Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

Conflicts:
	include/linux/mod_devicetable.h
	scripts/mod/file2alias.c

42 files changed, 704 insertions, 440 deletions

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index c99c64dc5f3..c33749f95b3 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -33,7 +33,7 @@
  * Atomically reads the value of @v.  Note that the guaranteed
  * useful range of an atomic_t is only 24 bits.
  */
-#define atomic_read(v)	((v)->counter)
+#define atomic_read(v)	(*(volatile int *)&(v)->counter)
 
 /**
  * atomic_set - set atomic variable
diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 00000000000..6a211f40665
--- /dev/null
+++ b/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1,25 @@
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+	return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+	return __sw_hweight16(w);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+	return __sw_hweight8(w);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+	return __sw_hweight64(w);
+}
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/const_hweight.h b/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 00000000000..fa2a50b7ee6
--- /dev/null
+++ b/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+
+/*
+ * Compile time versions of __arch_hweightN()
+ */
+#define __const_hweight8(w)		\
+      (	(!!((w) & (1ULL << 0))) +	\
+	(!!((w) & (1ULL << 1))) +	\
+	(!!((w) & (1ULL << 2))) +	\
+	(!!((w) & (1ULL << 3))) +	\
+	(!!((w) & (1ULL << 4))) +	\
+	(!!((w) & (1ULL << 5))) +	\
+	(!!((w) & (1ULL << 6))) +	\
+	(!!((w) & (1ULL << 7)))	)
+
+#define __const_hweight16(w) (__const_hweight8(w)  + __const_hweight8((w)  >> 8 ))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+/*
+ * Generic interface.
+ */
+#define hweight8(w)  (__builtin_constant_p(w) ? __const_hweight8(w)  : __arch_hweight8(w))
+#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))
+
+/*
+ * Interface for known constant arguments
+ */
+#define HWEIGHT8(w)  (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w))
+#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w))
+#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w))
+#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w))
+
+/*
+ * Type invariant interface to the compile time constant hweight functions.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)w)
+
+#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/hweight.h b/include/asm-generic/bitops/hweight.h
index fbbc383771d..a94d6519c7e 100644
--- a/include/asm-generic/bitops/hweight.h
+++ b/include/asm-generic/bitops/hweight.h
@@ -1,11 +1,7 @@
 #ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_HWEIGHT_H_
 
-#include <asm/types.h>
-
-extern unsigned int hweight32(unsigned int w);
-extern unsigned int hweight16(unsigned int w);
-extern unsigned int hweight8(unsigned int w);
-extern unsigned long hweight64(__u64 w);
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
 
 #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index b926afe8c03..3da73f5f0ae 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -116,11 +116,12 @@ extern unsigned long acpi_realmode_flags;
 
 int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
+int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi);
 
 #ifdef CONFIG_X86_IO_APIC
-extern int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity);
+extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity);
 #else
-#define acpi_get_override_irq(bus, trigger, polarity) (-1)
+#define acpi_get_override_irq(gsi, trigger, polarity) (-1)
 #endif
 /*
  * This function undoes the effect of one call to acpi_register_gsi().
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index b796eab5ca7..fc68053378c 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -10,6 +10,11 @@
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
 
+extern unsigned int __sw_hweight8(unsigned int w);
+extern unsigned int __sw_hweight16(unsigned int w);
+extern unsigned int __sw_hweight32(unsigned int w);
+extern unsigned long __sw_hweight64(__u64 w);
+
 /*
  * Include this here because some architectures need generic_ffs/fls in
  * scope
@@ -44,31 +49,6 @@ static inline unsigned long hweight_long(unsigned long w)
 	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
 }
 
-/*
- * Clearly slow versions of the hweightN() functions, their benefit is
- * of course compile time evaluation of constant arguments.
- */
-#define HWEIGHT8(w)					\
-      (	BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) +	\
-	(!!((w) & (1ULL << 0))) +			\
-	(!!((w) & (1ULL << 1))) +			\
-	(!!((w) & (1ULL << 2))) +			\
-	(!!((w) & (1ULL << 3))) +			\
-	(!!((w) & (1ULL << 4))) +			\
-	(!!((w) & (1ULL << 5))) +			\
-	(!!((w) & (1ULL << 6))) +			\
-	(!!((w) & (1ULL << 7)))	)
-
-#define HWEIGHT16(w) (HWEIGHT8(w)  + HWEIGHT8((w) >> 8))
-#define HWEIGHT32(w) (HWEIGHT16(w) + HWEIGHT16((w) >> 16))
-#define HWEIGHT64(w) (HWEIGHT32(w) + HWEIGHT32((w) >> 32))
-
-/*
- * Type invariant version that simply casts things to the
- * largest type.
- */
-#define HWEIGHT(w)   HWEIGHT64((u64)(w))
-
 /**
  * rol32 - rotate a 32-bit value left
  * @word: value to rotate
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 4de02b10007..9f15150ce8d 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -278,6 +278,27 @@ struct freq_attr {
 	ssize_t (*store)(struct cpufreq_policy *, const char *, size_t count);
 };
 
+#define cpufreq_freq_attr_ro(_name)		\
+static struct freq_attr _name =			\
+__ATTR(_name, 0444, show_##_name, NULL)
+
+#define cpufreq_freq_attr_ro_perm(_name, _perm)	\
+static struct freq_attr _name =			\
+__ATTR(_name, _perm, show_##_name, NULL)
+
+#define cpufreq_freq_attr_ro_old(_name)		\
+static struct freq_attr _name##_old =		\
+__ATTR(_name, 0444, show_##_name##_old, NULL)
+
+#define cpufreq_freq_attr_rw(_name)		\
+static struct freq_attr _name =			\
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+#define cpufreq_freq_attr_rw_old(_name)		\
+static struct freq_attr _name##_old =		\
+__ATTR(_name, 0644, show_##_name##_old, store_##_name##_old)
+
+
 struct global_attr {
 	struct attribute attr;
 	ssize_t (*show)(struct kobject *kobj,
@@ -286,6 +307,15 @@ struct global_attr {
 			 const char *c, size_t count);
 };
 
+#define define_one_global_ro(_name)		\
+static struct global_attr _name =		\
+__ATTR(_name, 0444, show_##_name, NULL)
+
+#define define_one_global_rw(_name)		\
+static struct global_attr _name =		\
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+
 /*********************************************************************
  *                        CPUFREQ 2.6. INTERFACE                     *
  *********************************************************************/
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index a5740fc4d04..a73454aec33 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -21,8 +21,7 @@ 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_cpus_allowed(struct task_struct *p, struct cpumask *mask);
-extern void cpuset_cpus_allowed_locked(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);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -69,9 +68,6 @@ struct seq_file;
 extern void cpuset_task_status_allowed(struct seq_file *m,
 					struct task_struct *task);
 
-extern void cpuset_lock(void);
-extern void cpuset_unlock(void);
-
 extern int cpuset_mem_spread_node(void);
 
 static inline int cpuset_do_page_mem_spread(void)
@@ -105,10 +101,11 @@ static inline void cpuset_cpus_allowed(struct task_struct *p,
 {
 	cpumask_copy(mask, cpu_possible_mask);
 }
-static inline void cpuset_cpus_allowed_locked(struct task_struct *p,
-					      struct cpumask *mask)
+
+static inline int cpuset_cpus_allowed_fallback(struct task_struct *p)
 {
-	cpumask_copy(mask, cpu_possible_mask);
+	cpumask_copy(&p->cpus_allowed, cpu_possible_mask);
+	return cpumask_any(cpu_active_mask);
 }
 
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
@@ -157,9 +154,6 @@ static inline void cpuset_task_status_allowed(struct seq_file *m,
 {
 }
 
