Merge remote branch 'tip/auto-latest'

Conflicts:
	Makefile

24 files changed, 375 insertions, 252 deletions

diff --git a/include/asm-generic/local64.h b/include/asm-generic/local64.h
new file mode 100644
index 000000000000..02ac760c1a8b
--- /dev/null
+++ b/include/asm-generic/local64.h
@@ -0,0 +1,96 @@
+#ifndef _ASM_GENERIC_LOCAL64_H
+#define _ASM_GENERIC_LOCAL64_H
+
+#include <linux/percpu.h>
+#include <asm/types.h>
+
+/*
+ * A signed long type for operations which are atomic for a single CPU.
+ * Usually used in combination with per-cpu variables.
+ *
+ * This is the default implementation, which uses atomic64_t.  Which is
+ * rather pointless.  The whole point behind local64_t is that some processors
+ * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs
+ * running on this CPU.  local64_t allows exploitation of such capabilities.
+ */
+
+/* Implement in terms of atomics. */
+
+#if BITS_PER_LONG == 64
+
+#include <asm/local.h>
+
+typedef struct {
+	local_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i)	{ LOCAL_INIT(i) }
+
+#define local64_read(l)		local_read(&(l)->a)
+#define local64_set(l,i)	local_set((&(l)->a),(i))
+#define local64_inc(l)		local_inc(&(l)->a)
+#define local64_dec(l)		local_dec(&(l)->a)
+#define local64_add(i,l)	local_add((i),(&(l)->a))
+#define local64_sub(i,l)	local_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) local_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) local_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) local_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) local_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) local_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) local_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)	local_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) local_cmpxchg((&(l)->a), (o), (n))
+#define local64_xchg(l, n)	local_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l)	local_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)	local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)	local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)	local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)	local64_set((l), local64_read(l) - (i))
+
+#else /* BITS_PER_LONG != 64 */
+
+#include <asm/atomic.h>
+
+/* Don't use typedef: don't want them to be mixed with atomic_t's. */
+typedef struct {
+	atomic64_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+
+#define local64_read(l)		atomic64_read(&(l)->a)
+#define local64_set(l,i)	atomic64_set((&(l)->a),(i))
+#define local64_inc(l)		atomic64_inc(&(l)->a)
+#define local64_dec(l)		atomic64_dec(&(l)->a)
+#define local64_add(i,l)	atomic64_add((i),(&(l)->a))
+#define local64_sub(i,l)	atomic64_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) atomic64_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) atomic64_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) atomic64_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) atomic64_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) atomic64_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) atomic64_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)	atomic64_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n))
+#define local64_xchg(l, n)	atomic64_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l)	atomic64_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)	local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)	local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)	local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)	local64_set((l), local64_read(l) - (i))
+
+#endif /* BITS_PER_LONG != 64 */
+
+#endif /* _ASM_GENERIC_LOCAL64_H */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index a5a472b10746..c1a62c56a660 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -16,6 +16,7 @@
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
 # define __percpu	__attribute__((noderef, address_space(3)))
+# define __rcu
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
 #else
@@ -34,6 +35,7 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # define __release(x) (void)0
 # define __cond_lock(x,c) (c)
 # define __percpu
+# define __rcu
 #endif
 
 #ifdef __KERNEL__
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index e287863ac053..de6b1722cdca 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -48,6 +48,31 @@ extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 struct notifier_block;
 
+/*
+ * CPU notifier priorities.
+ */
+enum {
+	/*
+	 * SCHED_ACTIVE marks a cpu which is coming up active during
+	 * CPU_ONLINE and CPU_DOWN_FAILED and must be the first
+	 * notifier.  CPUSET_ACTIVE adjusts cpuset according to
+	 * cpu_active mask right after SCHED_ACTIVE.  During
+	 * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are
+	 * ordered in the similar way.
+	 *
+	 * This ordering guarantees consistent cpu_active mask and
+	 * migration behavior to all cpu notifiers.
+	 */
+	CPU_PRI_SCHED_ACTIVE	= INT_MAX,
+	CPU_PRI_CPUSET_ACTIVE	= INT_MAX - 1,
+	CPU_PRI_SCHED_INACTIVE	= INT_MIN + 1,
+	CPU_PRI_CPUSET_INACTIVE	= INT_MIN,
+
+	/* migration should happen before other stuff but after perf */
+	CPU_PRI_PERF		= 20,
+	CPU_PRI_MIGRATION	= 10,
+};
+
 #ifdef CONFIG_SMP
 /* Need to know about CPUs going up/down? */
 #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 457ed765a116..f20eb8f16025 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -20,6 +20,7 @@ extern int number_of_cpusets;	/* How many cpusets are defined in system? */
 
 extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
+extern void cpuset_update_active_cpus(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern int cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -132,6 +133,11 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 static inline int cpuset_init(void) { return 0; }
 static inline void cpuset_init_smp(void) {}
 
