcu_read_unlock_sched();				\
+	} while (0)
+
+/*
+ * Make sure the alignment of the structure in the __tracepoints section will
+ * not add unwanted padding between the beginning of the section and the
+ * structure. Force alignment to the same alignment as the section start.
+ */
+#define DEFINE_TRACE(name, proto, args)					\
+	static inline void trace_##name(proto)				\
+	{								\
+		static const char __tpstrtab_##name[]			\
+		__attribute__((section("__tracepoints_strings")))	\
+		= #name ":" #proto;					\
+		static struct tracepoint __tracepoint_##name		\
+		__attribute__((section("__tracepoints"), aligned(8))) =	\
+		{ __tpstrtab_##name, 0, NULL };				\
+		if (unlikely(__tracepoint_##name.state))		\
+			__DO_TRACE(&__tracepoint_##name,		\
+				TPPROTO(proto), TPARGS(args));		\
+	}								\
+	static inline int register_trace_##name(void (*probe)(proto))	\
+	{								\
+		return tracepoint_probe_register(#name ":" #proto,	\
+			(void *)probe);					\
+	}								\
+	static inline void unregister_trace_##name(void (*probe)(proto))\
+	{								\
+		tracepoint_probe_unregister(#name ":" #proto,		\
+			(void *)probe);					\
+	}
+
+extern void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end);
+
+#else /* !CONFIG_TRACEPOINTS */
+#define DEFINE_TRACE(name, proto, args)			\
+	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
+	{ }								\
+	static inline void trace_##name(proto)				\
+	{ }								\
+	static inline int register_trace_##name(void (*probe)(proto))	\
+	{								\
+		return -ENOSYS;						\
+	}								\
+	static inline void unregister_trace_##name(void (*probe)(proto))\
+	{ }
+
+static inline void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end)
+{ }
+#endif /* CONFIG_TRACEPOINTS */
+
+/*
+ * Connect a probe to a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_register(const char *name, void *probe);
+
+/*
+ * Disconnect a probe from a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_unregister(const char *name, void *probe);
+
+struct tracepoint_iter {
+	struct module *module;
+	struct tracepoint *tracepoint;
+};
+
+extern void tracepoint_iter_start(struct tracepoint_iter *iter);
+extern void tracepoint_iter_next(struct tracepoint_iter *iter);
+extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
+extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
+extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
+	struct tracepoint *begin, struct tracepoint *end);
+
+/*
+ * tracepoint_synchronize_unregister must be called between the last tracepoint
+ * probe unregistration and the end of module exit to make sure there is no
+ * caller executing a probe when it is freed.
+ */
+static inline void tracepoint_synchronize_unregister(void)
+{
+	synchronize_sched();
+}
+
+#endif