-static inline void cpuset_lock(void) {}
-static inline void cpuset_unlock(void) {}
-
 static inline int cpuset_mem_spread_node(void)
 {
 	return 0;
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 30b93b2a01a..eebb617c17d 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -186,6 +186,8 @@ d_iput:		no		no		no       yes
 
 #define DCACHE_FSNOTIFY_PARENT_WATCHED	0x0080 /* Parent inode is watched by some fsnotify listener */
 
+#define DCACHE_CANT_MOUNT	0x0100
+
 extern spinlock_t dcache_lock;
 extern seqlock_t rename_lock;
 
@@ -358,6 +360,18 @@ static inline int d_unlinked(struct dentry *dentry)
 	return d_unhashed(dentry) && !IS_ROOT(dentry);
 }
 
+static inline int cant_mount(struct dentry *dentry)
+{
+	return (dentry->d_flags & DCACHE_CANT_MOUNT);
+}
+
+static inline void dont_mount(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	dentry->d_flags |= DCACHE_CANT_MOUNT;
+	spin_unlock(&dentry->d_lock);
+}
+
 static inline struct dentry *dget_parent(struct dentry *dentry)
 {
 	struct dentry *ret;
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 8c243aaa86a..597692f1fc8 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -20,12 +20,14 @@ struct debug_obj_descr;
  * struct debug_obj - representaion of an tracked object
  * @node:	hlist node to link the object into the tracker list
  * @state:	tracked object state
+ * @astate:	current active state
  * @object:	pointer to the real object
  * @descr:	pointer to an object type specific debug description structure
  */
 struct debug_obj {
 	struct hlist_node	node;
 	enum debug_obj_state	state;
+	unsigned int		astate;
 	void			*object;
 	struct debug_obj_descr	*descr;
 };
@@ -60,6 +62,15 @@ extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
 extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
 extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
 
+/*
+ * Active state:
+ * - Set at 0 upon initialization.
+ * - Must return to 0 before deactivation.
+ */
+extern void
+debug_object_active_state(void *addr, struct debug_obj_descr *descr,
+			  unsigned int expect, unsigned int next);
+
 extern void debug_objects_early_init(void);
 extern void debug_objects_mem_init(void);
 #else
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 01e6adea07e..41e46330d9b 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -82,9 +82,13 @@ void clear_ftrace_function(void);
 extern void ftrace_stub(unsigned long a0, unsigned long a1);
 
 #else /* !CONFIG_FUNCTION_TRACER */
-# define register_ftrace_function(ops) do { } while (0)
-# define unregister_ftrace_function(ops) do { } while (0)
-# define clear_ftrace_function(ops) do { } while (0)
+/*
+ * (un)register_ftrace_function must be a macro since the ops parameter
+ * must not be evaluated.
+ */
+#define register_ftrace_function(ops) ({ 0; })
+#define unregister_ftrace_function(ops) ({ 0; })
+static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
 static inline void ftrace_stop(void) { }
 static inline void ftrace_start(void) { }
@@ -237,11 +241,13 @@ extern int skip_trace(unsigned long ip);
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
 #else
-# define skip_trace(ip)				({ 0; })
-# define ftrace_force_update()			({ 0; })
-# 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 int skip_trace(unsigned long ip) { return 0; }
+static inline int ftrace_force_update(void) { return 0; }
+static inline void ftrace_set_filter(unsigned char *buf, int len, int reset)
+{
+}
+static inline void ftrace_disable_daemon(void) { }
+static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
 static inline int register_ftrace_command(struct ftrace_func_command *cmd)
 {
@@ -314,16 +320,16 @@ static inline void __ftrace_enabled_restore(int enabled)
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
   extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
 #else
-# define time_hardirqs_on(a0, a1)		do { } while (0)
-# define time_hardirqs_off(a0, a1)		do { } while (0)
+  static inline void time_hardirqs_on(unsigned long a0, unsigned long a1) { }
+  static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { }
 #endif
 
 #ifdef CONFIG_PREEMPT_TRACER
   extern void trace_preempt_on(unsigned long a0, unsigned long a1);
   extern void trace_preempt_off(unsigned long a0, unsigned long a1);
 #else
-# define trace_preempt_on(a0, a1)		do { } while (0)
-# define trace_preempt_off(a0, a1)		do { } while (0)
+  static inline void trace_preempt_on(unsigned long a0, unsigned long a1) { }
+  static inline void trace_preempt_off(unsigned long a0, unsigned long a1) { }
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
@@ -352,6 +358,10 @@ struct ftrace_graph_ret {
 	int depth;
 };
 
+/* Type of the callback handlers for tracing function graph*/
+typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
+typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 /* for init task */
@@ -400,10 +410,6 @@ extern char __irqentry_text_end[];
 
 #define FTRACE_RETFUNC_DEPTH 50
 #define FTRACE_RETSTACK_ALLOC_SIZE 32
-/* Type of the callback handlers for tracing function graph*/
-typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
-typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
-
 extern int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 				trace_func_graph_ent_t entryfunc);
 
@@ -441,6 +447,13 @@ static inline void unpause_graph_tracing(void)
 static inline void ftrace_graph_init_task(struct task_struct *t) { }
 static inline void ftrace_graph_exit_task(struct task_struct *t) { }
 
+static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
+			  trace_func_graph_ent_t entryfunc)
+{
+	return -1;
+}
+static inline void unregister_ftrace_graph(void) { }
+
 static inline int task_curr_ret_stack(struct task_struct *tsk)
 {
 	return -1;
@@ -492,7 +505,9 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 	return tsk->trace & TSK_TRACE_FL_GRAPH;
 }
 
-extern int ftrace_dump_on_oops;
+enum ftrace_dump_mode;
+
+extern enum ftrace_dump_mode ftrace_dump_on_oops;
 
 #ifdef CONFIG_PREEMPT
 #define INIT_TRACE_RECURSION		.trace_recursion = 0,
@@ -504,18 +519,6 @@ extern int ftrace_dump_on_oops;
 #define INIT_TRACE_RECURSION
 #endif
 
-#ifdef CONFIG_HW_BRANCH_TRACER
-
-void trace_hw_branch(u64 from, u64 to);
-void trace_hw_branch_oops(void);
-
-#else /* CONFIG_HW_BRANCH_TRACER */
-
-static inline void trace_hw_branch(u64 from, u64 to) {}
-static inline void trace_hw_branch_oops(void) {}
-
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
 #ifdef CONFIG_FTRACE_SYSCALLS
 
 unsigned long arch_syscall_addr(int nr);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index c0f4b364c71..39e71b0a3bf 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -58,6 +58,7 @@ struct trace_iterator {
 	/* The below is zeroed out in pipe_read */
 	struct trace_seq	seq;
 	struct trace_entry	*ent;
+	unsigned long		lost_events;
 	int			leftover;
 	int			cpu;
 	u64			ts;
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index c70d27af03f..a2d6ea49ec5 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -9,9 +9,22 @@ enum {
 };
 
 enum {
-	HW_BREAKPOINT_R = 1,
-	HW_BREAKPOINT_W = 2,
-	HW_BREAKPOINT_X = 4,
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
 };
 
 #ifdef __KERNEL__
@@ -34,6 +47,12 @@ static inline void hw_breakpoint_init(struct perf_event_attr *attr)
 	attr->sample_period = 1;
 }
 