+static inline void cpuset_update_active_cpus(void)
+{
+	partition_sched_domains(1, NULL, NULL);
+}
+
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 013dc529e95f..551671e87927 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -11,6 +11,7 @@
 #include <linux/rcupdate.h>
 #include <linux/types.h>
 #include <linux/init.h>
+#include <linux/fs.h>
 
 #include <asm/atomic.h>
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 3167f2df4126..01df7ca4ead7 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -146,6 +146,9 @@ struct ftrace_event_class {
 	int			(*raw_init)(struct ftrace_event_call *);
 };
 
+extern int ftrace_event_reg(struct ftrace_event_call *event,
+			    enum trace_reg type);
+
 enum {
 	TRACE_EVENT_FL_ENABLED_BIT,
 	TRACE_EVENT_FL_FILTERED_BIT,
@@ -257,8 +260,7 @@ static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
 		       u64 count, struct pt_regs *regs, void *head)
 {
-	perf_tp_event(addr, count, raw_data, size, regs, head);
-	perf_swevent_put_recursion_context(rctx);
+	perf_tp_event(addr, count, raw_data, size, regs, head, rctx);
 }
 #endif
 
diff --git a/include/linux/io.h b/include/linux/io.h
index 6c7f0ba0d5fa..7fd2d2138bf3 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -29,10 +29,10 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count);
 
 #ifdef CONFIG_MMU
 int ioremap_page_range(unsigned long addr, unsigned long end,
-		       unsigned long phys_addr, pgprot_t prot);
+		       phys_addr_t phys_addr, pgprot_t prot);
 #else
 static inline int ioremap_page_range(unsigned long addr, unsigned long end,
-				     unsigned long phys_addr, pgprot_t prot)
+				     phys_addr_t phys_addr, pgprot_t prot)
 {
 	return 0;
 }
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5de838b0fc1a..f05a46830460 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -252,6 +252,13 @@ extern struct pid *session_of_pgrp(struct pid *pgrp);
 #define FW_WARN		"[Firmware Warn]: "
 #define FW_INFO		"[Firmware Info]: "
 
+/*
+ * HW_ERR
+ * Add this to a message for hardware errors, so that user can report
+ * it to hardware vendor instead of LKML or software vendor.
+ */
+#define HW_ERR		"[Hardware Error]: "
+
 #ifdef CONFIG_PRINTK
 asmlinkage int vprintk(const char *fmt, va_list args)
 	__attribute__ ((format (printf, 1, 0)));
diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h
deleted file mode 100644
index b616d3930c3b..000000000000
--- a/include/linux/kmemtrace.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- *
- * This file is released under GPL version 2.
- */
-
-#ifndef _LINUX_KMEMTRACE_H
-#define _LINUX_KMEMTRACE_H
-
-#ifdef __KERNEL__
-
-#include <trace/events/kmem.h>
-
-#ifdef CONFIG_KMEMTRACE
-extern void kmemtrace_init(void);
-#else
-static inline void kmemtrace_init(void)
-{
-}
-#endif
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_KMEMTRACE_H */
-
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index b752e807adde..06aab5eee134 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -20,10 +20,14 @@ extern void touch_nmi_watchdog(void);
 extern void acpi_nmi_disable(void);
 extern void acpi_nmi_enable(void);
 #else
+#ifndef CONFIG_HARDLOCKUP_DETECTOR
 static inline void touch_nmi_watchdog(void)
 {
 	touch_softlockup_watchdog();
 }
+#else
+extern void touch_nmi_watchdog(void);
+#endif
 static inline void acpi_nmi_disable(void) { }
 static inline void acpi_nmi_enable(void) { }
 #endif
@@ -47,4 +51,13 @@ static inline bool trigger_all_cpu_backtrace(void)
 }
 #endif
 
