Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (162 commits)
  tracing/kprobes: unregister_trace_probe needs to be called under mutex
  perf: expose event__process function
  perf events: Fix mmap offset determination
  perf, powerpc: fsl_emb: Restore setting perf_sample_data.period
  perf, powerpc: Convert the FSL driver to use local64_t
  perf tools: Don't keep unreferenced maps when unmaps are detected
  perf session: Invalidate last_match when removing threads from rb_tree
  perf session: Free the ref_reloc_sym memory at the right place
  x86,mmiotrace: Add support for tracing STOS instruction
  perf, sched migration: Librarize task states and event headers helpers
  perf, sched migration: Librarize the GUI class
  perf, sched migration: Make the GUI class client agnostic
  perf, sched migration: Make it vertically scrollable
  perf, sched migration: Parameterize cpu height and spacing
  perf, sched migration: Fix key bindings
  perf, sched migration: Ignore unhandled task states
  perf, sched migration: Handle ignored migrate out events
  perf: New migration tool overview
  tracing: Drop cpparg() macro
  perf: Use tracepoint_synchronize_unregister() to flush any pending tracepoint call
  ...

Fix up trivial conflicts in Makefile and drivers/cpufreq/cpufreq.c

17 files changed, 228 insertions, 261 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/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 4e7ae6002056..8a92a170fb7d 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -156,10 +156,6 @@
 	CPU_KEEP(exit.data)						\
 	MEM_KEEP(init.data)						\
 	MEM_KEEP(exit.data)						\
-	. = ALIGN(8);							\
-	VMLINUX_SYMBOL(__start___markers) = .;				\
-	*(__markers)							\
-	VMLINUX_SYMBOL(__stop___markers) = .;				\
 	. = ALIGN(32);							\
 	VMLINUX_SYMBOL(__start___tracepoints) = .;			\
 	*(__tracepoints)						\
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 41e46330d9be..dcd6a7c3a435 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1,3 +1,8 @@
+/*
+ * Ftrace header.  For implementation details beyond the random comments
+ * scattered below, see: Documentation/trace/ftrace-design.txt
+ */
+
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 3167f2df4126..02b8b24f8f51 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -11,8 +11,6 @@ struct trace_array;
 struct tracer;
 struct dentry;
 
-DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq);
-
 struct trace_print_flags {
 	unsigned long		mask;
 	const char		*name;
@@ -58,6 +56,9 @@ struct trace_iterator {
 	struct ring_buffer_iter	*buffer_iter[NR_CPUS];
 	unsigned long		iter_flags;
 
+	/* trace_seq for __print_flags() and __print_symbolic() etc. */
+	struct trace_seq	tmp_seq;
+
 	/* The below is zeroed out in pipe_read */
 	struct trace_seq	seq;
 	struct trace_entry	*ent;
@@ -146,14 +147,19 @@ 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,
+	TRACE_EVENT_FL_RECORDED_CMD_BIT,
 };
 
 enum {
-	TRACE_EVENT_FL_ENABLED	= (1 << TRACE_EVENT_FL_ENABLED_BIT),
-	TRACE_EVENT_FL_FILTERED	= (1 << TRACE_EVENT_FL_FILTERED_BIT),
+	TRACE_EVENT_FL_ENABLED		= (1 << TRACE_EVENT_FL_ENABLED_BIT),
+	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
+	TRACE_EVENT_FL_RECORDED_CMD	= (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
 };
 
 struct ftrace_event_call {
@@ -171,6 +177,7 @@ struct ftrace_event_call {
 	 * 32 bit flags:
 	 *   bit 1:		enabled
 	 *   bit 2:		filter_active
+	 *   bit 3:		enabled cmd record
 	 *
 	 * Changes to flags must hold the event_mutex.
 	 *
@@ -257,8 +264,7 @@ 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/kernel.h b/include/linux/kernel.h
index 5de838b0fc1a..38e462e00594 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -513,9 +513,6 @@ extern void tracing_start(void);
 extern void tracing_stop(void);
 extern void ftrace_off_permanent(void);
 