+static inline void ptrace_breakpoint_init(struct perf_event_attr *attr)
+{
+	hw_breakpoint_init(attr);
+	attr->exclude_kernel = 1;
+}
+
 static inline unsigned long hw_breakpoint_addr(struct perf_event *bp)
 {
 	return bp->attr.bp_addr;
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index b1ed1cd8e2a..7996fc2c9ba 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -49,7 +49,6 @@ extern struct group_info init_groups;
 		{ .first = &init_task.pids[PIDTYPE_PGID].node },	\
 		{ .first = &init_task.pids[PIDTYPE_SID].node },		\
 	},								\
-	.rcu		= RCU_HEAD_INIT,				\
 	.level		= 0,						\
 	.numbers	= { {						\
 		.nr		= 0,					\
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3af4ffd591b..be22ad83689 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -37,9 +37,9 @@ struct iommu_ops {
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
-		   phys_addr_t paddr, size_t size, int prot);
-	void (*unmap)(struct iommu_domain *domain, unsigned long iova,
-		      size_t size);
+		   phys_addr_t paddr, int gfp_order, int prot);
+	int (*unmap)(struct iommu_domain *domain, unsigned long iova,
+		     int gfp_order);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    unsigned long iova);
 	int (*domain_has_cap)(struct iommu_domain *domain,
@@ -56,10 +56,10 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_map_range(struct iommu_domain *domain, unsigned long iova,
-			   phys_addr_t paddr, size_t size, int prot);
-extern void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova,
-			      size_t size);
+extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
+		     phys_addr_t paddr, int gfp_order, int prot);
+extern int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+		       int gfp_order);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
 				      unsigned long iova);
 extern int iommu_domain_has_cap(struct iommu_domain *domain,
@@ -96,16 +96,16 @@ static inline void iommu_detach_device(struct iommu_domain *domain,
 {
 }
 
-static inline int iommu_map_range(struct iommu_domain *domain,
-				  unsigned long iova, phys_addr_t paddr,
-				  size_t size, int prot)
+static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, int gfp_order, int prot)
 {
 	return -ENODEV;
 }
 
-static inline void iommu_unmap_range(struct iommu_domain *domain,
-				     unsigned long iova, size_t size)
+static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova,
+			      int gfp_order)
 {
+	return -ENODEV;
 }
 
 static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index a38d6bd6fde..fc33af91185 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -492,6 +492,13 @@ static inline void tracing_off(void) { }
 static inline void tracing_off_permanent(void) { }
 static inline int tracing_is_on(void) { return 0; }
 #endif
+
+enum ftrace_dump_mode {
+	DUMP_NONE,
+	DUMP_ALL,
+	DUMP_ORIG,
+};
+
 #ifdef CONFIG_TRACING
 extern void tracing_start(void);
 extern void tracing_stop(void);
@@ -573,7 +580,7 @@ __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
 extern int
 __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
 
-extern void ftrace_dump(void);
+extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
 #else
 static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
@@ -594,7 +601,7 @@ ftrace_vprintk(const char *fmt, va_list ap)
 {
 	return 0;
 }
-static inline void ftrace_dump(void) { }
+static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 #endif /* CONFIG_TRACING */
 
 /*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 462acaf36f3..fb19bb92b80 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,7 +19,6 @@ struct anon_vma;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
-struct rlimit;
 
 #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
@@ -1449,9 +1448,6 @@ int vmemmap_populate_basepages(struct page *start_page,
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 
-extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
-				 size_t size);
-extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 55f1f9c9506..007fbaafead 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -500,4 +500,13 @@ struct mdio_device_id {
 	__u32 phy_id_mask;
 };
 
+struct zorro_device_id {
+	__u32 id;			/* Device ID or ZORRO_WILDCARD */
+	kernel_ulong_t driver_data;	/* Data private to the driver */
+};
+
+#define ZORRO_WILDCARD			(0xffffffff)	/* not official */
+
+#define ZORRO_DEVICE_MODALIAS_FMT	"zorro:i%08X"
+
 #endif /* LINUX_MOD_DEVICETABLE_H */
diff --git a/include/linux/module.h b/include/linux/module.h
index 515d53ae6a7..6914fcad467 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -465,8 +465,7 @@ static inline void __module_get(struct module *module)
 	if (module) {
 		preempt_disable();
 		__this_cpu_inc(module->refptr->incs);
-		trace_module_get(module, _THIS_IP_,
-				 __this_cpu_read(module->refptr->incs));
+		trace_module_get(module, _THIS_IP_);
 		preempt_enable();
 	}
 }
@@ -480,8 +479,7 @@ static inline int try_module_get(struct module *module)
 
 		if (likely(module_is_live(module))) {
 			__this_cpu_inc(module->refptr->incs);
-			trace_module_get(module, _THIS_IP_,
-				__this_cpu_read(module->refptr->incs));
+			trace_module_get(module, _THIS_IP_);
 		} else
 			ret = 0;
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c8e37544040..3fd5c82e0e1 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -203,8 +203,19 @@ struct perf_event_attr {
 				enable_on_exec :  1, /* next exec enables     */
 				task           :  1, /* trace fork/exit       */
 				watermark      :  1, /* wakeup_watermark      */
-
-				__reserved_1   : 49;
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+
+				__reserved_1   : 47;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -287,11 +298,24 @@ struct perf_event_mmap_page {
 	__u64	data_tail;		/* user-space written tail */
 };
 
-#define PERF_RECORD_MISC_CPUMODE_MASK		(3 << 0)
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
 #define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
 #define PERF_RECORD_MISC_KERNEL			(1 << 0)
 #define PERF_RECORD_MISC_USER			(2 << 0)
 #define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
 
 struct perf_event_header {
 	__u32	type;
@@ -439,6 +463,12 @@ enum perf_callchain_context {
 # include <asm/perf_event.h>
 #endif
 
+struct perf_guest_info_callbacks {
+	int (*is_in_guest) (void);
+	int (*is_user_mode) (void);
+	unsigned long (*get_guest_ip) (void);
+};
+
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 #include <asm/hw_breakpoint.h>
 #endif
@@ -468,6 +498,17 @@ struct perf_raw_record {
 	void				*data;
 };
 
+struct perf_branch_entry {
+	__u64				from;
+	__u64				to;
+	__u64				flags;
+};
+
+struct perf_branch_stack {
+	__u64				nr;
+	struct perf_branch_entry	entries[0];
+};
+
 struct task_struct;
 
 /**
@@ -506,6 +547,8 @@ struct hw_perf_event {
 
 struct perf_event;
 
+#define PERF_EVENT_TXN_STARTED 1
+
 /**
  * struct pmu - generic performance monitoring unit
  */
@@ -516,6 +559,16 @@ struct pmu {
 	void (*stop)			(struct perf_event *event);
 	void (*read)			(struct perf_event *event);
 	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
+	 */
+
+	void (*start_txn)	(const struct pmu *pmu);
+	void (*cancel_txn)	(const struct pmu *pmu);
+	int  (*commit_txn)	(const struct pmu *pmu);
 };
 
 /**
@@ -571,6 +624,14 @@ enum perf_group_flag {
 	PERF_GROUP_SOFTWARE = 0x1,
 };
 
+#define SWEVENT_HLIST_BITS	8
+#define SWEVENT_HLIST_SIZE	(1 << SWEVENT_HLIST_BITS)
+
+struct swevent_hlist {
+	struct hlist_head	heads[SWEVENT_HLIST_SIZE];
+	struct rcu_head		rcu_head;
+};
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -579,6 +640,7 @@ struct perf_event {
 	struct list_head		group_entry;
 	struct list_head		event_entry;
 	struct list_head		sibling_list;
+	struct hlist_node		hlist_entry;
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
@@ -726,6 +788,9 @@ struct perf_cpu_context {
 	int				active_oncpu;
 	int				max_pertask;
 	int				exclusive;
+	struct swevent_hlist		*swevent_hlist;
+	struct mutex			hlist_mutex;
+	int				hlist_refcount;
 