+#ifdef CONFIG_LOCKUP_DETECTOR
+int hw_nmi_is_cpu_stuck(struct pt_regs *);
+u64 hw_nmi_get_sample_period(void);
+extern int watchdog_enabled;
+struct ctl_table;
+extern int proc_dowatchdog_enabled(struct ctl_table *, int ,
+			void __user *, size_t *, loff_t *);
+#endif
+
 #endif
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5d0266d94985..716f99b682c1 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -214,8 +214,9 @@ struct perf_event_attr {
 				 *  See also PERF_RECORD_MISC_EXACT_IP
 				 */
 				precise_ip     :  2, /* skid constraint       */
+				mmap_data      :  1, /* non-exec mmap data    */
 
-				__reserved_1   : 47;
+				__reserved_1   : 46;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -461,6 +462,7 @@ enum perf_callchain_context {
 
 #ifdef CONFIG_PERF_EVENTS
 # include <asm/perf_event.h>
+# include <asm/local64.h>
 #endif
 
 struct perf_guest_info_callbacks {
@@ -531,14 +533,16 @@ struct hw_perf_event {
 			struct hrtimer	hrtimer;
 		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
-		/* breakpoint */
-		struct arch_hw_breakpoint	info;
+		struct { /* breakpoint */
+			struct arch_hw_breakpoint	info;
+			struct list_head		bp_list;
+		};
 #endif
 	};
-	atomic64_t			prev_count;
+	local64_t			prev_count;
 	u64				sample_period;
 	u64				last_period;
-	atomic64_t			period_left;
+	local64_t			period_left;
 	u64				interrupts;
 
 	u64				freq_time_stamp;
@@ -548,7 +552,10 @@ struct hw_perf_event {
 
 struct perf_event;
 
-#define PERF_EVENT_TXN_STARTED 1
+/*
+ * Common implementation detail of pmu::{start,commit,cancel}_txn
+ */
+#define PERF_EVENT_TXN 0x1
 
 /**
  * struct pmu - generic performance monitoring unit
@@ -562,14 +569,28 @@ struct pmu {
 	void (*unthrottle)		(struct perf_event *event);
 
 	/*
-	 * group events scheduling is treated as a transaction,
-	 * add group events as a whole and perform one schedulability test.
-	 * If test fails, roll back the whole group
+	 * Group events scheduling is treated as a transaction, add group
+	 * events as a whole and perform one schedulability test. If the test
+	 * fails, roll back the whole group
 	 */
 
+	/*
+	 * Start the transaction, after this ->enable() doesn't need
+	 * to do schedulability tests.
+	 */
 	void (*start_txn)	(const struct pmu *pmu);
-	void (*cancel_txn)	(const struct pmu *pmu);
+	/*
+	 * If ->start_txn() disabled the ->enable() schedulability test
+	 * then ->commit_txn() is required to perform one. On success
+	 * the transaction is closed. On error the transaction is kept
+	 * open until ->cancel_txn() is called.
+	 */
 	int  (*commit_txn)	(const struct pmu *pmu);
+	/*
+	 * Will cancel the transaction, assumes ->disable() is called for
+	 * each successfull ->enable() during the transaction.
+	 */
+	void (*cancel_txn)	(const struct pmu *pmu);
 };
 
 /**
@@ -584,7 +605,9 @@ enum perf_event_active_state {
 
 struct file;
 
-struct perf_mmap_data {
+#define PERF_BUFFER_WRITABLE		0x01
+
+struct perf_buffer {
 	atomic_t			refcount;
 	struct rcu_head			rcu_head;
 #ifdef CONFIG_PERF_USE_VMALLOC
@@ -650,7 +673,8 @@ struct perf_event {
 
 	enum perf_event_active_state	state;
 	unsigned int			attach_state;
-	atomic64_t			count;
+	local64_t			count;
+	atomic64_t			child_count;
 
 	/*
 	 * These are the total time in nanoseconds that the event
@@ -709,7 +733,7 @@ struct perf_event {
 	atomic_t			mmap_count;
 	int				mmap_locked;
 	struct user_struct		*mmap_user;
-	struct perf_mmap_data		*data;
+	struct perf_buffer		*buffer;
 