-extern void
-ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
-
 static inline void __attribute__ ((format (printf, 1, 2)))
 ____trace_printk_check_format(const char *fmt, ...)
 {
@@ -591,8 +588,6 @@ __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
 
 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) { }
 static inline int
 trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
 
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..937495c25073 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
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0478888c6899..3992f50de614 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -316,20 +316,16 @@ 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)
 {
 }
@@ -2435,18 +2431,6 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_TRACING
-extern void
-__trace_special(void *__tr, void *__data,
-		unsigned long arg1, unsigned long arg2, unsigned long arg3);
-#else
-static inline void
-__trace_special(void *__tr, void *__data,
-		unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
-}
-#endif
-
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
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 13ebb5413a79..a6bfd1367d2a 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -167,7 +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)					\
@@ -182,7 +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/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..a9377c0083ad 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -75,15 +75,12 @@
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
 	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
 
-#undef __cpparg
-#define __cpparg(arg...) arg
-
 /* Callbacks are meaningless to ftrace. */
 #undef TRACE_EVENT_FN
 #define TRACE_EVENT_FN(name, proto, args, tstruct,			\
 		assign, print, reg, unreg)				\
-	TRACE_EVENT(name, __cpparg(proto), __cpparg(args),		\
-		__cpparg(tstruct), __cpparg(assign), __cpparg(print))	\
+	TRACE_EVENT(name, PARAMS(proto), PARAMS(args),			\
+		PARAMS(tstruct), PARAMS(assign), PARAMS(print))		\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
@@ -145,7 +142,7 @@
  *	struct trace_seq *s = &iter->seq;
  *	struct ftrace_raw_<call> *field; <-- defined in stage 1
  *	struct trace_entry *entry;
- *	struct trace_seq *p;
+ *	struct trace_seq *p = &iter->tmp_seq;
  *	int ret;
  *
  *	entry = iter->ent;
@@ -157,12 +154,10 @@
  *
  *	field = (typeof(field))entry;
  *
- *	p = &get_cpu_var(ftrace_event_seq);
  *	trace_seq_init(p);
  *	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;
  *
@@ -216,7 +211,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 	struct trace_seq *s = &iter->seq;				\
 	struct ftrace_raw_##call *field;				\
 	struct trace_entry *entry;					\
-	struct trace_seq *p;						\
+	struct trace_seq *p = &iter->tmp_seq;				\
 	int ret;							\
 									\
 	event = container_of(trace_event, struct ftrace_event_call,	\
@@ -231,12 +226,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 									\
 	field = (typeof(field))entry;					\
 									\
-	p = &get_cpu_var(ftrace_event_seq);				\
 	trace_seq_init(p);						\
 	ret = trace_seq_printf(s, "%s: ", event->name);			\
 	if (ret)							\
 		ret = trace_seq_printf(s, print);			\
-	put_cpu();							\
 	if (!ret)							\
 		return TRACE_TYPE_PARTIAL_LINE;				\
 									\
@@ -255,7 +248,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 	struct trace_seq *s = &iter->seq;				\
 	struct ftrace_raw_##template *field;				\
 	struct trace_entry *entry;					\
-	struct trace_seq *p;						\
+	struct trace_seq *p = &iter->tmp_seq;				\
 	int ret;							\
 									\
 	entry = iter->ent;						\
@@ -267,12 +260,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 									\
 	field = (typeof(field))entry;					\
 									\
-	p = &get_cpu_var(ftrace_event_seq);				\
 	trace_seq_init(p);						\
 	ret = trace_seq_printf(s, "%s: ", #call);			\
 	if (ret)							\
 		ret = trace_seq_printf(s, print);			\
-	put_cpu();							\
 	if (!ret)							\
 		return TRACE_TYPE_PARTIAL_LINE;				\
 									\
@@ -439,6 +430,7 @@ 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 +559,7 @@ 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 +698,7 @@ 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;