 	/*
 	 * Recursion avoidance:
@@ -769,9 +834,6 @@ extern void perf_disable(void);
 extern void perf_enable(void);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
-extern int hw_perf_group_sched_in(struct perf_event *group_leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx);
 extern void perf_event_update_userpage(struct perf_event *event);
 extern int perf_event_release_kernel(struct perf_event *event);
 extern struct perf_event *
@@ -902,6 +964,10 @@ static inline void perf_event_mmap(struct vm_area_struct *vma)
 		__perf_event_mmap(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);
+
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
@@ -971,6 +1037,11 @@ perf_sw_event(u32 event_id, u64 nr, int nmi,
 static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
+static inline int perf_register_guest_info_callbacks
+(struct perf_guest_info_callbacks *callbacks) { return 0; }
+static inline int perf_unregister_guest_info_callbacks
+(struct perf_guest_info_callbacks *callbacks) { return 0; }
+
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
 static inline void perf_event_comm(struct task_struct *tsk)		{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 212da17d06a..5417944d368 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -44,12 +44,14 @@ extern int platform_get_irq_byname(struct platform_device *, const char *);
 extern int platform_add_devices(struct platform_device **, int);
 
 extern struct platform_device *platform_device_register_simple(const char *, int id,
-					struct resource *, unsigned int);
+					const struct resource *, unsigned int);
 extern struct platform_device *platform_device_register_data(struct device *,
 		const char *, int, const void *, size_t);
 
 extern struct platform_device *platform_device_alloc(const char *name, int id);
-extern int platform_device_add_resources(struct platform_device *pdev, struct resource *res, unsigned int num);
+extern int platform_device_add_resources(struct platform_device *pdev,
+					 const struct resource *res,
+					 unsigned int num);
 extern int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size);
 extern int platform_device_add(struct platform_device *pdev);
 extern void platform_device_del(struct platform_device *pdev);
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index e1fb6072997..4272521e29e 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -345,18 +345,6 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
 #define arch_ptrace_stop(code, info)		do { } while (0)
 #endif
 
-#ifndef arch_ptrace_untrace
-/*
- * Do machine-specific work before untracing child.
- *
- * This is called for a normal detach as well as from ptrace_exit()
- * when the tracing task dies.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-#define arch_ptrace_untrace(task)		do { } while (0)
-#endif
-
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 5210a5c6087..fe1872e5b37 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -110,6 +110,7 @@ struct rb_node
 struct rb_root
 {
 	struct rb_node *rb_node;
+	void (*augment_cb)(struct rb_node *node);
 };
 
 
@@ -129,7 +130,9 @@ static inline void rb_set_color(struct rb_node *rb, int color)
 	rb->rb_parent_color = (rb->rb_parent_color & ~1) | color;
 }
 
-#define RB_ROOT	(struct rb_root) { NULL, }
+#define RB_ROOT	(struct rb_root) { NULL, NULL, }
+#define RB_AUGMENT_ROOT(x)	(struct rb_root) { NULL, x}
+
 #define	rb_entry(ptr, type, member) container_of(ptr, type, member)
 
 #define RB_EMPTY_ROOT(root)	((root)->rb_node == NULL)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index db266bbed23..b653b4aaa8a 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -56,8 +56,6 @@ struct rcu_head {
 };
 
 /* Exported common interfaces */
-extern void synchronize_rcu_bh(void);
-extern void synchronize_sched(void);
 extern void rcu_barrier(void);
 extern void rcu_barrier_bh(void);
 extern void rcu_barrier_sched(void);
@@ -66,8 +64,6 @@ extern int sched_expedited_torture_stats(char *page);
 
 /* Internal to kernel */
 extern void rcu_init(void);
-extern int rcu_scheduler_active;
-extern void rcu_scheduler_starting(void);
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
@@ -83,6 +79,14 @@ extern void rcu_scheduler_starting(void);
        (ptr)->next = NULL; (ptr)->func = NULL; \
 } while (0)
 
+static inline void init_rcu_head_on_stack(struct rcu_head *head)
+{
+}
+
+static inline void destroy_rcu_head_on_stack(struct rcu_head *head)
+{
+}
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 extern struct lockdep_map rcu_lock_map;
@@ -106,12 +110,13 @@ extern int debug_lockdep_rcu_enabled(void);
 /**
  * rcu_read_lock_held - might we be in RCU read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an RCU read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
+ * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
  * this assumes we are in an RCU read-side critical section unless it can
  * prove otherwise.
  *
- * Check rcu_scheduler_active to prevent false positives during boot.
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
  */
 static inline int rcu_read_lock_held(void)
 {
@@ -129,13 +134,15 @@ extern int rcu_read_lock_bh_held(void);
 /**
  * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in an
- * RCU-sched read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
- * this assumes we are in an RCU-sched read-side critical section unless it
- * can prove otherwise.  Note that disabling of preemption (including
- * disabling irqs) counts as an RCU-sched read-side critical section.
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * RCU-sched read-side critical section.  In absence of
+ * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
+ * critical section unless it can prove otherwise.  Note that disabling
+ * of preemption (including disabling irqs) counts as an RCU-sched
+ * read-side critical section.
  *
- * Check rcu_scheduler_active to prevent false positives during boot.
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
  */
 #ifdef CONFIG_PREEMPT
 static inline int rcu_read_lock_sched_held(void)
@@ -177,7 +184,7 @@ static inline int rcu_read_lock_bh_held(void)
 #ifdef CONFIG_PREEMPT
 static inline int rcu_read_lock_sched_held(void)
 {
-	return !rcu_scheduler_active || preempt_count() != 0 || irqs_disabled();
+	return preempt_count() != 0 || irqs_disabled();
 }
 #else /* #ifdef CONFIG_PREEMPT */
 static inline int rcu_read_lock_sched_held(void)
@@ -192,6 +199,15 @@ static inline int rcu_read_lock_sched_held(void)
 
 extern int rcu_my_thread_group_empty(void);
 
+#define __do_rcu_dereference_check(c)					\
+	do {								\
+		static bool __warned;					\
+		if (debug_lockdep_rcu_enabled() && !__warned && !(c)) {	\
+			__warned = true;				\
+			lockdep_rcu_dereference(__FILE__, __LINE__);	\
+		}							\
+	} while (0)
+
 /**
  * rcu_dereference_check - rcu_dereference with debug checking
  * @p: The pointer to read, prior to dereferencing
@@ -221,8 +237,7 @@ extern int rcu_my_thread_group_empty(void);
  */
 #define rcu_dereference_check(p, c) \
 	({ \
-		if (debug_lockdep_rcu_enabled() && !(c)) \
-			lockdep_rcu_dereference(__FILE__, __LINE__); \
+		__do_rcu_dereference_check(c); \
 		rcu_dereference_raw(p); \
 	})
 
@@ -239,8 +254,7 @@ extern int rcu_my_thread_group_empty(void);
  */
 #define rcu_dereference_protected(p, c) \
 	({ \
-		if (debug_lockdep_rcu_enabled() && !(c)) \
-			lockdep_rcu_dereference(__FILE__, __LINE__); \
+		__do_rcu_dereference_check(c); \
 		(p); \
 	})
 
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index a5195875480..e2e893144a8 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -29,6 +29,10 @@
 
 void rcu_sched_qs(int cpu);
 void rcu_bh_qs(int cpu);
+static inline void rcu_note_context_switch(int cpu)
+{
+	rcu_sched_qs(cpu);
+}
 
 #define __rcu_read_lock()	preempt_disable()
 #define __rcu_read_unlock()	preempt_enable()
@@ -60,8 +64,6 @@ static inline long rcu_batches_completed_bh(void)
 	return 0;
 }
 
-extern int rcu_expedited_torture_stats(char *page);
-
 static inline void rcu_force_quiescent_state(void)
 {
 }
@@ -74,7 +76,17 @@ static inline void rcu_sched_force_quiescent_state(void)
 {
 }
 