 	/* poll related */
 	wait_queue_head_t		waitq;
@@ -807,7 +831,7 @@ struct perf_cpu_context {
 
 struct perf_output_handle {
 	struct perf_event		*event;
-	struct perf_mmap_data		*data;
+	struct perf_buffer		*buffer;
 	unsigned long			wakeup;
 	unsigned long			size;
 	void				*addr;
@@ -910,8 +934,10 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
 
-extern void
-perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+#ifndef perf_arch_fetch_caller_regs
+static inline void
+perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
+#endif
 
 /*
  * Take a snapshot of the regs. Skip ip and frame pointer to
@@ -921,31 +947,11 @@ perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
  * - bp for callchains
  * - eflags, for future purposes, just in case
  */
-static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 {
-	unsigned long ip;
-
 	memset(regs, 0, sizeof(*regs));
 
-	switch (skip) {
-	case 1 :
-		ip = CALLER_ADDR0;
-		break;
-	case 2 :
-		ip = CALLER_ADDR1;
-		break;
-	case 3 :
-		ip = CALLER_ADDR2;
-		break;
-	case 4:
-		ip = CALLER_ADDR3;
-		break;
-	/* No need to support further for now */
-	default:
-		ip = 0;
-	}
-
-	return perf_arch_fetch_caller_regs(regs, ip, skip);
+	perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
 static inline void
@@ -955,21 +961,14 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 		struct pt_regs hot_regs;
 
 		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs, 1);
+			perf_fetch_caller_regs(&hot_regs);
 			regs = &hot_regs;
 		}
 		__perf_sw_event(event_id, nr, nmi, regs, addr);
 	}
 }
 
-extern void __perf_event_mmap(struct vm_area_struct *vma);
-
-static inline void perf_event_mmap(struct vm_area_struct *vma)
-{
-	if (vma->vm_flags & VM_EXEC)
-		__perf_event_mmap(vma);
-}
-
+extern void perf_event_mmap(struct vm_area_struct *vma);
 extern struct perf_guest_info_callbacks *perf_guest_cbs;
 extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
 extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
@@ -1001,7 +1000,7 @@ static inline bool perf_paranoid_kernel(void)
 extern void perf_event_init(void);
 extern void perf_tp_event(u64 addr, u64 count, void *record,
 			  int entry_size, struct pt_regs *regs,
-			  struct hlist_head *head);
+			  struct hlist_head *head, int rctx);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
@@ -1068,7 +1067,7 @@ static inline void perf_event_disable(struct perf_event *event)		{ }
 #define perf_cpu_notifier(fn)					\
 do {								\
 	static struct notifier_block fn##_nb __cpuinitdata =	\
-		{ .notifier_call = fn, .priority = 20 };	\
+		{ .notifier_call = fn, .priority = CPU_PRI_PERF }; \
 	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,		\
 		(void *)(unsigned long)smp_processor_id());	\
 	fn(&fn##_nb, (unsigned long)CPU_STARTING,		\
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index b653b4aaa8a6..9fbc54a2585d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -40,6 +40,7 @@
 #include <linux/seqlock.h>
 #include <linux/lockdep.h>
 #include <linux/completion.h>
+#include <linux/debugobjects.h>
 
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable; /* for sysctl */
@@ -79,6 +80,16 @@ extern void rcu_init(void);
        (ptr)->next = NULL; (ptr)->func = NULL; \
 } while (0)
 
+/*
+ * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
+ * initialization and destruction of rcu_head on the stack. rcu_head structures
+ * allocated dynamically in the heap or defined statically don't need any
+ * initialization.
+ */
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+extern void init_rcu_head_on_stack(struct rcu_head *head);
+extern void destroy_rcu_head_on_stack(struct rcu_head *head);
+#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 static inline void init_rcu_head_on_stack(struct rcu_head *head)
 {
 }
@@ -86,6 +97,7 @@ static inline void init_rcu_head_on_stack(struct rcu_head *head)
 static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
 {
 }
+#endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
@@ -517,4 +529,74 @@ extern void call_rcu(struct rcu_head *head,
 extern void call_rcu_bh(struct rcu_head *head,
 			void (*func)(struct rcu_head *head));
 
+/*
+ * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
+ * by call_rcu() and rcu callback execution, and are therefore not part of the
+ * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors.
+ */
+
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+# define STATE_RCU_HEAD_READY	0
+# define STATE_RCU_HEAD_QUEUED	1
+
+extern struct debug_obj_descr rcuhead_debug_descr;
+
+static inline void debug_rcu_head_queue(struct rcu_head *head)
+{
+	debug_object_activate(head, &rcuhead_debug_descr);
+	debug_object_active_state(head, &rcuhead_debug_descr,
+				  STATE_RCU_HEAD_READY,
+				  STATE_RCU_HEAD_QUEUED);
+}
+
+static inline void debug_rcu_head_unqueue(struct rcu_head *head)
+{
+	debug_object_active_state(head, &rcuhead_debug_descr,
+				  STATE_RCU_HEAD_QUEUED,
+				  STATE_RCU_HEAD_READY);
+	debug_object_deactivate(head, &rcuhead_debug_descr);
+}
+#else	/* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void debug_rcu_head_queue(struct rcu_head *head)
+{
+}
+
+static inline void debug_rcu_head_unqueue(struct rcu_head *head)
+{
+}
+#endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+
+#ifndef CONFIG_PROVE_RCU
+#define __do_rcu_dereference_check(c) do { } while (0)
+#endif /* #ifdef CONFIG_PROVE_RCU */
+
+#define __rcu_dereference_index_check(p, c) \
+	({ \
+		typeof(p) _________p1 = ACCESS_ONCE(p); \
+		__do_rcu_dereference_check(c); \
+		smp_read_barrier_depends(); \
+		(_________p1); \
+	})
+
+/**
+ * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * Similar to rcu_dereference_check(), but omits the sparse checking.
+ * This allows rcu_dereference_index_check() to be used on integers,
+ * which can then be used as array indices.  Attempting to use
+ * rcu_dereference_check() on an integer will give compiler warnings
+ * because the sparse address-space mechanism relies on dereferencing
+ * the RCU-protected pointer.  Dereferencing integers is not something
+ * that even gcc will put up with.
+ *
+ * Note that this function does not implicitly check for RCU read-side
+ * critical sections.  If this function gains lots of uses, it might
+ * make sense to provide versions for each flavor of RCU, but it does
+ * not make sense as of early 2010.
+ */
+#define rcu_dereference_index_check(p, c) \
+	__rcu_dereference_index_check((p), (c))
+
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 747fcaedddb7..1f2579879f69 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -271,14 +271,11 @@ extern int runqueue_is_locked(int cpu);
 
 extern cpumask_var_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
-extern int select_nohz_load_balancer(int cpu);
-extern int get_nohz_load_balancer(void);
+extern void select_nohz_load_balancer(int stop_tick);
+extern int get_nohz_timer_target(void);
 extern int nohz_ratelimit(int cpu);
 #else
-static inline int select_nohz_load_balancer(int cpu)
-{
-	return 0;
-}
+static inline void select_nohz_load_balancer(int stop_tick) { }
 
 static inline int nohz_ratelimit(int cpu)
 {
@@ -315,20 +312,16 @@ extern void scheduler_tick(void);
 
 extern void sched_show_task(struct task_struct *p);
 
-#ifdef CONFIG_DETECT_SOFTLOCKUP
-extern void softlockup_tick(void);
+#ifdef CONFIG_LOCKUP_DETECTOR
 extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
-extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
-				    void __user *buffer,
-				    size_t *lenp, loff_t *ppos);
+extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
+				  void __user *buffer,
+				  size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
 extern int softlockup_thresh;
 #else
-static inline void softlockup_tick(void)
-{
-}
 static inline void touch_softlockup_watchdog(void)
 {
 }
@@ -804,7 +797,7 @@ enum cpu_idle_type {
 #define SD_POWERSAVINGS_BALANCE	0x0100	/* Balance for power savings */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
-
+#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
 
 enum powersavings_balance_level {
@@ -839,6 +832,8 @@ static inline int sd_balance_for_package_power(void)
 	return SD_PREFER_SIBLING;
 }
 
+extern int __weak arch_sd_sibiling_asym_packing(void);
+
 /*
  * Optimise SD flags for power savings:
  * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings.
@@ -860,7 +855,7 @@ struct sched_group {
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
 	 * single CPU.
 	 */
-	unsigned int cpu_power;
+	unsigned int cpu_power, cpu_power_orig;
 
 	/*
 	 * The CPUs this group covers.
@@ -1696,6 +1691,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
 #define PF_VCPU		0x00000010	/* I'm a virtual CPU */
+#define PF_WQ_WORKER	0x00000020	/* I'm a workqueue worker */
 #define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
 #define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
 #define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
@@ -1790,20 +1786,23 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 #endif
 