-#define synchronize_rcu synchronize_sched
+extern void synchronize_sched(void);
+
+static inline void synchronize_rcu(void)
+{
+	synchronize_sched();
+}
+
+static inline void synchronize_rcu_bh(void)
+{
+	synchronize_sched();
+}
 
 static inline void synchronize_rcu_expedited(void)
 {
@@ -114,4 +126,17 @@ static inline int rcu_preempt_depth(void)
 	return 0;
 }
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+extern int rcu_scheduler_active __read_mostly;
+extern void rcu_scheduler_starting(void);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+static inline void rcu_scheduler_starting(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 42cc3a04779..c0ed1c056f2 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -34,8 +34,8 @@ struct notifier_block;
 
 extern void rcu_sched_qs(int cpu);
 extern void rcu_bh_qs(int cpu);
+extern void rcu_note_context_switch(int cpu);
 extern int rcu_needs_cpu(int cpu);
-extern int rcu_expedited_torture_stats(char *page);
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
@@ -86,6 +86,8 @@ static inline void __rcu_read_unlock_bh(void)
 
 extern void call_rcu_sched(struct rcu_head *head,
 			   void (*func)(struct rcu_head *rcu));
+extern void synchronize_rcu_bh(void);
+extern void synchronize_sched(void);
 extern void synchronize_rcu_expedited(void);
 
 static inline void synchronize_rcu_bh_expedited(void)
@@ -120,4 +122,7 @@ static inline int rcu_blocking_is_gp(void)
 	return num_online_cpus() == 1;
 }
 
+extern void rcu_scheduler_starting(void);
+extern int rcu_scheduler_active __read_mostly;
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 5fcc31ed577..25b4f686d91 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -120,12 +120,16 @@ 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);
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
+		 unsigned long *lost_events);
 struct ring_buffer_event *
-ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts);
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
+		    unsigned long *lost_events);
 
 struct ring_buffer_iter *
-ring_buffer_read_start(struct ring_buffer *buffer, int cpu);
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu);
+void ring_buffer_read_prepare_sync(void);
+void ring_buffer_read_start(struct ring_buffer_iter *iter);
 void ring_buffer_read_finish(struct ring_buffer_iter *iter);
 
 struct ring_buffer_event *
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2b7b81df78b..b55e988988b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -99,7 +99,6 @@ struct futex_pi_state;
 struct robust_list_head;
 struct bio_list;
 struct fs_struct;
-struct bts_context;
 struct perf_event_context;
 
 /*
@@ -275,11 +274,17 @@ 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 int nohz_ratelimit(int cpu);
 #else
 static inline int select_nohz_load_balancer(int cpu)
 {
 	return 0;
 }
+
+static inline int nohz_ratelimit(int cpu)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -954,6 +959,7 @@ struct sched_domain {
 	char *name;
 #endif
 
+	unsigned int span_weight;
 	/*
 	 * Span of all CPUs in this domain.
 	 *
@@ -1026,12 +1032,17 @@ struct sched_domain;
 #define WF_SYNC		0x01		/* waker goes to sleep after wakup */
 #define WF_FORK		0x02		/* child wakeup after fork */
 
+#define ENQUEUE_WAKEUP		1
+#define ENQUEUE_WAKING		2
+#define ENQUEUE_HEAD		4
+
+#define DEQUEUE_SLEEP		1
+
 struct sched_class {
 	const struct sched_class *next;
 
-	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup,
-			      bool head);
-	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
+	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
+	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task) (struct rq *rq);
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
@@ -1040,7 +1051,8 @@ struct sched_class {
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
+	int  (*select_task_rq)(struct rq *rq, struct task_struct *p,
+			       int sd_flag, int flags);
 
 	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
@@ -1077,36 +1089,8 @@ struct load_weight {
 	unsigned long weight, inv_weight;
 };
 
-/*
- * CFS stats for a schedulable entity (task, task-group etc)
- *
- * Current field usage histogram:
- *
- *     4 se->block_start
- *     4 se->run_node
- *     4 se->sleep_start
- *     6 se->load.weight
- */
-struct sched_entity {
-	struct load_weight	load;		/* for load-balancing */
-	struct rb_node		run_node;
-	struct list_head	group_node;
-	unsigned int		on_rq;
-
-	u64			exec_start;
-	u64			sum_exec_runtime;
-	u64			vruntime;
-	u64			prev_sum_exec_runtime;
-
-	u64			last_wakeup;
-	u64			avg_overlap;
-
-	u64			nr_migrations;
-
-	u64			start_runtime;
-	u64			avg_wakeup;
-
 #ifdef CONFIG_SCHEDSTATS
+struct sched_statistics {
 	u64			wait_start;
 	u64			wait_max;
 	u64			wait_count;
@@ -1138,6 +1122,24 @@ struct sched_entity {
 	u64			nr_wakeups_affine_attempts;
 	u64			nr_wakeups_passive;
 	u64			nr_wakeups_idle;
+};
+#endif
+
+struct sched_entity {
+	struct load_weight	load;		/* for load-balancing */
+	struct rb_node		run_node;
+	struct list_head	group_node;
+	unsigned int		on_rq;
+
+	u64			exec_start;
+	u64			sum_exec_runtime;
+	u64			vruntime;
+	u64			prev_sum_exec_runtime;
+
+	u64			nr_migrations;
+
+#ifdef CONFIG_SCHEDSTATS
+	struct sched_statistics statistics;
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1272,12 +1274,6 @@ struct task_struct {
 	struct list_head ptraced;
 	struct list_head ptrace_entry;
 
-	/*
-	 * This is the tracer handle for the ptrace BTS extension.
-	 * This field actually belongs to the ptracer task.
-	 */
-	struct bts_context *bts;
-
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
@@ -1846,6 +1842,7 @@ extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 
 #ifdef CONFIG_HOTPLUG_CPU
+extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p);
 extern void idle_task_exit(void);
 #else
 static inline void idle_task_exit(void) {}
@@ -2122,10 +2119,8 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
-extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
-static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 4d5ecb222af..4d5d2f546db 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -27,6 +27,8 @@
 #ifndef _LINUX_SRCU_H
 #define _LINUX_SRCU_H
 
+#include <linux/mutex.h>
+
 struct srcu_struct_array {
 	int c[2];
 };
@@ -84,8 +86,8 @@ long srcu_batches_completed(struct srcu_struct *sp);
 /**
  * srcu_read_lock_held - might we be in SRCU read-side critical section?
  *
- * If CONFIG_PROVE_LOCKING is selected and enabled, returns nonzero iff in
- * an SRCU read-side critical section.  In absence of CONFIG_PROVE_LOCKING,
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU
+ * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
  * this assumes we are in an SRCU read-side critical section unless it can
  * prove otherwise.
  */
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index baba3a23a81..6b524a0d02e 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -1,13 +1,101 @@
 #ifndef _LINUX_STOP_MACHINE
 #define _LINUX_STOP_MACHINE
-/* "Bogolock": stop the entire machine, disable interrupts.  This is a
-   very heavy lock, which is equivalent to grabbing every spinlock
-   (and more).  So the "read" side to such a lock is anything which
-   disables preeempt. */
+
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
+#include <linux/list.h>
 #include <asm/system.h>
 
+/*
+ * stop_cpu[s]() is simplistic per-cpu maximum priority cpu
+ * monopolization mechanism.  The caller can specify a non-sleeping
+ * function to be executed on a single or multiple cpus preempting all
+ * other processes and monopolizing those cpus until it finishes.
+ *
+ * Resources for this mechanism are preallocated when a cpu is brought
+ * up and requests are guaranteed to be served as long as the target
+ * cpus are online.
+ */
+typedef int (*cpu_stop_fn_t)(void *arg);
+
+#ifdef CONFIG_SMP
+
+struct cpu_stop_work {
+	struct list_head	list;		/* cpu_stopper->works */
+	cpu_stop_fn_t		fn;
+	void			*arg;
+	struct cpu_stop_done	*done;
+};
+
+int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
+void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
+			 struct cpu_stop_work *work_buf);
+int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
+int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
+
+#else	/* CONFIG_SMP */
+
+#include <linux/workqueue.h>
+
+struct cpu_stop_work {
+	struct work_struct	work;
+	cpu_stop_fn_t		fn;
+	void			*arg;
+};
+
+static inline int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
+{
+	int ret = -ENOENT;
+	preempt_disable();
+	if (cpu == smp_processor_id())
+		ret = fn(arg);
+	preempt_enable();
+	return ret;
+}
+
+static void stop_one_cpu_nowait_workfn(struct work_struct *work)
+{
+	struct cpu_stop_work *stwork =
+		container_of(work, struct cpu_stop_work, work);
+	preempt_disable();
+	stwork->fn(stwork->arg);
+	preempt_enable();
+}
+
+static inline void stop_one_cpu_nowait(unsigned int cpu,
+				       cpu_stop_fn_t fn, void *arg,
+				       struct cpu_stop_work *work_buf)
+{
+	if (cpu == smp_processor_id()) {
+		INIT_WORK(&work_buf->work, stop_one_cpu_nowait_workfn);
+		work_buf->fn = fn;
+		work_buf->arg = arg;
+		schedule_work(&work_buf->work);
+	}
+}
+
+static inline int stop_cpus(const struct cpumask *cpumask,
+			    cpu_stop_fn_t fn, void *arg)
+{
+	if (cpumask_test_cpu(raw_smp_processor_id(), cpumask))
+		return stop_one_cpu(raw_smp_processor_id(), fn, arg);
+	return -ENOENT;
+}
+
+static inline int try_stop_cpus(const struct cpumask *cpumask,
+				cpu_stop_fn_t fn, void *arg)
+{
+	return stop_cpus(cpumask, fn, arg);
+}
+
+#endif	/* CONFIG_SMP */
+
+/*
+ * stop_machine "Bogolock": stop the entire machine, disable
+ * interrupts.  This is a very heavy lock, which is equivalent to
+ * grabbing every spinlock (and more).  So the "read" side to such a
+ * lock is anything which disables preeempt.
+ */
 #if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP)
 
 /**
@@ -36,24 +124,7 @@ int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
  */
 int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
 
-/**
- * stop_machine_create: create all stop_machine threads
- *
- * Description: This causes all stop_machine threads to be created before
- * stop_machine actually gets called. This can be used by subsystems that
- * need a non failing stop_machine infrastructure.
- */
-int stop_machine_create(void);
-
-/**
- * stop_machine_destroy: destroy all stop_machine threads
- *
- * Description: This causes all stop_machine threads which were created with
- * stop_machine_create to be destroyed again.
- */
-void stop_machine_destroy(void);
-
-#else
+#else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
 
 static inline int stop_machine(int (*fn)(void *), void *data,
 			       const struct cpumask *cpus)
@@ -65,8 +136,5 @@ static inline int stop_machine(int (*fn)(void *), void *data,
 	return ret;
 }
 
-static inline int stop_machine_create(void) { return 0; }
-static inline void stop_machine_destroy(void) { }
-
-#endif /* CONFIG_SMP */
-#endif /* _LINUX_STOP_MACHINE */
+#endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#endif	/* _LINUX_STOP_MACHINE */
diff --git a/include/linux/tick.h b/include/linux/tick.h
index d2ae79e21be..b232ccc0ee2 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -42,6 +42,7 @@ enum tick_nohz_mode {
  * @idle_waketime:	Time when the idle was interrupted
  * @idle_exittime:	Time when the idle state was left
  * @idle_sleeptime:	Sum of the time slept in idle with sched tick stopped
+ * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
  * @sleep_length:	Duration of the current idle sleep
  * @do_timer_lst:	CPU was the last one doing do_timer before going idle
  */
@@ -60,7 +61,7 @@ struct tick_sched {
 	ktime_t				idle_waketime;
 	ktime_t				idle_exittime;
 	ktime_t				idle_sleeptime;
-	ktime_t				idle_lastupdate;
+	ktime_t				iowait_sleeptime;
 	ktime_t				sleep_length;
 	unsigned long			last_jiffies;
 	unsigned long			next_jiffies;
@@ -124,6 +125,7 @@ extern void tick_nohz_stop_sched_tick(int inidle);
 extern void tick_nohz_restart_sched_tick(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
+extern u64 get_cpu_iowait_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) { }
@@ -134,6 +136,7 @@ static inline ktime_t tick_nohz_get_sleep_length(void)
 	return len;
 }
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
+static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 # endif /* !NO_HZ */
 
 #endif
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 78b4bd3be49..1d85f9a6a19 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -33,6 +33,65 @@ struct tracepoint {
 					 * Keep in sync with vmlinux.lds.h.
 					 */
 
+/*
+ * 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);
+
+extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
+extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
+extern void tracepoint_probe_update_all(void);
+
+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();
+}
+
+#define PARAMS(args...) args
+
+#ifdef CONFIG_TRACEPOINTS
+extern void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end);
+#else
+static inline void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end)
+{ }
+#endif /* CONFIG_TRACEPOINTS */
+
+#endif /* _LINUX_TRACEPOINT_H */
+
+/*
+ * Note: we keep the TRACE_EVENT and DECLARE_TRACE outside the include
+ *  file ifdef protection.
+ *  This is due to the way trace events work. If a file includes two
+ *  trace event headers under one "CREATE_TRACE_POINTS" the first include
+ *  will override the TRACE_EVENT and break the second include.
+ */
+
 #ifndef DECLARE_TRACE
 
 #define TP_PROTO(args...)	args
@@ -96,9 +155,6 @@ struct tracepoint {
 #define EXPORT_TRACEPOINT_SYMBOL(name)					\
 	EXPORT_SYMBOL(__tracepoint_##name)
 
-extern void tracepoint_update_probe_range(struct tracepoint *begin,
-	struct tracepoint *end);
-
 #else /* !CONFIG_TRACEPOINTS */
 #define DECLARE_TRACE(name, proto, args)				\
 	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
@@ -119,61 +175,9 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin,
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)
 
-static inline void tracepoint_update_probe_range(struct tracepoint *begin,
-	struct tracepoint *end)
-{ }
 #endif /* CONFIG_TRACEPOINTS */
 #endif /* DECLARE_TRACE */
 
-/*
- * 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);
-
-extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
-extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
-extern void tracepoint_probe_update_all(void);
-
-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();
-}
-
-#define PARAMS(args...) args
-
-#endif /* _LINUX_TRACEPOINT_H */
-
-/*
- * Note: we keep the TRACE_EVENT outside the include file ifdef protection.
- *  This is due to the way trace events work. If a file includes two
- *  trace event headers under one "CREATE_TRACE_POINTS" the first include
- *  will override the TRACE_EVENT and break the second include.
- */
-
 #ifndef TRACE_EVENT
 /*
  * For use with the TRACE_EVENT macro:
diff --git a/include/linux/types.h b/include/linux/types.h
index c42724f8c80..23d237a075e 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -188,12 +188,12 @@ typedef u32 phys_addr_t;
 typedef phys_addr_t resource_size_t;
 
 typedef struct {
-	volatile int counter;
+	int counter;
 } atomic_t;
 
 #ifdef CONFIG_64BIT
 typedef struct {
-	volatile long counter;
+	long counter;
 } atomic64_t;
 #endif
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index a48e16b77d5..76d96d035ea 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -127,12 +127,26 @@ static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new)
 /*
  * Used for wake-one threads:
  */
+static inline void __add_wait_queue_exclusive(wait_queue_head_t *q,
+					      wait_queue_t *wait)
+{
+	wait->flags |= WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue(q, wait);
+}
+
 static inline void __add_wait_queue_tail(wait_queue_head_t *head,
-						wait_queue_t *new)
+					 wait_queue_t *new)
 {
 	list_add_tail(&new->task_list, &head->task_list);
 }
 