 /*
- * Architectures can set this to 1 if they have specified
- * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
- * but then during bootup it turns out that sched_clock()
- * is reliable after all:
+ * Do not use outside of architecture code which knows its limitations.
+ *
+ * sched_clock() has no promise of monotonicity or bounded drift between
+ * CPUs, use (which you should not) requires disabling IRQs.
+ *
+ * Please use one of the three interfaces below.
  */
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-extern int sched_clock_stable;
-#endif
-
-/* ftrace calls sched_clock() directly */
 extern unsigned long long notrace sched_clock(void);
+/*
+ * See the comment in kernel/sched_clock.c
+ */
+extern u64 cpu_clock(int cpu);
+extern u64 local_clock(void);
+extern u64 sched_clock_cpu(int cpu);
+
 
 extern void sched_clock_init(void);
-extern u64 sched_clock_cpu(int cpu);
 
 #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 static inline void sched_clock_tick(void)
@@ -1818,17 +1817,19 @@ static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
 }
 #else
+/*
+ * Architectures can set this to 1 if they have specified
+ * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
+ * but then during bootup it turns out that sched_clock()
+ * is reliable after all:
+ */
+extern int sched_clock_stable;
+
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 #endif
 
-/*
- * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
- * clock constructed from sched_clock():
- */
-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);
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 1812dac8c496..1acfa73ce2ac 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -14,7 +14,8 @@
 #include <asm/page.h>		/* kmalloc_sizes.h needs PAGE_SIZE */
 #include <asm/cache.h>		/* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
-#include <linux/kmemtrace.h>
+
+#include <trace/events/kmem.h>
 
 #ifndef ARCH_KMALLOC_MINALIGN
 /*
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 4ba59cfc1f75..6447a723ecb1 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -10,9 +10,10 @@
 #include <linux/gfp.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
-#include <linux/kmemtrace.h>
 #include <linux/kmemleak.h>
 
+#include <trace/events/kmem.h>
+
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
 	ALLOC_SLOWPATH,		/* Allocation by getting a new cpu slab */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 3c7620c26201..ad7600a62b7e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -124,7 +124,8 @@ extern struct trace_event_functions enter_syscall_print_funcs;
 extern struct trace_event_functions exit_syscall_print_funcs;
 
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
-	static struct syscall_metadata __syscall_meta_##sname;		\
+	static struct syscall_metadata					\
+	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_enter_##sname;		\
 	static struct ftrace_event_call __used				\
@@ -138,7 +139,8 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
-	static struct syscall_metadata __syscall_meta_##sname;		\
+	static struct syscall_metadata					\
+	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_exit_##sname;		\
 	static struct ftrace_event_call __used				\
@@ -165,7 +167,6 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.enter_event	= &event_enter_##sname,		\
 		.exit_event	= &event_exit_##sname,		\
 		.enter_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
-		.exit_fields	= LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \
 	};
 