+static inline void __add_wait_queue_tail_exclusive(wait_queue_head_t *q,
+					      wait_queue_t *wait)
+{
+	wait->flags |= WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue_tail(q, wait);
+}
+
 static inline void __remove_wait_queue(wait_queue_head_t *head,
 							wait_queue_t *old)
 {
@@ -404,25 +418,6 @@ do {									\
 })
 
 /*
- * Must be called with the spinlock in the wait_queue_head_t held.
- */
-static inline void add_wait_queue_exclusive_locked(wait_queue_head_t *q,
-						   wait_queue_t * wait)
-{
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	__add_wait_queue_tail(q,  wait);
-}
-
-/*
- * Must be called with the spinlock in the wait_queue_head_t held.
- */
-static inline void remove_wait_queue_locked(wait_queue_head_t *q,
-					    wait_queue_t * wait)
-{
-	__remove_wait_queue(q,  wait);
-}
-
-/*
  * These are the old interfaces to sleep waiting for an event.
  * They are racy.  DO NOT use them, use the wait_event* interfaces above.
  * We plan to remove these interfaces.
diff --git a/include/linux/zorro.h b/include/linux/zorro.h
index 913bfc226dd..7bf9db525e9 100644
--- a/include/linux/zorro.h
+++ b/include/linux/zorro.h
@@ -38,8 +38,6 @@
 typedef __u32 zorro_id;
 
 
-#define ZORRO_WILDCARD		(0xffffffff)	/* not official */
-
 /* Include the ID list */
 #include <linux/zorro_ids.h>
 
@@ -116,6 +114,7 @@ struct ConfigDev {
 
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/mod_devicetable.h>
 
 #include <asm/zorro.h>
 
@@ -142,29 +141,10 @@ struct zorro_dev {
      *  Zorro bus
      */
 
-struct zorro_bus {
-    struct list_head devices;		/* list of devices on this bus */
-    unsigned int num_resources;		/* number of resources */
-    struct resource resources[4];	/* address space routed to this bus */
-    struct device dev;
-    char name[10];
-};
-
-extern struct zorro_bus zorro_bus;	/* single Zorro bus */
 extern struct bus_type zorro_bus_type;
 
 
     /*
-     *  Zorro device IDs
-     */
-
-struct zorro_device_id {
-	zorro_id id;			/* Device ID or ZORRO_WILDCARD */
-	unsigned long driver_data;	/* Data private to the driver */
-};
-
-
-    /*
      *  Zorro device drivers
      */
 
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index 5acfb1eb4df..1dfab540151 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -65,6 +65,10 @@
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+/* Make all open coded DECLARE_TRACE nops */
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)
+
 #ifdef CONFIG_EVENT_TRACING
 #include <trace/ftrace.h>
 #endif
@@ -75,6 +79,7 @@
 #undef DEFINE_EVENT
 #undef DEFINE_EVENT_PRINT
 #undef TRACE_HEADER_MULTI_READ
+#undef DECLARE_TRACE
 
 /* Only undef what we defined in this file */
 #ifdef UNDEF_TRACE_INCLUDE_FILE
diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index 5c1dcfc16c6..2821b86de63 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -35,15 +35,15 @@ TRACE_EVENT(lock_acquire,
 		  __get_str(name))
 );
 
-TRACE_EVENT(lock_release,
+DECLARE_EVENT_CLASS(lock,
 
-	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_ARGS(lock, nested, ip),
+	TP_ARGS(lock, ip),
 
 	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(void *, lockdep_addr)
+		__string(	name, 	lock->name	)
+		__field(	void *, lockdep_addr	)
 	),
 
 	TP_fast_assign(
@@ -51,51 +51,30 @@ TRACE_EVENT(lock_release,
 		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%p %s",
-		  __entry->lockdep_addr, __get_str(name))
+	TP_printk("%p %s",  __entry->lockdep_addr, __get_str(name))
 );
 
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_EVENT(lock_contended,
+DEFINE_EVENT(lock, lock_release,
 
 	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_ARGS(lock, ip),
+	TP_ARGS(lock, ip)
+);
 
-	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(void *, lockdep_addr)
-	),
+#ifdef CONFIG_LOCK_STAT
 
-	TP_fast_assign(
-		__assign_str(name, lock->name);
-		__entry->lockdep_addr = lock;
-	),
+DEFINE_EVENT(lock, lock_contended,
 
-	TP_printk("%p %s",
-		  __entry->lockdep_addr, __get_str(name))
-);
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-TRACE_EVENT(lock_acquired,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+	TP_ARGS(lock, ip)
+);
 
-	TP_ARGS(lock, ip, waittime),
+DEFINE_EVENT(lock, lock_acquired,
 
-	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(s64, wait_nsec)
-		__field(void *, lockdep_addr)
-	),
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_fast_assign(
-		__assign_str(name, lock->name);
-		__entry->wait_nsec = waittime;
-		__entry->lockdep_addr = lock;
-	),
-	TP_printk("%p %s (%llu ns)", __entry->lockdep_addr,
-		  __get_str(name),
-		  __entry->wait_nsec)
+	TP_ARGS(lock, ip)
 );
 
 #endif
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 4b0f48ba16a..c7bb2f0482f 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -51,11 +51,14 @@ TRACE_EVENT(module_free,
 	TP_printk("%s", __get_str(name))
 );
 
+#ifdef CONFIG_MODULE_UNLOAD
+/* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */
+
 DECLARE_EVENT_CLASS(module_refcnt,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt),
+	TP_ARGS(mod, ip),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	ip		)
@@ -65,7 +68,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= refcnt;
+		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
 		__assign_str(name, mod->name);
 	),
 
@@ -75,17 +78,18 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 DEFINE_EVENT(module_refcnt, module_get,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
 
 DEFINE_EVENT(module_refcnt, module_put,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
+#endif /* CONFIG_MODULE_UNLOAD */
 
 TRACE_EVENT(module_request,
 
diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
index a8989c4547e..188deca2f3c 100644
--- a/include/trace/events/napi.h
+++ b/include/trace/events/napi.h
@@ -1,4 +1,7 @@
-#ifndef _TRACE_NAPI_H_
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM napi
+
+#if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_NAPI_H_
 
 #include <linux/netdevice.h>
@@ -8,4 +11,7 @@ DECLARE_TRACE(napi_poll,
 	TP_PROTO(struct napi_struct *napi),
 	TP_ARGS(napi));
 
-#endif
+#endif /* _TRACE_NAPI_H_ */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index cfceb0b73e2..4f733ecea46 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -51,15 +51,12 @@ TRACE_EVENT(sched_kthread_stop_ret,
 
 /*
  * Tracepoint for waiting on task to unschedule:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 TRACE_EVENT(sched_wait_task,
 
-	TP_PROTO(struct rq *rq, struct task_struct *p),
+	TP_PROTO(struct task_struct *p),
 
-	TP_ARGS(rq, p),
+	TP_ARGS(p),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -79,15 +76,12 @@ TRACE_EVENT(sched_wait_task,
 
 /*
  * Tracepoint for waking up a task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
 
-	TP_PROTO(struct rq *rq, struct task_struct *p, int success),
+	TP_PROTO(struct task_struct *p, int success),
 
-	TP_ARGS(rq, p, success),
+	TP_ARGS(p, success),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -111,31 +105,25 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 );
 
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
-	     TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-	     TP_ARGS(rq, p, success));
+	     TP_PROTO(struct task_struct *p, int success),
+	     TP_ARGS(p, success));
 