 #define SYSCALL_DEFINE0(sname)					\
@@ -180,7 +181,6 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.enter_event	= &event_enter__##sname,	\
 		.exit_event	= &event_exit__##sname,		\
 		.enter_fields	= LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \
-		.exit_fields	= LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \
 	};							\
 	asmlinkage long sys_##sname(void)
 #else
diff --git a/include/linux/topology.h b/include/linux/topology.h
index c44df50a05ab..b572e432d2f3 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -103,6 +103,7 @@ int arch_update_cpu_topology(void);
 				| 1*SD_SHARE_PKG_RESOURCES		\
 				| 0*SD_SERIALIZE			\
 				| 0*SD_PREFER_SIBLING			\
+				| arch_sd_sibling_asym_packing()	\
 				,					\
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 227c2a585e4f..de05e96e0a70 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -30,7 +30,7 @@ struct vm_struct {
 	unsigned long		flags;
 	struct page		**pages;
 	unsigned int		nr_pages;
-	unsigned long		phys_addr;
+	phys_addr_t		phys_addr;
 	void			*caller;
 };
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 9466e860d8c2..d0f7c8178498 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -297,4 +297,8 @@ static inline long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
 #else
 long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg);
 #endif /* CONFIG_SMP */
+
+#ifdef CONFIG_LOCKDEP
+int in_workqueue_context(struct workqueue_struct *wq);
+#endif
 #endif
diff --git a/include/trace/boot.h b/include/trace/boot.h
deleted file mode 100644
index 088ea089e31d..000000000000
--- a/include/trace/boot.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef _LINUX_TRACE_BOOT_H
-#define _LINUX_TRACE_BOOT_H
-
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/init.h>
-
-/*
- * Structure which defines the trace of an initcall
- * while it is called.
- * You don't have to fill the func field since it is
- * only used internally by the tracer.
- */
-struct boot_trace_call {
-	pid_t			caller;
-	char			func[KSYM_SYMBOL_LEN];
-};
-
-/*
- * Structure which defines the trace of an initcall
- * while it returns.
- */
-struct boot_trace_ret {
-	char			func[KSYM_SYMBOL_LEN];
-	int				result;
-	unsigned long long	duration;		/* nsecs */
-};
-
-#ifdef CONFIG_BOOT_TRACER
-/* Append the traces on the ring-buffer */
-extern void trace_boot_call(struct boot_trace_call *bt, initcall_t fn);
-extern void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn);
-
-/* Tells the tracer that smp_pre_initcall is finished.
- * So we can start the tracing
- */
-extern void start_boot_trace(void);
-
-/* Resume the tracing of other necessary events
- * such as sched switches
- */
-extern void enable_boot_trace(void);
-
-/* Suspend this tracing. Actually, only sched_switches tracing have
- * to be suspended. Initcalls doesn't need it.)
- */
-extern void disable_boot_trace(void);
-#else
-static inline
-void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { }
-
-static inline
-void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { }
-
-static inline void start_boot_trace(void) { }
-static inline void enable_boot_trace(void) { }
-static inline void disable_boot_trace(void) { }
-#endif /* CONFIG_BOOT_TRACER */
-
-#endif /* __LINUX_TRACE_BOOT_H */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index b9e1dd6c6208..9208c92aeab5 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -50,31 +50,6 @@ TRACE_EVENT(sched_kthread_stop_ret,
 );
 
 /*
- * Tracepoint for waiting on task to unschedule:
- */
-TRACE_EVENT(sched_wait_task,
-
-	TP_PROTO(struct task_struct *p),
-
-	TP_ARGS(p),
-
-	TP_STRUCT__entry(
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
-		__field(	int,	prio			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid	= p->pid;
-		__entry->prio	= p->prio;
-	),
-
-	TP_printk("comm=%s pid=%d prio=%d",
-		  __entry->comm, __entry->pid, __entry->prio)
-);
-
-/*
  * Tracepoint for waking up a task:
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
@@ -240,6 +215,13 @@ DEFINE_EVENT(sched_process_template, sched_process_exit,
 	     TP_ARGS(p));
 
 /*
+ * Tracepoint for waiting on task to unschedule:
+ */
+DEFINE_EVENT(sched_process_template, sched_wait_task,
+	TP_PROTO(struct task_struct *p),
+	TP_ARGS(p));
+
+/*
  * Tracepoint for a waiting task:
  */
 TRACE_EVENT(sched_process_wait,
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 9496b965d62a..c624126a9c8a 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -8,11 +8,7 @@
 #include <linux/hrtimer.h>
 #include <linux/timer.h>
 
-/**
- * timer_init - called when the timer is initialized
- * @timer:	pointer to struct timer_list
- */
-TRACE_EVENT(timer_init,
+DECLARE_EVENT_CLASS(timer_class,
 
 	TP_PROTO(struct timer_list *timer),
 
@@ -30,6 +26,17 @@ TRACE_EVENT(timer_init,
 );
 
 /**
+ * timer_init - called when the timer is initialized
+ * @timer:	pointer to struct timer_list
+ */
+DEFINE_EVENT(timer_class, timer_init,
+
+	TP_PROTO(struct timer_list *timer),
+
+	TP_ARGS(timer)
+);
+
+/**
  * timer_start - called when the timer is started
  * @timer:	pointer to struct timer_list
  * @expires:	the timers expiry time
@@ -94,42 +101,22 @@ TRACE_EVENT(timer_expire_entry,
  * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might
  * be invalid. We solely track the pointer.
  */
-TRACE_EVENT(timer_expire_exit,
+DEFINE_EVENT(timer_class, timer_expire_exit,
 