 /*
  * Tracepoint for waking up a new task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
-	     TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-	     TP_ARGS(rq, p, success));
+	     TP_PROTO(struct task_struct *p, int success),
+	     TP_ARGS(p, success));
 
 /*
  * Tracepoint for task switches, performed by the scheduler:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 TRACE_EVENT(sched_switch,
 
-	TP_PROTO(struct rq *rq, struct task_struct *prev,
+	TP_PROTO(struct task_struct *prev,
 		 struct task_struct *next),
 
-	TP_ARGS(rq, prev, next),
+	TP_ARGS(prev, next),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h
index a510b75ac30..814566c99d2 100644
--- a/include/trace/events/signal.h
+++ b/include/trace/events/signal.h
@@ -100,18 +100,7 @@ TRACE_EVENT(signal_deliver,
 		  __entry->sa_handler, __entry->sa_flags)
 );
 
-/**
- * signal_overflow_fail - called when signal queue is overflow
- * @sig: signal number
- * @group: signal to process group or not (bool)
- * @info: pointer to struct siginfo
- *
- * Kernel fails to generate 'sig' signal with 'info' siginfo, because
- * siginfo queue is overflow, and the signal is dropped.
- * 'group' is not 0 if the signal will be sent to a process group.
- * 'sig' is always one of RT signals.
- */
-TRACE_EVENT(signal_overflow_fail,
+DECLARE_EVENT_CLASS(signal_queue_overflow,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 
@@ -135,6 +124,24 @@ TRACE_EVENT(signal_overflow_fail,
 );
 
 /**
+ * signal_overflow_fail - called when signal queue is overflow
+ * @sig: signal number
+ * @group: signal to process group or not (bool)
+ * @info: pointer to struct siginfo
+ *
+ * Kernel fails to generate 'sig' signal with 'info' siginfo, because
+ * siginfo queue is overflow, and the signal is dropped.
+ * 'group' is not 0 if the signal will be sent to a process group.
+ * 'sig' is always one of RT signals.
+ */
+DEFINE_EVENT(signal_queue_overflow, signal_overflow_fail,
+
+	TP_PROTO(int sig, int group, struct siginfo *info),
+
+	TP_ARGS(sig, group, info)
+);
+
+/**
  * signal_lose_info - called when siginfo is lost
  * @sig: signal number
  * @group: signal to process group or not (bool)
@@ -145,28 +152,13 @@ TRACE_EVENT(signal_overflow_fail,
  * 'group' is not 0 if the signal will be sent to a process group.
  * 'sig' is always one of non-RT signals.
  */
-TRACE_EVENT(signal_lose_info,
+DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 
-	TP_ARGS(sig, group, info),
-
-	TP_STRUCT__entry(
-		__field(	int,	sig	)
-		__field(	int,	group	)
-		__field(	int,	errno	)
-		__field(	int,	code	)
-	),
-
-	TP_fast_assign(
-		__entry->sig	= sig;
-		__entry->group	= group;
-		TP_STORE_SIGINFO(__entry, info);
-	),
-
-	TP_printk("sig=%d group=%d errno=%d code=%d",
-		  __entry->sig, __entry->group, __entry->errno, __entry->code)
+	TP_ARGS(sig, group, info)
 );
+
 #endif /* _TRACE_SIGNAL_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index ea6f9d4a20e..16253db38d7 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -154,9 +154,11 @@
  *
  *	field = (typeof(field))entry;
  *
- *	p = get_cpu_var(ftrace_event_seq);
+ *	p = &get_cpu_var(ftrace_event_seq);
  *	trace_seq_init(p);
- *	ret = trace_seq_printf(s, <TP_printk> "\n");
+ *	ret = trace_seq_printf(s, "%s: ", <call>);
+ *	if (ret)
+ *		ret = trace_seq_printf(s, <TP_printk> "\n");
  *	put_cpu();
  *	if (!ret)
  *		return TRACE_TYPE_PARTIAL_LINE;
@@ -450,38 +452,38 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *
  * static void ftrace_raw_event_<call>(proto)
  * {
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ring_buffer_event *event;
  *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
  *	struct ring_buffer *buffer;
  *	unsigned long irq_flags;
+ *	int __data_size;
  *	int pc;
  *
  *	local_save_flags(irq_flags);
  *	pc = preempt_count();
  *
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
  *	event = trace_current_buffer_lock_reserve(&buffer,
  *				  event_<call>.id,
- *				  sizeof(struct ftrace_raw_<call>),
+ *				  sizeof(*entry) + __data_size,
  *				  irq_flags, pc);
  *	if (!event)
  *		return;
  *	entry	= ring_buffer_event_data(event);
  *
- *	<assign>;  <-- Here we assign the entries by the __field and
- *			__array macros.
+ *	{ <assign>; }  <-- Here we assign the entries by the __field and
+ *			   __array macros.
  *
- *	trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ *	if (!filter_current_check_discard(buffer, event_call, entry, event))
+ *		trace_current_buffer_unlock_commit(buffer,
+ *						   event, irq_flags, pc);
  * }
  *
  * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
  * {
- *	int ret;
- *
- *	ret = register_trace_<call>(ftrace_raw_event_<call>);
- *	if (!ret)
- *		pr_info("event trace: Could not activate trace point "
- *			"probe to <call>");
- *	return ret;
+ *	return register_trace_<call>(ftrace_raw_event_<call>);
  * }
  *
  * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
@@ -493,6 +495,8 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *	.trace			= ftrace_raw_output_<call>, <-- stage 2
  * };
  *
+ * static const char print_fmt_<call>[] = <TP_printk>;
+ *
  * static struct ftrace_event_call __used
  * __attribute__((__aligned__(4)))
  * __attribute__((section("_ftrace_events"))) event_<call> = {
@@ -501,6 +505,8 @@ perf_trace_disable_##name(struct ftrace_event_call *unused)		\
  *	.raw_init		= trace_event_raw_init,
  *	.regfunc		= ftrace_reg_event_<call>,
  *	.unregfunc		= ftrace_unreg_event_<call>,
+ *	.print_fmt		= print_fmt_<call>,
+ *	.define_fields		= ftrace_define_fields_<call>,
  * }
  *
  */
@@ -569,7 +575,6 @@ ftrace_raw_event_id_##call(struct ftrace_event_call *event_call,	\
 		return;							\
 	entry	= ring_buffer_event_data(event);			\
 									\
-									\
 	tstruct								\
 									\
 	{ assign; }							\
@@ -758,13 +763,12 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static notrace void							\
 perf_trace_templ_##call(struct ftrace_event_call *event_call,		\
-			    proto)					\
+			struct pt_regs *__regs, proto)			\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
-	struct pt_regs *__regs;						\
 	int __entry_size;						\
 	int __data_size;						\
 	int rctx;							\
@@ -785,20 +789,22 @@ perf_trace_templ_##call(struct ftrace_event_call *event_call,		\
 									\
 	{ assign; }							\
 									\
-	__regs = &__get_cpu_var(perf_trace_regs);			\
-	perf_fetch_caller_regs(__regs, 2);				\
-									\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
 			       __count, irq_flags, __regs);		\
 }
 
 #undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args)		\
-static notrace void perf_trace_##call(proto)			\
-{								\
-	struct ftrace_event_call *event_call = &event_##call;	\
-								\
-	perf_trace_templ_##template(event_call, args);		\
+#define DEFINE_EVENT(template, call, proto, args)			\
+static notrace void perf_trace_##call(proto)				\
+{									\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	struct pt_regs *__regs = &get_cpu_var(perf_trace_regs);		\
+									\
+	perf_fetch_caller_regs(__regs, 1);				\
+									\
+	perf_trace_templ_##template(event_call, __regs, args);		\
+									\
+	put_cpu_var(perf_trace_regs);					\
 }
 
 #undef DEFINE_EVENT_PRINT