 	TP_PROTO(struct timer_list *timer),
 
-	TP_ARGS(timer),
-
-	TP_STRUCT__entry(
-		__field(void *,	timer	)
-	),
-
-	TP_fast_assign(
-		__entry->timer	= timer;
-	),
-
-	TP_printk("timer=%p", __entry->timer)
+	TP_ARGS(timer)
 );
 
 /**
  * timer_cancel - called when the timer is canceled
  * @timer:	pointer to struct timer_list
  */
-TRACE_EVENT(timer_cancel,
+DEFINE_EVENT(timer_class, timer_cancel,
 
 	TP_PROTO(struct timer_list *timer),
 
-	TP_ARGS(timer),
-
-	TP_STRUCT__entry(
-		__field( void *,	timer	)
-	),
-
-	TP_fast_assign(
-		__entry->timer	= timer;
-	),
-
-	TP_printk("timer=%p", __entry->timer)
+	TP_ARGS(timer)
 );
 
 /**
@@ -224,14 +211,7 @@ TRACE_EVENT(hrtimer_expire_entry,
 		  (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now }))
  );
 
-/**
- * hrtimer_expire_exit - called immediately after the hrtimer callback returns
- * @timer:	pointer to struct hrtimer
- *
- * When used in combination with the hrtimer_expire_entry tracepoint we can
- * determine the runtime of the callback function.
- */
-TRACE_EVENT(hrtimer_expire_exit,
+DECLARE_EVENT_CLASS(hrtimer_class,
 
 	TP_PROTO(struct hrtimer *hrtimer),
 
@@ -249,24 +229,28 @@ TRACE_EVENT(hrtimer_expire_exit,
 );
 
 /**
- * hrtimer_cancel - called when the hrtimer is canceled
- * @hrtimer:	pointer to struct hrtimer
+ * hrtimer_expire_exit - called immediately after the hrtimer callback returns
+ * @timer:	pointer to struct hrtimer
+ *
+ * When used in combination with the hrtimer_expire_entry tracepoint we can
+ * determine the runtime of the callback function.
  */
-TRACE_EVENT(hrtimer_cancel,
+DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit,
 
 	TP_PROTO(struct hrtimer *hrtimer),
 
-	TP_ARGS(hrtimer),
+	TP_ARGS(hrtimer)
+);
 
-	TP_STRUCT__entry(
-		__field( void *,	hrtimer	)
-	),
+/**
+ * hrtimer_cancel - called when the hrtimer is canceled
+ * @hrtimer:	pointer to struct hrtimer
+ */
+DEFINE_EVENT(hrtimer_class, hrtimer_cancel,
 
-	TP_fast_assign(
-		__entry->hrtimer	= hrtimer;
-	),
+	TP_PROTO(struct hrtimer *hrtimer),
 
-	TP_printk("hrtimer=%p", __entry->hrtimer)
+	TP_ARGS(hrtimer)
 );
 
 /**
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 5a64905d7278..55c1fd1bbc3d 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -439,6 +439,7 @@ static inline notrace int ftrace_get_offsets_##call(			\
  *	.fields			= LIST_HEAD_INIT(event_class_##call.fields),
  *	.raw_init		= trace_event_raw_init,
  *	.probe			= ftrace_raw_event_##call,
+ *	.reg			= ftrace_event_reg,
  * };
  *
  * static struct ftrace_event_call __used
@@ -567,6 +568,7 @@ static struct ftrace_event_class __used event_class_##call = {		\
 	.fields			= LIST_HEAD_INIT(event_class_##call.fields),\
 	.raw_init		= trace_event_raw_init,			\
 	.probe			= ftrace_raw_event_##call,		\
+	.reg			= ftrace_event_reg,			\
 	_TRACE_PERF_INIT(call)						\
 };
 
@@ -705,7 +707,7 @@ perf_trace_##call(void *__data, proto)					\
 	int __data_size;						\
 	int rctx;							\
 									\
-	perf_fetch_caller_regs(&__regs, 1);				\
+	perf_fetch_caller_regs(&__regs);				\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 257e08960d7b..31966a4fb8cc 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -26,7 +26,6 @@ struct syscall_metadata {
 	const char	**types;
 	const char	**args;
 	struct list_head enter_fields;
-	struct list_head exit_fields;
 
 	struct ftrace_event_call *enter_event;
 	struct ftrace_event_call *exit_event;